Add files using upload-large-folder tool
Browse files- README.md +68 -0
- checkpoint-100/added_tokens.json +24 -0
- checkpoint-100/chat_template.jinja +54 -0
- checkpoint-100/config.json +66 -0
- checkpoint-100/generation_config.json +14 -0
- checkpoint-100/special_tokens_map.json +31 -0
- checkpoint-100/tokenizer_config.json +207 -0
- checkpoint-150/added_tokens.json +24 -0
- checkpoint-150/chat_template.jinja +54 -0
- checkpoint-150/model.safetensors.index.json +443 -0
- checkpoint-150/tokenizer_config.json +207 -0
- checkpoint-150/trainer_state.json +0 -0
- checkpoint-200/added_tokens.json +24 -0
- checkpoint-200/config.json +66 -0
- checkpoint-200/generation_config.json +14 -0
- checkpoint-200/model.safetensors.index.json +443 -0
- checkpoint-200/special_tokens_map.json +31 -0
- checkpoint-200/trainer_state.json +0 -0
- checkpoint-250/added_tokens.json +24 -0
- checkpoint-250/generation_config.json +14 -0
- checkpoint-250/model.safetensors.index.json +443 -0
- checkpoint-250/special_tokens_map.json +31 -0
- checkpoint-250/tokenizer_config.json +207 -0
- checkpoint-250/trainer_state.json +0 -0
- checkpoint-250/vocab.json +0 -0
- checkpoint-300/added_tokens.json +24 -0
- checkpoint-300/config.json +66 -0
- checkpoint-300/generation_config.json +14 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/model.safetensors.index.json +443 -0
- checkpoint-300/special_tokens_map.json +31 -0
- checkpoint-300/trainer_state.json +0 -0
- checkpoint-300/vocab.json +0 -0
- checkpoint-350/added_tokens.json +24 -0
- checkpoint-350/chat_template.jinja +54 -0
- checkpoint-350/config.json +66 -0
- checkpoint-350/generation_config.json +14 -0
- checkpoint-350/merges.txt +0 -0
- checkpoint-350/special_tokens_map.json +31 -0
- checkpoint-350/tokenizer_config.json +207 -0
- checkpoint-350/trainer_state.json +0 -0
- checkpoint-350/vocab.json +0 -0
- checkpoint-50/added_tokens.json +24 -0
- checkpoint-50/chat_template.jinja +54 -0
- checkpoint-50/config.json +66 -0
- checkpoint-50/generation_config.json +14 -0
- checkpoint-50/merges.txt +0 -0
- checkpoint-50/model.safetensors.index.json +443 -0
- checkpoint-50/trainer_state.json +1184 -0
- checkpoint-50/vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-3B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-3B-Instruct-IF-ICRM-hf
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- grpo
|
| 8 |
+
- trl
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-3B-Instruct-IF-ICRM-hf
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jiwooya1000/ICRM-RLHF/runs/5dfch2ds)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.22.2
|
| 38 |
+
- Transformers: 4.55.2
|
| 39 |
+
- Pytorch: 2.8.0
|
| 40 |
+
- Datasets: 4.1.0
|
| 41 |
+
- Tokenizers: 0.21.4
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
Cite GRPO as:
|
| 46 |
+
|
| 47 |
+
```bibtex
|
| 48 |
+
@article{shao2024deepseekmath,
|
| 49 |
+
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
| 50 |
+
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
| 51 |
+
year = 2024,
|
| 52 |
+
eprint = {arXiv:2402.03300},
|
| 53 |
+
}
|
| 54 |
+
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
Cite TRL as:
|
| 58 |
+
|
| 59 |
+
```bibtex
|
| 60 |
+
@misc{vonwerra2022trl,
|
| 61 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 62 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 63 |
+
year = 2020,
|
| 64 |
+
journal = {GitHub repository},
|
| 65 |
+
publisher = {GitHub},
|
| 66 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 67 |
+
}
|
| 68 |
+
```
|
checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-100/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.55.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-150/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-150/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-150/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 771484672,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
checkpoint-150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-150/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.55.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-200/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 771484672,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-250/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-250/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-250/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 771484672,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
checkpoint-250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-250/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-250/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.55.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
checkpoint-300/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 771484672,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-350/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-350/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-350/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.55.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
checkpoint-350/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-350/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-350/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-350/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-350/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-350/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-50/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-50/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-50/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.55.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
checkpoint-50/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
checkpoint-50/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-50/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 771484672,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,1184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03765060240963856,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 50,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"clip_ratio": 0.0,
|
| 14 |
+
"completions/clipped_ratio": 0.005859375,
|
| 15 |
+
"completions/max_length": 1536.0,
|
| 16 |
+
"completions/max_terminated_length": 1461.0,
|
| 17 |
+
"completions/mean_length": 539.939453125,
|
| 18 |
+
"completions/mean_terminated_length": 534.0687866210938,
|
| 19 |
+
"completions/min_length": 150.0,
|
| 20 |
+
"completions/min_terminated_length": 150.0,
|
| 21 |
+
"epoch": 0.0007530120481927711,
|
| 22 |
+
"frac_reward_zero_std": 0.0,
|
| 23 |
+
"grad_norm": 0.24425463378429413,
|
| 24 |
+
"learning_rate": 1e-06,
|
| 25 |
+
"loss": 0.0483,
|
| 26 |
+
"num_tokens": 322497.0,
|
| 27 |
+
"reward": 18.535240173339844,
|
| 28 |
+
"reward_std": 4.5626091957092285,
|
| 29 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 30 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 31 |
+
"rewards/skywork_reward/mean": 18.535240173339844,
|
| 32 |
+
"rewards/skywork_reward/std": 7.240255355834961,
|
| 33 |
+
"step": 1
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"clip_ratio": 0.0,
|
| 37 |
+
"completions/clipped_ratio": 0.001953125,
|
| 38 |
+
"completions/max_length": 1536.0,
|
| 39 |
+
"completions/max_terminated_length": 1313.0,
|
| 40 |
+
"completions/mean_length": 539.921875,
|
| 41 |
+
"completions/mean_terminated_length": 537.9725952148438,
|
| 42 |
+
"completions/min_length": 162.0,
|
| 43 |
+
"completions/min_terminated_length": 162.0,
|
| 44 |
+
"epoch": 0.0015060240963855422,
|
| 45 |
+
"frac_reward_zero_std": 0.0,
|
| 46 |
+
"grad_norm": 0.2527785897254944,
|
| 47 |
+
"learning_rate": 1e-06,
|
| 48 |
+
"loss": 0.0676,
|
| 49 |
+
"num_tokens": 642601.0,
|
| 50 |
+
"reward": 19.66384506225586,
|
| 51 |
+
"reward_std": 4.405518531799316,
|
| 52 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 53 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 54 |
+
"rewards/skywork_reward/mean": 19.66384506225586,
|
| 55 |
+
"rewards/skywork_reward/std": 7.860788822174072,
|
| 56 |
+
"step": 2
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"clip_ratio": 0.0,
|
| 60 |
+
"completions/clipped_ratio": 0.0,
|
| 61 |
+
"completions/max_length": 1096.0,
|
| 62 |
+
"completions/max_terminated_length": 1096.0,
|
| 63 |
+
"completions/mean_length": 509.203125,
|
| 64 |
+
"completions/mean_terminated_length": 509.203125,
|
| 65 |
+
"completions/min_length": 115.0,
|
| 66 |
+
"completions/min_terminated_length": 115.0,
|
| 67 |
+
"epoch": 0.002259036144578313,
|
| 68 |
+
"frac_reward_zero_std": 0.0,
|
| 69 |
+
"grad_norm": 0.23311284184455872,
|
| 70 |
+
"learning_rate": 1e-06,
|
| 71 |
+
"loss": 0.036,
|
| 72 |
+
"num_tokens": 948897.0,
|
| 73 |
+
"reward": 19.736499786376953,
|
| 74 |
+
"reward_std": 4.317551136016846,
|
| 75 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 76 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 77 |
+
"rewards/skywork_reward/mean": 19.736499786376953,
|
| 78 |
+
"rewards/skywork_reward/std": 8.241270065307617,
|
| 79 |
+
"step": 3
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"clip_ratio": 0.0,
|
| 83 |
+
"completions/clipped_ratio": 0.0,
|
| 84 |
+
"completions/max_length": 1332.0,
|
| 85 |
+
"completions/max_terminated_length": 1332.0,
|
| 86 |
+
"completions/mean_length": 481.34765625,
|
| 87 |
+
"completions/mean_terminated_length": 481.34765625,
|
| 88 |
+
"completions/min_length": 144.0,
|
| 89 |
+
"completions/min_terminated_length": 144.0,
|
| 90 |
+
"epoch": 0.0030120481927710845,
|
| 91 |
+
"frac_reward_zero_std": 0.0,
|
| 92 |
+
"grad_norm": 0.25114020705223083,
|
| 93 |
+
"learning_rate": 1e-06,
|
| 94 |
+
"loss": 0.037,
|
| 95 |
+
"num_tokens": 1240675.0,
|
| 96 |
+
"reward": 19.980758666992188,
|
| 97 |
+
"reward_std": 4.497593879699707,
|
| 98 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 99 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 100 |
+
"rewards/skywork_reward/mean": 19.980758666992188,
|
| 101 |
+
"rewards/skywork_reward/std": 7.561793804168701,
|
| 102 |
+
"step": 4
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"clip_ratio": 0.0,
|
| 106 |
+
"completions/clipped_ratio": 0.001953125,
|
| 107 |
+
"completions/max_length": 1536.0,
|
| 108 |
+
"completions/max_terminated_length": 1367.0,
|
| 109 |
+
"completions/mean_length": 550.08984375,
|
| 110 |
+
"completions/mean_terminated_length": 548.1604614257812,
|
| 111 |
+
"completions/min_length": 105.0,
|
| 112 |
+
"completions/min_terminated_length": 105.0,
|
| 113 |
+
"epoch": 0.0037650602409638554,
|
| 114 |
+
"frac_reward_zero_std": 0.0,
|
| 115 |
+
"grad_norm": 0.27846774458885193,
|
| 116 |
+
"learning_rate": 1e-06,
|
| 117 |
+
"loss": 0.06,
|
| 118 |
+
"num_tokens": 1567393.0,
|
| 119 |
+
"reward": 15.45170783996582,
|
| 120 |
+
"reward_std": 4.615124702453613,
|
| 121 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 122 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 123 |
+
"rewards/skywork_reward/mean": 15.45170783996582,
|
| 124 |
+
"rewards/skywork_reward/std": 7.330972194671631,
|
| 125 |
+
"step": 5
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"clip_ratio": 0.0,
|
| 129 |
+
"completions/clipped_ratio": 0.00390625,
|
| 130 |
+
"completions/max_length": 1536.0,
|
| 131 |
+
"completions/max_terminated_length": 1435.0,
|
| 132 |
+
"completions/mean_length": 466.416015625,
|
| 133 |
+
"completions/mean_terminated_length": 462.2215881347656,
|
| 134 |
+
"completions/min_length": 137.0,
|
| 135 |
+
"completions/min_terminated_length": 137.0,
|
| 136 |
+
"epoch": 0.004518072289156626,
|
| 137 |
+
"frac_reward_zero_std": 0.0,
|
| 138 |
+
"grad_norm": 0.26218029856681824,
|
| 139 |
+
"learning_rate": 1e-06,
|
| 140 |
+
"loss": 0.0554,
|
| 141 |
+
"num_tokens": 1848294.0,
|
| 142 |
+
"reward": 15.858068466186523,
|
| 143 |
+
"reward_std": 4.51039981842041,
|
| 144 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 145 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 146 |
+
"rewards/skywork_reward/mean": 15.858068466186523,
|
| 147 |
+
"rewards/skywork_reward/std": 8.340972900390625,
|
| 148 |
+
"step": 6
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"clip_ratio": 0.0,
|
| 152 |
+
"completions/clipped_ratio": 0.001953125,
|
| 153 |
+
"completions/max_length": 1536.0,
|
| 154 |
+
"completions/max_terminated_length": 1397.0,
|
| 155 |
+
"completions/mean_length": 546.90625,
|
| 156 |
+
"completions/mean_terminated_length": 544.9706420898438,
|
| 157 |
+
"completions/min_length": 127.0,
|
| 158 |
+
"completions/min_terminated_length": 127.0,
|
| 159 |
+
"epoch": 0.005271084337349397,
|
| 160 |
+
"frac_reward_zero_std": 0.0,
|
| 161 |
+
"grad_norm": 0.2502232789993286,
|
| 162 |
+
"learning_rate": 1e-06,
|
| 163 |
+
"loss": 0.0183,
|
| 164 |
+
"num_tokens": 2176214.0,
|
| 165 |
+
"reward": 20.738807678222656,
|
| 166 |
+
"reward_std": 4.506719589233398,
|
| 167 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 168 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 169 |
+
"rewards/skywork_reward/mean": 20.738807678222656,
|
| 170 |
+
"rewards/skywork_reward/std": 7.784599781036377,
|
| 171 |
+
"step": 7
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"clip_ratio": 0.0,
|
| 175 |
+
"completions/clipped_ratio": 0.001953125,
|
| 176 |
+
"completions/max_length": 1536.0,
|
| 177 |
+
"completions/max_terminated_length": 1344.0,
|
| 178 |
+
"completions/mean_length": 507.919921875,
|
| 179 |
+
"completions/mean_terminated_length": 505.90802001953125,
|
| 180 |
+
"completions/min_length": 149.0,
|
| 181 |
+
"completions/min_terminated_length": 149.0,
|
| 182 |
+
"epoch": 0.006024096385542169,
|
| 183 |
+
"frac_reward_zero_std": 0.0,
|
| 184 |
+
"grad_norm": 0.24587783217430115,
|
| 185 |
+
"learning_rate": 1e-06,
|
| 186 |
+
"loss": 0.0108,
|
| 187 |
+
"num_tokens": 2483485.0,
|
| 188 |
+
"reward": 18.190261840820312,
|
| 189 |
+
"reward_std": 4.080215930938721,
|
| 190 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 191 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 192 |
+
"rewards/skywork_reward/mean": 18.190261840820312,
|
| 193 |
+
"rewards/skywork_reward/std": 7.144257068634033,
|
| 194 |
+
"step": 8
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"clip_ratio": 0.0,
|
| 198 |
+
"completions/clipped_ratio": 0.00390625,
|
| 199 |
+
"completions/max_length": 1536.0,
|
| 200 |
+
"completions/max_terminated_length": 1392.0,
|
| 201 |
+
"completions/mean_length": 517.755859375,
|
| 202 |
+
"completions/mean_terminated_length": 513.7627563476562,
|
| 203 |
+
"completions/min_length": 147.0,
|
| 204 |
+
"completions/min_terminated_length": 147.0,
|
| 205 |
+
"epoch": 0.00677710843373494,
|
| 206 |
+
"frac_reward_zero_std": 0.0,
|
| 207 |
+
"grad_norm": 0.25550204515457153,
|
| 208 |
+
"learning_rate": 1e-06,
|
| 209 |
+
"loss": 0.0365,
|
| 210 |
+
"num_tokens": 2791968.0,
|
| 211 |
+
"reward": 18.123830795288086,
|
| 212 |
+
"reward_std": 3.959782838821411,
|
| 213 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 214 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 215 |
+
"rewards/skywork_reward/mean": 18.123830795288086,
|
| 216 |
+
"rewards/skywork_reward/std": 8.163817405700684,
|
| 217 |
+
"step": 9
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"clip_ratio": 0.0,
|
| 221 |
+
"completions/clipped_ratio": 0.001953125,
|
| 222 |
+
"completions/max_length": 1536.0,
|
| 223 |
+
"completions/max_terminated_length": 1385.0,
|
| 224 |
+
"completions/mean_length": 469.869140625,
|
| 225 |
+
"completions/mean_terminated_length": 467.78277587890625,
|
| 226 |
+
"completions/min_length": 119.0,
|
| 227 |
+
"completions/min_terminated_length": 119.0,
|
| 228 |
+
"epoch": 0.007530120481927711,
|
| 229 |
+
"frac_reward_zero_std": 0.0,
|
| 230 |
+
"grad_norm": 0.2836010456085205,
|
| 231 |
+
"learning_rate": 1e-06,
|
| 232 |
+
"loss": 0.0308,
|
| 233 |
+
"num_tokens": 3079901.0,
|
| 234 |
+
"reward": 19.304351806640625,
|
| 235 |
+
"reward_std": 4.372314453125,
|
| 236 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 237 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 238 |
+
"rewards/skywork_reward/mean": 19.304351806640625,
|
| 239 |
+
"rewards/skywork_reward/std": 7.716484069824219,
|
| 240 |
+
"step": 10
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"clip_ratio": 0.0,
|
| 244 |
+
"completions/clipped_ratio": 0.0,
|
| 245 |
+
"completions/max_length": 1485.0,
|
| 246 |
+
"completions/max_terminated_length": 1485.0,
|
| 247 |
+
"completions/mean_length": 500.615234375,
|
| 248 |
+
"completions/mean_terminated_length": 500.615234375,
|
| 249 |
+
"completions/min_length": 84.0,
|
| 250 |
+
"completions/min_terminated_length": 84.0,
|
| 251 |
+
"epoch": 0.008283132530120483,
|
| 252 |
+
"frac_reward_zero_std": 0.0,
|
| 253 |
+
"grad_norm": 0.246844083070755,
|
| 254 |
+
"learning_rate": 1e-06,
|
| 255 |
+
"loss": 0.0386,
|
| 256 |
+
"num_tokens": 3382520.0,
|
| 257 |
+
"reward": 18.477981567382812,
|
| 258 |
+
"reward_std": 4.108589172363281,
|
| 259 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 260 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 261 |
+
"rewards/skywork_reward/mean": 18.477981567382812,
|
| 262 |
+
"rewards/skywork_reward/std": 7.084549427032471,
|
| 263 |
+
"step": 11
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"clip_ratio": 0.0,
|
| 267 |
+
"completions/clipped_ratio": 0.0,
|
| 268 |
+
"completions/max_length": 1090.0,
|
| 269 |
+
"completions/max_terminated_length": 1090.0,
|
| 270 |
+
"completions/mean_length": 478.2578125,
|
| 271 |
+
"completions/mean_terminated_length": 478.2578125,
|
| 272 |
+
"completions/min_length": 202.0,
|
| 273 |
+
"completions/min_terminated_length": 202.0,
|
| 274 |
+
"epoch": 0.009036144578313253,
|
| 275 |
+
"frac_reward_zero_std": 0.0,
|
| 276 |
+
"grad_norm": 0.2760355472564697,
|
| 277 |
+
"learning_rate": 1e-06,
|
| 278 |
+
"loss": 0.0437,
|
| 279 |
+
"num_tokens": 3669020.0,
|
| 280 |
+
"reward": 18.244699478149414,
|
| 281 |
+
"reward_std": 4.524354457855225,
|
| 282 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 283 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 284 |
+
"rewards/skywork_reward/mean": 18.244699478149414,
|
| 285 |
+
"rewards/skywork_reward/std": 7.753305435180664,
|
| 286 |
+
"step": 12
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"clip_ratio": 0.0,
|
| 290 |
+
"completions/clipped_ratio": 0.00390625,
|
| 291 |
+
"completions/max_length": 1536.0,
|
| 292 |
+
"completions/max_terminated_length": 1359.0,
|
| 293 |
+
"completions/mean_length": 509.525390625,
|
| 294 |
+
"completions/mean_terminated_length": 505.5000305175781,
|
| 295 |
+
"completions/min_length": 139.0,
|
| 296 |
+
"completions/min_terminated_length": 139.0,
|
| 297 |
+
"epoch": 0.009789156626506024,
|
| 298 |
+
"frac_reward_zero_std": 0.0,
|
| 299 |
+
"grad_norm": 0.2421659678220749,
|
| 300 |
+
"learning_rate": 1e-06,
|
| 301 |
+
"loss": 0.0431,
|
| 302 |
+
"num_tokens": 3973577.0,
|
| 303 |
+
"reward": 18.84097671508789,
|
| 304 |
+
"reward_std": 3.6833090782165527,
|
| 305 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 306 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 307 |
+
"rewards/skywork_reward/mean": 18.84097671508789,
|
| 308 |
+
"rewards/skywork_reward/std": 7.0365753173828125,
|
| 309 |
+
"step": 13
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"clip_ratio": 0.0,
|
| 313 |
+
"completions/clipped_ratio": 0.0,
|
| 314 |
+
"completions/max_length": 986.0,
|
| 315 |
+
"completions/max_terminated_length": 986.0,
|
| 316 |
+
"completions/mean_length": 502.75,
|
| 317 |
+
"completions/mean_terminated_length": 502.75,
|
| 318 |
+
"completions/min_length": 201.0,
|
| 319 |
+
"completions/min_terminated_length": 201.0,
|
| 320 |
+
"epoch": 0.010542168674698794,
|
| 321 |
+
"frac_reward_zero_std": 0.0,
|
| 322 |
+
"grad_norm": 0.24300047755241394,
|
| 323 |
+
"learning_rate": 1e-06,
|
| 324 |
+
"loss": 0.0095,
|
| 325 |
+
"num_tokens": 4275273.0,
|
| 326 |
+
"reward": 19.73338508605957,
|
| 327 |
+
"reward_std": 3.7505850791931152,
|
| 328 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 329 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 330 |
+
"rewards/skywork_reward/mean": 19.73338508605957,
|
| 331 |
+
"rewards/skywork_reward/std": 7.851949691772461,
|
| 332 |
+
"step": 14
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"clip_ratio": 0.0,
|
| 336 |
+
"completions/clipped_ratio": 0.001953125,
|
| 337 |
+
"completions/max_length": 1536.0,
|
| 338 |
+
"completions/max_terminated_length": 1212.0,
|
| 339 |
+
"completions/mean_length": 495.01171875,
|
| 340 |
+
"completions/mean_terminated_length": 492.97454833984375,
|
| 341 |
+
"completions/min_length": 82.0,
|
| 342 |
+
"completions/min_terminated_length": 82.0,
|
| 343 |
+
"epoch": 0.011295180722891566,
|
| 344 |
+
"frac_reward_zero_std": 0.0,
|
| 345 |
+
"grad_norm": 0.24820354580879211,
|
| 346 |
+
"learning_rate": 1e-06,
|
| 347 |
+
"loss": 0.041,
|
| 348 |
+
"num_tokens": 4572607.0,
|
| 349 |
+
"reward": 20.985137939453125,
|
| 350 |
+
"reward_std": 3.9907798767089844,
|
| 351 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 352 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 353 |
+
"rewards/skywork_reward/mean": 20.985137939453125,
|
| 354 |
+
"rewards/skywork_reward/std": 7.5082783699035645,
|
| 355 |
+
"step": 15
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"clip_ratio": 0.0,
|
| 359 |
+
"completions/clipped_ratio": 0.0,
|
| 360 |
+
"completions/max_length": 1452.0,
|
| 361 |
+
"completions/max_terminated_length": 1452.0,
|
| 362 |
+
"completions/mean_length": 503.646484375,
|
| 363 |
+
"completions/mean_terminated_length": 503.646484375,
|
| 364 |
+
"completions/min_length": 167.0,
|
| 365 |
+
"completions/min_terminated_length": 167.0,
|
| 366 |
+
"epoch": 0.012048192771084338,
|
| 367 |
+
"frac_reward_zero_std": 0.0,
|
| 368 |
+
"grad_norm": 0.25032636523246765,
|
| 369 |
+
"learning_rate": 1e-06,
|
| 370 |
+
"loss": 0.0271,
|
| 371 |
+
"num_tokens": 4879242.0,
|
| 372 |
+
"reward": 19.479820251464844,
|
| 373 |
+
"reward_std": 3.9832570552825928,
|
| 374 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 375 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 376 |
+
"rewards/skywork_reward/mean": 19.479820251464844,
|
| 377 |
+
"rewards/skywork_reward/std": 7.7815022468566895,
|
| 378 |
+
"step": 16
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"clip_ratio": 0.0,
|
| 382 |
+
"completions/clipped_ratio": 0.001953125,
|
| 383 |
+
"completions/max_length": 1536.0,
|
| 384 |
+
"completions/max_terminated_length": 1505.0,
|
| 385 |
+
"completions/mean_length": 548.275390625,
|
| 386 |
+
"completions/mean_terminated_length": 546.3424682617188,
|
| 387 |
+
"completions/min_length": 183.0,
|
| 388 |
+
"completions/min_terminated_length": 183.0,
|
| 389 |
+
"epoch": 0.012801204819277108,
|
| 390 |
+
"frac_reward_zero_std": 0.0,
|
| 391 |
+
"grad_norm": 0.23289093375205994,
|
| 392 |
+
"learning_rate": 1e-06,
|
| 393 |
+
"loss": 0.0344,
|
| 394 |
+
"num_tokens": 5206471.0,
|
| 395 |
+
"reward": 18.09130859375,
|
| 396 |
+
"reward_std": 4.67989444732666,
|
| 397 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 398 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 399 |
+
"rewards/skywork_reward/mean": 18.09130859375,
|
| 400 |
+
"rewards/skywork_reward/std": 8.046331405639648,
|
| 401 |
+
"step": 17
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"clip_ratio": 0.0,
|
| 405 |
+
"completions/clipped_ratio": 0.0,
|
| 406 |
+
"completions/max_length": 1333.0,
|
| 407 |
+
"completions/max_terminated_length": 1333.0,
|
| 408 |
+
"completions/mean_length": 500.513671875,
|
| 409 |
+
"completions/mean_terminated_length": 500.513671875,
|
| 410 |
+
"completions/min_length": 105.0,
|
| 411 |
+
"completions/min_terminated_length": 105.0,
|
| 412 |
+
"epoch": 0.01355421686746988,
|
| 413 |
+
"frac_reward_zero_std": 0.0,
|
| 414 |
+
"grad_norm": 0.2743029296398163,
|
| 415 |
+
"learning_rate": 1e-06,
|
| 416 |
+
"loss": 0.0608,
|
| 417 |
+
"num_tokens": 5508110.0,
|
| 418 |
+
"reward": 19.004474639892578,
|
| 419 |
+
"reward_std": 4.812801361083984,
|
| 420 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 421 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 422 |
+
"rewards/skywork_reward/mean": 19.004474639892578,
|
| 423 |
+
"rewards/skywork_reward/std": 7.56382942199707,
|
| 424 |
+
"step": 18
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"clip_ratio": 0.0,
|
| 428 |
+
"completions/clipped_ratio": 0.001953125,
|
| 429 |
+
"completions/max_length": 1536.0,
|
| 430 |
+
"completions/max_terminated_length": 1300.0,
|
| 431 |
+
"completions/mean_length": 493.69921875,
|
| 432 |
+
"completions/mean_terminated_length": 491.65948486328125,
|
| 433 |
+
"completions/min_length": 173.0,
|
| 434 |
+
"completions/min_terminated_length": 173.0,
|
| 435 |
+
"epoch": 0.01430722891566265,
|
| 436 |
+
"frac_reward_zero_std": 0.0,
|
| 437 |
+
"grad_norm": 0.24759620428085327,
|
| 438 |
+
"learning_rate": 1e-06,
|
| 439 |
+
"loss": 0.0399,
|
| 440 |
+
"num_tokens": 5802532.0,
|
| 441 |
+
"reward": 20.18354034423828,
|
| 442 |
+
"reward_std": 4.097359657287598,
|
| 443 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 444 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 445 |
+
"rewards/skywork_reward/mean": 20.18354034423828,
|
| 446 |
+
"rewards/skywork_reward/std": 6.95109224319458,
|
| 447 |
+
"step": 19
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"clip_ratio": 0.0,
|
| 451 |
+
"completions/clipped_ratio": 0.00390625,
|
| 452 |
+
"completions/max_length": 1536.0,
|
| 453 |
+
"completions/max_terminated_length": 1506.0,
|
| 454 |
+
"completions/mean_length": 540.8828125,
|
| 455 |
+
"completions/mean_terminated_length": 536.9804077148438,
|
| 456 |
+
"completions/min_length": 141.0,
|
| 457 |
+
"completions/min_terminated_length": 141.0,
|
| 458 |
+
"epoch": 0.015060240963855422,
|
| 459 |
+
"frac_reward_zero_std": 0.0,
|
| 460 |
+
"grad_norm": 0.22581446170806885,
|
| 461 |
+
"learning_rate": 1e-06,
|
| 462 |
+
"loss": 0.0349,
|
| 463 |
+
"num_tokens": 6127912.0,
|
| 464 |
+
"reward": 18.810096740722656,
|
| 465 |
+
"reward_std": 4.296095848083496,
|
| 466 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 467 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 468 |
+
"rewards/skywork_reward/mean": 18.810096740722656,
|
| 469 |
+
"rewards/skywork_reward/std": 7.788106918334961,
|
| 470 |
+
"step": 20
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"clip_ratio": 0.0,
|
| 474 |
+
"completions/clipped_ratio": 0.005859375,
|
| 475 |
+
"completions/max_length": 1536.0,
|
| 476 |
+
"completions/max_terminated_length": 1486.0,
|
| 477 |
+
"completions/mean_length": 568.685546875,
|
| 478 |
+
"completions/mean_terminated_length": 562.9843139648438,
|
| 479 |
+
"completions/min_length": 141.0,
|
| 480 |
+
"completions/min_terminated_length": 141.0,
|
| 481 |
+
"epoch": 0.01581325301204819,
|
| 482 |
+
"frac_reward_zero_std": 0.0,
|
| 483 |
+
"grad_norm": 0.25190842151641846,
|
| 484 |
+
"learning_rate": 1e-06,
|
| 485 |
+
"loss": 0.031,
|
| 486 |
+
"num_tokens": 6462007.0,
|
| 487 |
+
"reward": 16.9500675201416,
|
| 488 |
+
"reward_std": 3.961681842803955,
|
| 489 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 490 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 491 |
+
"rewards/skywork_reward/mean": 16.9500675201416,
|
| 492 |
+
"rewards/skywork_reward/std": 7.946998119354248,
|
| 493 |
+
"step": 21
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"clip_ratio": 0.0,
|
| 497 |
+
"completions/clipped_ratio": 0.001953125,
|
| 498 |
+
"completions/max_length": 1536.0,
|
| 499 |
+
"completions/max_terminated_length": 1516.0,
|
| 500 |
+
"completions/mean_length": 536.982421875,
|
| 501 |
+
"completions/mean_terminated_length": 535.0274047851562,
|
| 502 |
+
"completions/min_length": 138.0,
|
| 503 |
+
"completions/min_terminated_length": 138.0,
|
| 504 |
+
"epoch": 0.016566265060240965,
|
| 505 |
+
"frac_reward_zero_std": 0.0,
|
| 506 |
+
"grad_norm": 0.23905393481254578,
|
| 507 |
+
"learning_rate": 1e-06,
|
| 508 |
+
"loss": 0.0237,
|
| 509 |
+
"num_tokens": 6777998.0,
|
| 510 |
+
"reward": 19.38282012939453,
|
| 511 |
+
"reward_std": 3.568166494369507,
|
| 512 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 513 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 514 |
+
"rewards/skywork_reward/mean": 19.38282012939453,
|
| 515 |
+
"rewards/skywork_reward/std": 8.19947624206543,
|
| 516 |
+
"step": 22
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"clip_ratio": 0.0,
|
| 520 |
+
"completions/clipped_ratio": 0.001953125,
|
| 521 |
+
"completions/max_length": 1536.0,
|
| 522 |
+
"completions/max_terminated_length": 1442.0,
|
| 523 |
+
"completions/mean_length": 564.58203125,
|
| 524 |
+
"completions/mean_terminated_length": 562.6810302734375,
|
| 525 |
+
"completions/min_length": 91.0,
|
| 526 |
+
"completions/min_terminated_length": 91.0,
|
| 527 |
+
"epoch": 0.017319277108433735,
|
| 528 |
+
"frac_reward_zero_std": 0.0,
|
| 529 |
+
"grad_norm": 0.24202950298786163,
|
| 530 |
+
"learning_rate": 1e-06,
|
| 531 |
+
"loss": 0.0379,
|
| 532 |
+
"num_tokens": 7113960.0,
|
| 533 |
+
"reward": 17.542194366455078,
|
| 534 |
+
"reward_std": 3.6086037158966064,
|
| 535 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 536 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 537 |
+
"rewards/skywork_reward/mean": 17.542194366455078,
|
| 538 |
+
"rewards/skywork_reward/std": 6.972787857055664,
|
| 539 |
+
"step": 23
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"clip_ratio": 0.0,
|
| 543 |
+
"completions/clipped_ratio": 0.009765625,
|
| 544 |
+
"completions/max_length": 1536.0,
|
| 545 |
+
"completions/max_terminated_length": 1526.0,
|
| 546 |
+
"completions/mean_length": 594.02734375,
|
| 547 |
+
"completions/mean_terminated_length": 584.7376708984375,
|
| 548 |
+
"completions/min_length": 157.0,
|
| 549 |
+
"completions/min_terminated_length": 157.0,
|
| 550 |
+
"epoch": 0.018072289156626505,
|
| 551 |
+
"frac_reward_zero_std": 0.0,
|
| 552 |
+
"grad_norm": 0.23193013668060303,
|
| 553 |
+
"learning_rate": 1e-06,
|
| 554 |
+
"loss": 0.0177,
|
| 555 |
+
"num_tokens": 7464662.0,
|
| 556 |
+
"reward": 19.02389907836914,
|
| 557 |
+
"reward_std": 4.250513076782227,
|
| 558 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 559 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 560 |
+
"rewards/skywork_reward/mean": 19.02389907836914,
|
| 561 |
+
"rewards/skywork_reward/std": 6.219736576080322,
|
| 562 |
+
"step": 24
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"clip_ratio": 0.0,
|
| 566 |
+
"completions/clipped_ratio": 0.001953125,
|
| 567 |
+
"completions/max_length": 1536.0,
|
| 568 |
+
"completions/max_terminated_length": 1258.0,
|
| 569 |
+
"completions/mean_length": 549.28125,
|
| 570 |
+
"completions/mean_terminated_length": 547.3502807617188,
|
| 571 |
+
"completions/min_length": 244.0,
|
| 572 |
+
"completions/min_terminated_length": 244.0,
|
| 573 |
+
"epoch": 0.01882530120481928,
|
| 574 |
+
"frac_reward_zero_std": 0.0,
|
| 575 |
+
"grad_norm": 0.24706406891345978,
|
| 576 |
+
"learning_rate": 1e-06,
|
| 577 |
+
"loss": 0.0544,
|
| 578 |
+
"num_tokens": 7789846.0,
|
| 579 |
+
"reward": 18.385107040405273,
|
| 580 |
+
"reward_std": 4.854748249053955,
|
| 581 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 582 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 583 |
+
"rewards/skywork_reward/mean": 18.385107040405273,
|
| 584 |
+
"rewards/skywork_reward/std": 7.241014003753662,
|
| 585 |
+
"step": 25
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"clip_ratio": 0.0,
|
| 589 |
+
"completions/clipped_ratio": 0.009765625,
|
| 590 |
+
"completions/max_length": 1536.0,
|
| 591 |
+
"completions/max_terminated_length": 1387.0,
|
| 592 |
+
"completions/mean_length": 531.689453125,
|
| 593 |
+
"completions/mean_terminated_length": 521.7850341796875,
|
| 594 |
+
"completions/min_length": 180.0,
|
| 595 |
+
"completions/min_terminated_length": 180.0,
|
| 596 |
+
"epoch": 0.01957831325301205,
|
| 597 |
+
"frac_reward_zero_std": 0.0,
|
| 598 |
+
"grad_norm": 0.2525196373462677,
|
| 599 |
+
"learning_rate": 1e-06,
|
| 600 |
+
"loss": 0.0523,
|
| 601 |
+
"num_tokens": 8111927.0,
|
| 602 |
+
"reward": 19.272109985351562,
|
| 603 |
+
"reward_std": 3.762904167175293,
|
| 604 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 605 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 606 |
+
"rewards/skywork_reward/mean": 19.272109985351562,
|
| 607 |
+
"rewards/skywork_reward/std": 7.09940767288208,
|
| 608 |
+
"step": 26
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"clip_ratio": 0.0,
|
| 612 |
+
"completions/clipped_ratio": 0.001953125,
|
| 613 |
+
"completions/max_length": 1536.0,
|
| 614 |
+
"completions/max_terminated_length": 1308.0,
|
| 615 |
+
"completions/mean_length": 547.365234375,
|
| 616 |
+
"completions/mean_terminated_length": 545.4305419921875,
|
| 617 |
+
"completions/min_length": 145.0,
|
| 618 |
+
"completions/min_terminated_length": 145.0,
|
| 619 |
+
"epoch": 0.02033132530120482,
|
| 620 |
+
"frac_reward_zero_std": 0.0,
|
| 621 |
+
"grad_norm": 0.2493782937526703,
|
| 622 |
+
"learning_rate": 1e-06,
|
| 623 |
+
"loss": 0.0507,
|
| 624 |
+
"num_tokens": 8435202.0,
|
| 625 |
+
"reward": 17.78737449645996,
|
| 626 |
+
"reward_std": 4.015490531921387,
|
| 627 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 628 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 629 |
+
"rewards/skywork_reward/mean": 17.78737449645996,
|
| 630 |
+
"rewards/skywork_reward/std": 7.691453456878662,
|
| 631 |
+
"step": 27
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"clip_ratio": 0.0,
|
| 635 |
+
"completions/clipped_ratio": 0.0,
|
| 636 |
+
"completions/max_length": 1301.0,
|
| 637 |
+
"completions/max_terminated_length": 1301.0,
|
| 638 |
+
"completions/mean_length": 478.685546875,
|
| 639 |
+
"completions/mean_terminated_length": 478.685546875,
|
| 640 |
+
"completions/min_length": 149.0,
|
| 641 |
+
"completions/min_terminated_length": 149.0,
|
| 642 |
+
"epoch": 0.02108433734939759,
|
| 643 |
+
"frac_reward_zero_std": 0.0,
|
| 644 |
+
"grad_norm": 0.26527339220046997,
|
| 645 |
+
"learning_rate": 1e-06,
|
| 646 |
+
"loss": 0.0339,
|
| 647 |
+
"num_tokens": 8727633.0,
|
| 648 |
+
"reward": 18.366004943847656,
|
| 649 |
+
"reward_std": 3.85819411277771,
|
| 650 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 651 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 652 |
+
"rewards/skywork_reward/mean": 18.366004943847656,
|
| 653 |
+
"rewards/skywork_reward/std": 6.539942264556885,
|
| 654 |
+
"step": 28
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"clip_ratio": 0.0,
|
| 658 |
+
"completions/clipped_ratio": 0.0,
|
| 659 |
+
"completions/max_length": 1473.0,
|
| 660 |
+
"completions/max_terminated_length": 1473.0,
|
| 661 |
+
"completions/mean_length": 509.15234375,
|
| 662 |
+
"completions/mean_terminated_length": 509.15234375,
|
| 663 |
+
"completions/min_length": 99.0,
|
| 664 |
+
"completions/min_terminated_length": 99.0,
|
| 665 |
+
"epoch": 0.021837349397590362,
|
| 666 |
+
"frac_reward_zero_std": 0.0,
|
| 667 |
+
"grad_norm": 0.2530669867992401,
|
| 668 |
+
"learning_rate": 1e-06,
|
| 669 |
+
"loss": 0.0226,
|
| 670 |
+
"num_tokens": 9036511.0,
|
| 671 |
+
"reward": 18.36314582824707,
|
| 672 |
+
"reward_std": 3.6422839164733887,
|
| 673 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 674 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 675 |
+
"rewards/skywork_reward/mean": 18.36314582824707,
|
| 676 |
+
"rewards/skywork_reward/std": 7.377774715423584,
|
| 677 |
+
"step": 29
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"clip_ratio": 0.0,
|
| 681 |
+
"completions/clipped_ratio": 0.001953125,
|
| 682 |
+
"completions/max_length": 1536.0,
|
| 683 |
+
"completions/max_terminated_length": 1452.0,
|
| 684 |
+
"completions/mean_length": 523.609375,
|
| 685 |
+
"completions/mean_terminated_length": 521.628173828125,
|
| 686 |
+
"completions/min_length": 139.0,
|
| 687 |
+
"completions/min_terminated_length": 139.0,
|
| 688 |
+
"epoch": 0.022590361445783132,
|
| 689 |
+
"frac_reward_zero_std": 0.0,
|
| 690 |
+
"grad_norm": 0.24128130078315735,
|
| 691 |
+
"learning_rate": 1e-06,
|
| 692 |
+
"loss": 0.0412,
|
| 693 |
+
"num_tokens": 9345751.0,
|
| 694 |
+
"reward": 20.08295440673828,
|
| 695 |
+
"reward_std": 3.875840902328491,
|
| 696 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 697 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 698 |
+
"rewards/skywork_reward/mean": 20.08295440673828,
|
| 699 |
+
"rewards/skywork_reward/std": 7.567595958709717,
|
| 700 |
+
"step": 30
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"clip_ratio": 0.0,
|
| 704 |
+
"completions/clipped_ratio": 0.00390625,
|
| 705 |
+
"completions/max_length": 1536.0,
|
| 706 |
+
"completions/max_terminated_length": 1503.0,
|
| 707 |
+
"completions/mean_length": 516.138671875,
|
| 708 |
+
"completions/mean_terminated_length": 512.1392211914062,
|
| 709 |
+
"completions/min_length": 169.0,
|
| 710 |
+
"completions/min_terminated_length": 169.0,
|
| 711 |
+
"epoch": 0.023343373493975902,
|
| 712 |
+
"frac_reward_zero_std": 0.0,
|
| 713 |
+
"grad_norm": 0.2687889337539673,
|
| 714 |
+
"learning_rate": 1e-06,
|
| 715 |
+
"loss": 0.0406,
|
| 716 |
+
"num_tokens": 9651646.0,
|
| 717 |
+
"reward": 18.440399169921875,
|
| 718 |
+
"reward_std": 4.034783363342285,
|
| 719 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 720 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 721 |
+
"rewards/skywork_reward/mean": 18.440399169921875,
|
| 722 |
+
"rewards/skywork_reward/std": 9.241204261779785,
|
| 723 |
+
"step": 31
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"clip_ratio": 0.0,
|
| 727 |
+
"completions/clipped_ratio": 0.0,
|
| 728 |
+
"completions/max_length": 1351.0,
|
| 729 |
+
"completions/max_terminated_length": 1351.0,
|
| 730 |
+
"completions/mean_length": 509.87109375,
|
| 731 |
+
"completions/mean_terminated_length": 509.87109375,
|
| 732 |
+
"completions/min_length": 136.0,
|
| 733 |
+
"completions/min_terminated_length": 136.0,
|
| 734 |
+
"epoch": 0.024096385542168676,
|
| 735 |
+
"frac_reward_zero_std": 0.0,
|
| 736 |
+
"grad_norm": 0.2565000653266907,
|
| 737 |
+
"learning_rate": 1e-06,
|
| 738 |
+
"loss": 0.0341,
|
| 739 |
+
"num_tokens": 9958156.0,
|
| 740 |
+
"reward": 21.218032836914062,
|
| 741 |
+
"reward_std": 3.8647594451904297,
|
| 742 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 743 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 744 |
+
"rewards/skywork_reward/mean": 21.218032836914062,
|
| 745 |
+
"rewards/skywork_reward/std": 7.692581653594971,
|
| 746 |
+
"step": 32
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"clip_ratio": 0.0,
|
| 750 |
+
"completions/clipped_ratio": 0.001953125,
|
| 751 |
+
"completions/max_length": 1536.0,
|
| 752 |
+
"completions/max_terminated_length": 1272.0,
|
| 753 |
+
"completions/mean_length": 483.21484375,
|
| 754 |
+
"completions/mean_terminated_length": 481.15460205078125,
|
| 755 |
+
"completions/min_length": 47.0,
|
| 756 |
+
"completions/min_terminated_length": 47.0,
|
| 757 |
+
"epoch": 0.024849397590361446,
|
| 758 |
+
"frac_reward_zero_std": 0.0,
|
| 759 |
+
"grad_norm": 0.2624817490577698,
|
| 760 |
+
"learning_rate": 1e-06,
|
| 761 |
+
"loss": 0.0431,
|
| 762 |
+
"num_tokens": 10249610.0,
|
| 763 |
+
"reward": 19.79848861694336,
|
| 764 |
+
"reward_std": 4.353243827819824,
|
| 765 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 766 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 767 |
+
"rewards/skywork_reward/mean": 19.79848861694336,
|
| 768 |
+
"rewards/skywork_reward/std": 7.000552654266357,
|
| 769 |
+
"step": 33
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"clip_ratio": 0.0,
|
| 773 |
+
"completions/clipped_ratio": 0.0,
|
| 774 |
+
"completions/max_length": 1237.0,
|
| 775 |
+
"completions/max_terminated_length": 1237.0,
|
| 776 |
+
"completions/mean_length": 479.90234375,
|
| 777 |
+
"completions/mean_terminated_length": 479.90234375,
|
| 778 |
+
"completions/min_length": 135.0,
|
| 779 |
+
"completions/min_terminated_length": 135.0,
|
| 780 |
+
"epoch": 0.025602409638554216,
|
| 781 |
+
"frac_reward_zero_std": 0.0,
|
| 782 |
+
"grad_norm": 0.2779456377029419,
|
| 783 |
+
"learning_rate": 1e-06,
|
| 784 |
+
"loss": 0.0414,
|
| 785 |
+
"num_tokens": 10539784.0,
|
| 786 |
+
"reward": 18.208389282226562,
|
| 787 |
+
"reward_std": 3.7550158500671387,
|
| 788 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 789 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 790 |
+
"rewards/skywork_reward/mean": 18.208389282226562,
|
| 791 |
+
"rewards/skywork_reward/std": 7.102542400360107,
|
| 792 |
+
"step": 34
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"clip_ratio": 0.0,
|
| 796 |
+
"completions/clipped_ratio": 0.0,
|
| 797 |
+
"completions/max_length": 1438.0,
|
| 798 |
+
"completions/max_terminated_length": 1438.0,
|
| 799 |
+
"completions/mean_length": 538.0859375,
|
| 800 |
+
"completions/mean_terminated_length": 538.0859375,
|
| 801 |
+
"completions/min_length": 181.0,
|
| 802 |
+
"completions/min_terminated_length": 181.0,
|
| 803 |
+
"epoch": 0.02635542168674699,
|
| 804 |
+
"frac_reward_zero_std": 0.0,
|
| 805 |
+
"grad_norm": 0.27090051770210266,
|
| 806 |
+
"learning_rate": 1e-06,
|
| 807 |
+
"loss": 0.0616,
|
| 808 |
+
"num_tokens": 10861060.0,
|
| 809 |
+
"reward": 18.551515579223633,
|
| 810 |
+
"reward_std": 4.775388717651367,
|
| 811 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 812 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 813 |
+
"rewards/skywork_reward/mean": 18.551515579223633,
|
| 814 |
+
"rewards/skywork_reward/std": 8.144341468811035,
|
| 815 |
+
"step": 35
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"clip_ratio": 0.0,
|
| 819 |
+
"completions/clipped_ratio": 0.001953125,
|
| 820 |
+
"completions/max_length": 1536.0,
|
| 821 |
+
"completions/max_terminated_length": 1414.0,
|
| 822 |
+
"completions/mean_length": 523.318359375,
|
| 823 |
+
"completions/mean_terminated_length": 521.3366088867188,
|
| 824 |
+
"completions/min_length": 161.0,
|
| 825 |
+
"completions/min_terminated_length": 161.0,
|
| 826 |
+
"epoch": 0.02710843373493976,
|
| 827 |
+
"frac_reward_zero_std": 0.0,
|
| 828 |
+
"grad_norm": 0.24933283030986786,
|
| 829 |
+
"learning_rate": 1e-06,
|
| 830 |
+
"loss": 0.0219,
|
| 831 |
+
"num_tokens": 11174711.0,
|
| 832 |
+
"reward": 19.23906707763672,
|
| 833 |
+
"reward_std": 3.579415798187256,
|
| 834 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 835 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 836 |
+
"rewards/skywork_reward/mean": 19.23906707763672,
|
| 837 |
+
"rewards/skywork_reward/std": 6.7693352699279785,
|
| 838 |
+
"step": 36
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"clip_ratio": 0.0,
|
| 842 |
+
"completions/clipped_ratio": 0.0,
|
| 843 |
+
"completions/max_length": 1471.0,
|
| 844 |
+
"completions/max_terminated_length": 1471.0,
|
| 845 |
+
"completions/mean_length": 540.38671875,
|
| 846 |
+
"completions/mean_terminated_length": 540.38671875,
|
| 847 |
+
"completions/min_length": 112.0,
|
| 848 |
+
"completions/min_terminated_length": 112.0,
|
| 849 |
+
"epoch": 0.02786144578313253,
|
| 850 |
+
"frac_reward_zero_std": 0.0,
|
| 851 |
+
"grad_norm": 0.2600509524345398,
|
| 852 |
+
"learning_rate": 1e-06,
|
| 853 |
+
"loss": 0.0552,
|
| 854 |
+
"num_tokens": 11499629.0,
|
| 855 |
+
"reward": 17.48117446899414,
|
| 856 |
+
"reward_std": 4.680095672607422,
|
| 857 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 858 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 859 |
+
"rewards/skywork_reward/mean": 17.48117446899414,
|
| 860 |
+
"rewards/skywork_reward/std": 7.522308826446533,
|
| 861 |
+
"step": 37
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"clip_ratio": 0.0,
|
| 865 |
+
"completions/clipped_ratio": 0.001953125,
|
| 866 |
+
"completions/max_length": 1536.0,
|
| 867 |
+
"completions/max_terminated_length": 1324.0,
|
| 868 |
+
"completions/mean_length": 527.3359375,
|
| 869 |
+
"completions/mean_terminated_length": 525.362060546875,
|
| 870 |
+
"completions/min_length": 178.0,
|
| 871 |
+
"completions/min_terminated_length": 178.0,
|
| 872 |
+
"epoch": 0.0286144578313253,
|
| 873 |
+
"frac_reward_zero_std": 0.0,
|
| 874 |
+
"grad_norm": 0.2569137215614319,
|
| 875 |
+
"learning_rate": 1e-06,
|
| 876 |
+
"loss": 0.0256,
|
| 877 |
+
"num_tokens": 11812185.0,
|
| 878 |
+
"reward": 19.502559661865234,
|
| 879 |
+
"reward_std": 4.2003655433654785,
|
| 880 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 881 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 882 |
+
"rewards/skywork_reward/mean": 19.502559661865234,
|
| 883 |
+
"rewards/skywork_reward/std": 7.574954986572266,
|
| 884 |
+
"step": 38
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"clip_ratio": 0.0,
|
| 888 |
+
"completions/clipped_ratio": 0.005859375,
|
| 889 |
+
"completions/max_length": 1536.0,
|
| 890 |
+
"completions/max_terminated_length": 1497.0,
|
| 891 |
+
"completions/mean_length": 546.02734375,
|
| 892 |
+
"completions/mean_terminated_length": 540.1925659179688,
|
| 893 |
+
"completions/min_length": 201.0,
|
| 894 |
+
"completions/min_terminated_length": 201.0,
|
| 895 |
+
"epoch": 0.029367469879518073,
|
| 896 |
+
"frac_reward_zero_std": 0.0,
|
| 897 |
+
"grad_norm": 0.25866448879241943,
|
| 898 |
+
"learning_rate": 1e-06,
|
| 899 |
+
"loss": 0.0702,
|
| 900 |
+
"num_tokens": 12136471.0,
|
| 901 |
+
"reward": 19.45880889892578,
|
| 902 |
+
"reward_std": 4.22914457321167,
|
| 903 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 904 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 905 |
+
"rewards/skywork_reward/mean": 19.45880889892578,
|
| 906 |
+
"rewards/skywork_reward/std": 7.417150497436523,
|
| 907 |
+
"step": 39
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"clip_ratio": 0.0,
|
| 911 |
+
"completions/clipped_ratio": 0.005859375,
|
| 912 |
+
"completions/max_length": 1536.0,
|
| 913 |
+
"completions/max_terminated_length": 1300.0,
|
| 914 |
+
"completions/mean_length": 549.212890625,
|
| 915 |
+
"completions/mean_terminated_length": 543.3968505859375,
|
| 916 |
+
"completions/min_length": 106.0,
|
| 917 |
+
"completions/min_terminated_length": 106.0,
|
| 918 |
+
"epoch": 0.030120481927710843,
|
| 919 |
+
"frac_reward_zero_std": 0.0,
|
| 920 |
+
"grad_norm": 0.26242557168006897,
|
| 921 |
+
"learning_rate": 1e-06,
|
| 922 |
+
"loss": 0.0572,
|
| 923 |
+
"num_tokens": 12468676.0,
|
| 924 |
+
"reward": 18.719432830810547,
|
| 925 |
+
"reward_std": 4.223837852478027,
|
| 926 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 927 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 928 |
+
"rewards/skywork_reward/mean": 18.719432830810547,
|
| 929 |
+
"rewards/skywork_reward/std": 7.981883525848389,
|
| 930 |
+
"step": 40
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"clip_ratio": 0.0,
|
| 934 |
+
"completions/clipped_ratio": 0.005859375,
|
| 935 |
+
"completions/max_length": 1536.0,
|
| 936 |
+
"completions/max_terminated_length": 1474.0,
|
| 937 |
+
"completions/mean_length": 592.703125,
|
| 938 |
+
"completions/mean_terminated_length": 587.1434326171875,
|
| 939 |
+
"completions/min_length": 206.0,
|
| 940 |
+
"completions/min_terminated_length": 206.0,
|
| 941 |
+
"epoch": 0.030873493975903613,
|
| 942 |
+
"frac_reward_zero_std": 0.0,
|
| 943 |
+
"grad_norm": 0.23195688426494598,
|
| 944 |
+
"learning_rate": 1e-06,
|
| 945 |
+
"loss": 0.0277,
|
| 946 |
+
"num_tokens": 12819564.0,
|
| 947 |
+
"reward": 19.721298217773438,
|
| 948 |
+
"reward_std": 4.098422527313232,
|
| 949 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 950 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 951 |
+
"rewards/skywork_reward/mean": 19.721298217773438,
|
| 952 |
+
"rewards/skywork_reward/std": 8.307689666748047,
|
| 953 |
+
"step": 41
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"clip_ratio": 0.0,
|
| 957 |
+
"completions/clipped_ratio": 0.00390625,
|
| 958 |
+
"completions/max_length": 1536.0,
|
| 959 |
+
"completions/max_terminated_length": 1385.0,
|
| 960 |
+
"completions/mean_length": 505.2734375,
|
| 961 |
+
"completions/mean_terminated_length": 501.2314147949219,
|
| 962 |
+
"completions/min_length": 163.0,
|
| 963 |
+
"completions/min_terminated_length": 163.0,
|
| 964 |
+
"epoch": 0.03162650602409638,
|
| 965 |
+
"frac_reward_zero_std": 0.0,
|
| 966 |
+
"grad_norm": 0.26936817169189453,
|
| 967 |
+
"learning_rate": 1e-06,
|
| 968 |
+
"loss": 0.0703,
|
| 969 |
+
"num_tokens": 13120760.0,
|
| 970 |
+
"reward": 19.512004852294922,
|
| 971 |
+
"reward_std": 4.078932762145996,
|
| 972 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 973 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 974 |
+
"rewards/skywork_reward/mean": 19.512004852294922,
|
| 975 |
+
"rewards/skywork_reward/std": 7.664077281951904,
|
| 976 |
+
"step": 42
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"clip_ratio": 0.0,
|
| 980 |
+
"completions/clipped_ratio": 0.001953125,
|
| 981 |
+
"completions/max_length": 1536.0,
|
| 982 |
+
"completions/max_terminated_length": 1478.0,
|
| 983 |
+
"completions/mean_length": 525.787109375,
|
| 984 |
+
"completions/mean_terminated_length": 523.8101806640625,
|
| 985 |
+
"completions/min_length": 132.0,
|
| 986 |
+
"completions/min_terminated_length": 132.0,
|
| 987 |
+
"epoch": 0.03237951807228916,
|
| 988 |
+
"frac_reward_zero_std": 0.0,
|
| 989 |
+
"grad_norm": 0.25450485944747925,
|
| 990 |
+
"learning_rate": 1e-06,
|
| 991 |
+
"loss": 0.0453,
|
| 992 |
+
"num_tokens": 13435275.0,
|
| 993 |
+
"reward": 19.4080810546875,
|
| 994 |
+
"reward_std": 4.121971130371094,
|
| 995 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 996 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 997 |
+
"rewards/skywork_reward/mean": 19.4080810546875,
|
| 998 |
+
"rewards/skywork_reward/std": 8.246720314025879,
|
| 999 |
+
"step": 43
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"clip_ratio": 0.0,
|
| 1003 |
+
"completions/clipped_ratio": 0.025390625,
|
| 1004 |
+
"completions/max_length": 1536.0,
|
| 1005 |
+
"completions/max_terminated_length": 1514.0,
|
| 1006 |
+
"completions/mean_length": 598.4140625,
|
| 1007 |
+
"completions/mean_terminated_length": 573.9879760742188,
|
| 1008 |
+
"completions/min_length": 203.0,
|
| 1009 |
+
"completions/min_terminated_length": 203.0,
|
| 1010 |
+
"epoch": 0.03313253012048193,
|
| 1011 |
+
"frac_reward_zero_std": 0.0,
|
| 1012 |
+
"grad_norm": 0.22897975146770477,
|
| 1013 |
+
"learning_rate": 1e-06,
|
| 1014 |
+
"loss": 0.0552,
|
| 1015 |
+
"num_tokens": 13792623.0,
|
| 1016 |
+
"reward": 19.808815002441406,
|
| 1017 |
+
"reward_std": 4.206421375274658,
|
| 1018 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1019 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1020 |
+
"rewards/skywork_reward/mean": 19.808815002441406,
|
| 1021 |
+
"rewards/skywork_reward/std": 8.275568008422852,
|
| 1022 |
+
"step": 44
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"clip_ratio": 0.0,
|
| 1026 |
+
"completions/clipped_ratio": 0.02734375,
|
| 1027 |
+
"completions/max_length": 1536.0,
|
| 1028 |
+
"completions/max_terminated_length": 1531.0,
|
| 1029 |
+
"completions/mean_length": 540.21875,
|
| 1030 |
+
"completions/mean_terminated_length": 512.224853515625,
|
| 1031 |
+
"completions/min_length": 122.0,
|
| 1032 |
+
"completions/min_terminated_length": 122.0,
|
| 1033 |
+
"epoch": 0.0338855421686747,
|
| 1034 |
+
"frac_reward_zero_std": 0.0,
|
| 1035 |
+
"grad_norm": 0.26464077830314636,
|
| 1036 |
+
"learning_rate": 1e-06,
|
| 1037 |
+
"loss": 0.084,
|
| 1038 |
+
"num_tokens": 14114543.0,
|
| 1039 |
+
"reward": 19.398923873901367,
|
| 1040 |
+
"reward_std": 4.753540992736816,
|
| 1041 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1042 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1043 |
+
"rewards/skywork_reward/mean": 19.398923873901367,
|
| 1044 |
+
"rewards/skywork_reward/std": 8.964569091796875,
|
| 1045 |
+
"step": 45
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"clip_ratio": 0.0,
|
| 1049 |
+
"completions/clipped_ratio": 0.0078125,
|
| 1050 |
+
"completions/max_length": 1536.0,
|
| 1051 |
+
"completions/max_terminated_length": 1331.0,
|
| 1052 |
+
"completions/mean_length": 550.970703125,
|
| 1053 |
+
"completions/mean_terminated_length": 543.2145385742188,
|
| 1054 |
+
"completions/min_length": 141.0,
|
| 1055 |
+
"completions/min_terminated_length": 141.0,
|
| 1056 |
+
"epoch": 0.03463855421686747,
|
| 1057 |
+
"frac_reward_zero_std": 0.0,
|
| 1058 |
+
"grad_norm": 0.26099711656570435,
|
| 1059 |
+
"learning_rate": 1e-06,
|
| 1060 |
+
"loss": 0.0685,
|
| 1061 |
+
"num_tokens": 14438880.0,
|
| 1062 |
+
"reward": 20.744400024414062,
|
| 1063 |
+
"reward_std": 4.4266676902771,
|
| 1064 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1065 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1066 |
+
"rewards/skywork_reward/mean": 20.744400024414062,
|
| 1067 |
+
"rewards/skywork_reward/std": 9.021385192871094,
|
| 1068 |
+
"step": 46
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"clip_ratio": 0.0,
|
| 1072 |
+
"completions/clipped_ratio": 0.001953125,
|
| 1073 |
+
"completions/max_length": 1536.0,
|
| 1074 |
+
"completions/max_terminated_length": 1476.0,
|
| 1075 |
+
"completions/mean_length": 555.751953125,
|
| 1076 |
+
"completions/mean_terminated_length": 553.8336791992188,
|
| 1077 |
+
"completions/min_length": 159.0,
|
| 1078 |
+
"completions/min_terminated_length": 159.0,
|
| 1079 |
+
"epoch": 0.035391566265060244,
|
| 1080 |
+
"frac_reward_zero_std": 0.0,
|
| 1081 |
+
"grad_norm": 0.23918218910694122,
|
| 1082 |
+
"learning_rate": 1e-06,
|
| 1083 |
+
"loss": 0.0153,
|
| 1084 |
+
"num_tokens": 14773041.0,
|
| 1085 |
+
"reward": 18.19009017944336,
|
| 1086 |
+
"reward_std": 3.2478275299072266,
|
| 1087 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1088 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1089 |
+
"rewards/skywork_reward/mean": 18.19009017944336,
|
| 1090 |
+
"rewards/skywork_reward/std": 8.022202491760254,
|
| 1091 |
+
"step": 47
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"clip_ratio": 0.0,
|
| 1095 |
+
"completions/clipped_ratio": 0.001953125,
|
| 1096 |
+
"completions/max_length": 1536.0,
|
| 1097 |
+
"completions/max_terminated_length": 1381.0,
|
| 1098 |
+
"completions/mean_length": 504.818359375,
|
| 1099 |
+
"completions/mean_terminated_length": 502.8003845214844,
|
| 1100 |
+
"completions/min_length": 163.0,
|
| 1101 |
+
"completions/min_terminated_length": 163.0,
|
| 1102 |
+
"epoch": 0.03614457831325301,
|
| 1103 |
+
"frac_reward_zero_std": 0.0,
|
| 1104 |
+
"grad_norm": 0.2639124095439911,
|
| 1105 |
+
"learning_rate": 1e-06,
|
| 1106 |
+
"loss": 0.0118,
|
| 1107 |
+
"num_tokens": 15076308.0,
|
| 1108 |
+
"reward": 18.888355255126953,
|
| 1109 |
+
"reward_std": 3.525162696838379,
|
| 1110 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1111 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1112 |
+
"rewards/skywork_reward/mean": 18.888355255126953,
|
| 1113 |
+
"rewards/skywork_reward/std": 7.233704090118408,
|
| 1114 |
+
"step": 48
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"clip_ratio": 0.0,
|
| 1118 |
+
"completions/clipped_ratio": 0.005859375,
|
| 1119 |
+
"completions/max_length": 1536.0,
|
| 1120 |
+
"completions/max_terminated_length": 1477.0,
|
| 1121 |
+
"completions/mean_length": 558.080078125,
|
| 1122 |
+
"completions/mean_terminated_length": 552.3163452148438,
|
| 1123 |
+
"completions/min_length": 171.0,
|
| 1124 |
+
"completions/min_terminated_length": 171.0,
|
| 1125 |
+
"epoch": 0.036897590361445784,
|
| 1126 |
+
"frac_reward_zero_std": 0.0,
|
| 1127 |
+
"grad_norm": 0.2637381851673126,
|
| 1128 |
+
"learning_rate": 1e-06,
|
| 1129 |
+
"loss": 0.061,
|
| 1130 |
+
"num_tokens": 15408557.0,
|
| 1131 |
+
"reward": 18.518508911132812,
|
| 1132 |
+
"reward_std": 4.11885929107666,
|
| 1133 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1134 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1135 |
+
"rewards/skywork_reward/mean": 18.518508911132812,
|
| 1136 |
+
"rewards/skywork_reward/std": 7.327213287353516,
|
| 1137 |
+
"step": 49
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"clip_ratio": 0.0,
|
| 1141 |
+
"completions/clipped_ratio": 0.015625,
|
| 1142 |
+
"completions/max_length": 1536.0,
|
| 1143 |
+
"completions/max_terminated_length": 1511.0,
|
| 1144 |
+
"completions/mean_length": 519.8359375,
|
| 1145 |
+
"completions/mean_terminated_length": 503.7063903808594,
|
| 1146 |
+
"completions/min_length": 216.0,
|
| 1147 |
+
"completions/min_terminated_length": 216.0,
|
| 1148 |
+
"epoch": 0.03765060240963856,
|
| 1149 |
+
"frac_reward_zero_std": 0.0,
|
| 1150 |
+
"grad_norm": 0.2628968060016632,
|
| 1151 |
+
"learning_rate": 1e-06,
|
| 1152 |
+
"loss": 0.052,
|
| 1153 |
+
"num_tokens": 15719481.0,
|
| 1154 |
+
"reward": 19.84031105041504,
|
| 1155 |
+
"reward_std": 3.317889928817749,
|
| 1156 |
+
"rewards/accuracy_reward/mean": 0.0,
|
| 1157 |
+
"rewards/accuracy_reward/std": 0.0,
|
| 1158 |
+
"rewards/skywork_reward/mean": 19.84031105041504,
|
| 1159 |
+
"rewards/skywork_reward/std": 7.0079755783081055,
|
| 1160 |
+
"step": 50
|
| 1161 |
+
}
|
| 1162 |
+
],
|
| 1163 |
+
"logging_steps": 1,
|
| 1164 |
+
"max_steps": 1328,
|
| 1165 |
+
"num_input_tokens_seen": 15719481,
|
| 1166 |
+
"num_train_epochs": 1,
|
| 1167 |
+
"save_steps": 50,
|
| 1168 |
+
"stateful_callbacks": {
|
| 1169 |
+
"TrainerControl": {
|
| 1170 |
+
"args": {
|
| 1171 |
+
"should_epoch_stop": false,
|
| 1172 |
+
"should_evaluate": false,
|
| 1173 |
+
"should_log": false,
|
| 1174 |
+
"should_save": true,
|
| 1175 |
+
"should_training_stop": false
|
| 1176 |
+
},
|
| 1177 |
+
"attributes": {}
|
| 1178 |
+
}
|
| 1179 |
+
},
|
| 1180 |
+
"total_flos": 0.0,
|
| 1181 |
+
"train_batch_size": 64,
|
| 1182 |
+
"trial_name": null,
|
| 1183 |
+
"trial_params": null
|
| 1184 |
+
}
|
checkpoint-50/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|