Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +181 -0
- added_tokens.json +60 -0
- chat_template.jinja +120 -0
- config.json +66 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +721 -0
- preprocessor_config.json +39 -0
- special_tokens_map.json +242 -0
- tokenizer.json +3 -0
- tokenizer_config.json +516 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: Qwen/Qwen3-VL-4B-Instruct
|
| 5 |
+
arxiv: 2602.21202
|
| 6 |
+
datasets:
|
| 7 |
+
- friedrichor/MSR-VTT
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
tags:
|
| 11 |
+
- video-retrieval
|
| 12 |
+
- multi-vector
|
| 13 |
+
- late-interaction
|
| 14 |
+
- colbert
|
| 15 |
+
- index-compression
|
| 16 |
+
- attention-guided-clustering
|
| 17 |
+
- text-to-video
|
| 18 |
+
- feature-extraction
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# AGC-Qwen3-VL-4B
|
| 22 |
+
|
| 23 |
+
This model applies **Attention-Guided Clustering (AGC)** to compress multi-vector video representations for efficient ColBERT-style late interaction retrieval. Model weights are initialized from [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) and finetuned on [MSR-VTT](https://huggingface.co/datasets/friedrichor/MSR-VTT) for text-to-video retrieval with bidirectional attention.
|
| 24 |
+
|
| 25 |
+
AGC compresses ~1300 video token vectors into a fixed budget of **32 vectors** (97.6% compression), while **matching or exceeding uncompressed retrieval performance**.
|
| 26 |
+
|
| 27 |
+
[](https://arxiv.org/abs/2602.21202)
|
| 28 |
+
[](https://github.com/hanxiangqin/omni-col-press)
|
| 29 |
+
[](https://opensource.org/licenses/MIT)
|
| 30 |
+
|
| 31 |
+
## Method Overview
|
| 32 |
+
|
| 33 |
+
AGC consists of three components:
|
| 34 |
+
|
| 35 |
+
1. **Attention-based Centroid Selection** — Learned universal query tokens are appended to the document token sequence. The attention weights from these learned tokens to document tokens at the last transformer layer produce saliency scores, identifying the most semantically important regions. The top-*m* tokens by saliency are selected as cluster centroids.
|
| 36 |
+
|
| 37 |
+
2. **Hard Clustering** — Every document token is assigned to its nearest centroid via cosine similarity, grouping related content into coherent clusters while preserving distinct semantic details.
|
| 38 |
+
|
| 39 |
+
3. **Weighted Aggregation** — Tokens within each cluster are aggregated into a single vector using saliency-weighted averaging, prioritizing informative tokens and maintaining gradient flow stable for training.
|
| 40 |
+
|
| 41 |
+
The resulting *m* compressed vectors are used with ColBERT-style MaxSim scoring for retrieval.
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
## Results on MSR-VTT
|
| 46 |
+
|
| 47 |
+
| Method | Tokens | R@1 | R@10 | nDCG@10 |
|
| 48 |
+
|---|---|---|---|---|
|
| 49 |
+
| OmniEmbed-7B | 1 | 51.5 | 83.2 | 67.1 |
|
| 50 |
+
| Video-ColBERT | 26 | 51.5 | 85.5 | 67.7 |
|
| 51 |
+
| Baseline (Ours, uncompressed) | 1318 | 55.7 | 88.3 | 71.9 |
|
| 52 |
+
| SeqResize | 32 | 53.3 | 86.9 | 69.9 |
|
| 53 |
+
| MemTok | 32 | 54.2 | 86.4 | 69.9 |
|
| 54 |
+
| H-Pool | 32 | 54.1 | 87.3 | 70.4 |
|
| 55 |
+
| **AGC-Qwen3-VL-4B (This model)** | **32** | **58.5** | **88.4** | **73.0** |
|
| 56 |
+
|
| 57 |
+
AGC at 32 tokens **outperforms the uncompressed baseline at R@1** while using only 2.4% of the original index size, demonstrating that compression reduces redundancy in multimodal representations. This Qwen3-VL-4B variant achieves the best MSR-VTT performance among the reported model sizes (see paper Table 7).
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
## Model Details
|
| 61 |
+
|
| 62 |
+
| | |
|
| 63 |
+
|---|---|
|
| 64 |
+
| **Initial weights** | Qwen3-VL-4B-Instruct |
|
| 65 |
+
| **Architecture** | Qwen3-VL with bidirectional attention |
|
| 66 |
+
| **Hidden dimension** | 2048 |
|
| 67 |
+
| **Compression method** | AGC (Attention-Guided Clustering) |
|
| 68 |
+
| **Universal query tokens** | 32 learned universal query tokens (`<\|mem0\|>` – `<\|mem31\|>`) |
|
| 69 |
+
| **Default budget** | 32 vectors per document |
|
| 70 |
+
| **Scoring** | ColBERT-style MaxSim (late interaction) |
|
| 71 |
+
| **Normalization** | L2-normalized embeddings |
|
| 72 |
+
| **Query prefix** | `"Query: "` |
|
| 73 |
+
| **Passage prefix** | `"Passage: "` |
|
| 74 |
+
| **Precision** | bfloat16 |
|
| 75 |
+
| **Training video frames** | 24 |
|
| 76 |
+
|
| 77 |
+
## Usage
|
| 78 |
+
|
| 79 |
+
```python
|
| 80 |
+
import torch
|
| 81 |
+
from transformers import AutoProcessor
|
| 82 |
+
from qwen_vl_utils import process_vision_info
|
| 83 |
+
|
| 84 |
+
from src.arguments import ModelArguments
|
| 85 |
+
from src.encoder.select_encoder import AttentionSelectEncoder
|
| 86 |
+
from src.models.qwen3_vl_embed.qwen3_vl_embed import Qwen3ForEmbedding
|
| 87 |
+
from src.utils import get_appending_token_strings
|
| 88 |
+
|
| 89 |
+
MODEL_ID = "PLACEHOLDER"
|
| 90 |
+
VIDEO_PATH = "PLACEHOLDER"
|
| 91 |
+
NUM_PROXY_TOKENS = 32
|
| 92 |
+
APPENDING_SUFFIX = "".join(get_appending_token_strings(NUM_PROXY_TOKENS))
|
| 93 |
+
|
| 94 |
+
# --- Setup ---
|
| 95 |
+
model_args = ModelArguments(
|
| 96 |
+
model_name_or_path=MODEL_ID,
|
| 97 |
+
pooling="select",
|
| 98 |
+
normalize=True,
|
| 99 |
+
num_appending_token=NUM_PROXY_TOKENS,
|
| 100 |
+
use_cluster_pooling=True,
|
| 101 |
+
use_attn_weight_cluster_pooling=True,
|
| 102 |
+
attn_implementation="flash_attention_2",
|
| 103 |
+
)
|
| 104 |
+
|
| 105 |
+
processor = AutoProcessor.from_pretrained(MODEL_ID)
|
| 106 |
+
model = AttentionSelectEncoder.load(
|
| 107 |
+
Qwen3ForEmbedding,
|
| 108 |
+
model_args,
|
| 109 |
+
attn_implementation=model_args.attn_implementation,
|
| 110 |
+
dtype=torch.bfloat16,
|
| 111 |
+
)
|
| 112 |
+
model = model.to("cuda").eval()
|
| 113 |
+
|
| 114 |
+
# --- Encode a video document ---
|
| 115 |
+
passage_messages = [
|
| 116 |
+
{
|
| 117 |
+
"role": "user",
|
| 118 |
+
"content": [
|
| 119 |
+
{"type": "text", "text": "Passage: "},
|
| 120 |
+
{"type": "video", "video": VIDEO_PATH, "nframes": 24, "max_pixels": 110592, "min_pixels": 98304},
|
| 121 |
+
],
|
| 122 |
+
}
|
| 123 |
+
]
|
| 124 |
+
text = processor.apply_chat_template(passage_messages, tokenize=False, add_generation_prompt=False)
|
| 125 |
+
text += APPENDING_SUFFIX
|
| 126 |
+
image_inputs, video_inputs, _ = process_vision_info(
|
| 127 |
+
passage_messages,
|
| 128 |
+
image_patch_size=16,
|
| 129 |
+
return_video_kwargs=True,
|
| 130 |
+
return_video_metadata=True,
|
| 131 |
+
)
|
| 132 |
+
video_inputs, video_metadatas = zip(*video_inputs)
|
| 133 |
+
video_inputs, video_metadatas = list(video_inputs), list(video_metadatas)
|
| 134 |
+
passage_inputs = processor(
|
| 135 |
+
text=[text],
|
| 136 |
+
videos=video_inputs,
|
| 137 |
+
video_metadata=video_metadatas,
|
| 138 |
+
do_resize=False,
|
| 139 |
+
do_sample_frames=False,
|
| 140 |
+
padding=True,
|
| 141 |
+
return_tensors="pt",
|
| 142 |
+
).to("cuda")
|
| 143 |
+
|
| 144 |
+
with torch.amp.autocast(device_type="cuda", dtype=torch.bfloat16):
|
| 145 |
+
with torch.inference_mode():
|
| 146 |
+
doc_embeddings, doc_mask = model.encode(passage_inputs, is_query=False)
|
| 147 |
+
print(doc_embeddings.shape)
|
| 148 |
+
# doc_embeddings: (1, 32, 2048) — 32 compressed AGC vectors
|
| 149 |
+
|
| 150 |
+
# --- Encode a text query ---
|
| 151 |
+
query_messages = [{"role": "user", "content": [{"type": "text", "text": "Query: a person is cooking"}]}]
|
| 152 |
+
query_text = processor.apply_chat_template(query_messages, tokenize=False, add_generation_prompt=False)
|
| 153 |
+
query_inputs = processor(text=[query_text], padding=True, return_tensors="pt").to("cuda")
|
| 154 |
+
|
| 155 |
+
with torch.amp.autocast(device_type="cuda", dtype=torch.bfloat16):
|
| 156 |
+
with torch.inference_mode():
|
| 157 |
+
query_embeddings, query_mask = model.encode(query_inputs, is_query=True)
|
| 158 |
+
print(query_embeddings.shape)
|
| 159 |
+
|
| 160 |
+
# --- ColBERT MaxSim scoring ---
|
| 161 |
+
score = model.compute_similarity(query_embeddings, doc_embeddings, query_mask, doc_mask)
|
| 162 |
+
print(f"Similarity score: {score.item():.4f}")
|
| 163 |
+
```
|
| 164 |
+
|
| 165 |
+
## Command line usage
|
| 166 |
+
|
| 167 |
+
For running inference and evaluation from the command line, see the [Quick Start](https://github.com/HanxiangQin/omni-col-press?tab=readme-ov-file#quick-start-1) section.
|
| 168 |
+
|
| 169 |
+
## Citation
|
| 170 |
+
|
| 171 |
+
```bibtex
|
| 172 |
+
@misc{qin2026multivectorindexcompressionmodality,
|
| 173 |
+
title={Multi-Vector Index Compression in Any Modality},
|
| 174 |
+
author={Hanxiang Qin and Alexander Martin and Rohan Jha and Chunsheng Zuo and Reno Kriz and Benjamin Van Durme},
|
| 175 |
+
year={2026},
|
| 176 |
+
eprint={2602.21202},
|
| 177 |
+
archivePrefix={arXiv},
|
| 178 |
+
primaryClass={cs.IR},
|
| 179 |
+
url={https://arxiv.org/abs/2602.21202},
|
| 180 |
+
}
|
| 181 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|mem0|>": 151669,
|
| 20 |
+
"<|mem10|>": 151679,
|
| 21 |
+
"<|mem11|>": 151680,
|
| 22 |
+
"<|mem12|>": 151681,
|
| 23 |
+
"<|mem13|>": 151682,
|
| 24 |
+
"<|mem14|>": 151683,
|
| 25 |
+
"<|mem15|>": 151684,
|
| 26 |
+
"<|mem16|>": 151685,
|
| 27 |
+
"<|mem17|>": 151686,
|
| 28 |
+
"<|mem18|>": 151687,
|
| 29 |
+
"<|mem19|>": 151688,
|
| 30 |
+
"<|mem1|>": 151670,
|
| 31 |
+
"<|mem20|>": 151689,
|
| 32 |
+
"<|mem21|>": 151690,
|
| 33 |
+
"<|mem22|>": 151691,
|
| 34 |
+
"<|mem23|>": 151692,
|
| 35 |
+
"<|mem24|>": 151693,
|
| 36 |
+
"<|mem25|>": 151694,
|
| 37 |
+
"<|mem26|>": 151695,
|
| 38 |
+
"<|mem27|>": 151696,
|
| 39 |
+
"<|mem28|>": 151697,
|
| 40 |
+
"<|mem29|>": 151698,
|
| 41 |
+
"<|mem2|>": 151671,
|
| 42 |
+
"<|mem30|>": 151699,
|
| 43 |
+
"<|mem31|>": 151700,
|
| 44 |
+
"<|mem3|>": 151672,
|
| 45 |
+
"<|mem4|>": 151673,
|
| 46 |
+
"<|mem5|>": 151674,
|
| 47 |
+
"<|mem6|>": 151675,
|
| 48 |
+
"<|mem7|>": 151676,
|
| 49 |
+
"<|mem8|>": 151677,
|
| 50 |
+
"<|mem9|>": 151678,
|
| 51 |
+
"<|object_ref_end|>": 151647,
|
| 52 |
+
"<|object_ref_start|>": 151646,
|
| 53 |
+
"<|quad_end|>": 151651,
|
| 54 |
+
"<|quad_start|>": 151650,
|
| 55 |
+
"<|repo_name|>": 151663,
|
| 56 |
+
"<|video_pad|>": 151656,
|
| 57 |
+
"<|vision_end|>": 151653,
|
| 58 |
+
"<|vision_pad|>": 151654,
|
| 59 |
+
"<|vision_start|>": 151652
|
| 60 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForEmbedding"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 151643,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 151645,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 2560,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 9728,
|
| 20 |
+
"max_position_embeddings": 262144,
|
| 21 |
+
"model_type": "qwen3_vl_text",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 36,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"mrope_interleaved": true,
|
| 28 |
+
"mrope_section": [
|
| 29 |
+
24,
|
| 30 |
+
20,
|
| 31 |
+
20
|
| 32 |
+
],
|
| 33 |
+
"rope_type": "default"
|
| 34 |
+
},
|
| 35 |
+
"rope_theta": 5000000,
|
| 36 |
+
"tie_word_embeddings": true,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 151701
|
| 39 |
+
},
|
| 40 |
+
"tie_word_embeddings": true,
|
| 41 |
+
"transformers_version": "4.57.3",
|
| 42 |
+
"video_token_id": 151656,
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"deepstack_visual_indexes": [
|
| 45 |
+
5,
|
| 46 |
+
11,
|
| 47 |
+
17
|
| 48 |
+
],
|
| 49 |
+
"depth": 24,
|
| 50 |
+
"dtype": "bfloat16",
|
| 51 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 52 |
+
"hidden_size": 1024,
|
| 53 |
+
"in_channels": 3,
|
| 54 |
+
"initializer_range": 0.02,
|
| 55 |
+
"intermediate_size": 4096,
|
| 56 |
+
"model_type": "qwen3_vl",
|
| 57 |
+
"num_heads": 16,
|
| 58 |
+
"num_position_embeddings": 2304,
|
| 59 |
+
"out_hidden_size": 2560,
|
| 60 |
+
"patch_size": 16,
|
| 61 |
+
"spatial_merge_size": 2,
|
| 62 |
+
"temporal_patch_size": 2
|
| 63 |
+
},
|
| 64 |
+
"vision_end_token_id": 151653,
|
| 65 |
+
"vision_start_token_id": 151652
|
| 66 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:681de333cc9297619ead1f8df24e8b15cbe5c760ffc9e256693072ba483facff
|
| 3 |
+
size 4989294680
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26d3a72723771190ad1cc17f3a5c13d9a67c3f590348a196e9e2bd20c3515442
|
| 3 |
+
size 3885221448
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 569856,
|
| 4 |
+
"total_size": 8874428416
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
|
| 720 |
+
}
|
| 721 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|mem0|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|mem1|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|mem2|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|mem3|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<|mem4|>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "<|mem5|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "<|mem6|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "<|mem7|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<|mem8|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "<|mem9|>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<|mem10|>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "<|mem11|>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"content": "<|mem12|>",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"content": "<|mem13|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"content": "<|mem14|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"content": "<|mem15|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"content": "<|mem16|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "<|mem17|>",
|
| 124 |
+
"lstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"content": "<|mem18|>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"content": "<|mem19|>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": false,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"content": "<|mem20|>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"content": "<|mem21|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "<|mem22|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"content": "<|mem23|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"content": "<|mem24|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"content": "<|mem25|>",
|
| 180 |
+
"lstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"content": "<|mem26|>",
|
| 187 |
+
"lstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"single_word": false
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"content": "<|mem27|>",
|
| 194 |
+
"lstrip": false,
|
| 195 |
+
"normalized": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"single_word": false
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"content": "<|mem28|>",
|
| 201 |
+
"lstrip": false,
|
| 202 |
+
"normalized": false,
|
| 203 |
+
"rstrip": false,
|
| 204 |
+
"single_word": false
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"content": "<|mem29|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"content": "<|mem30|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"content": "<|mem31|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false
|
| 226 |
+
}
|
| 227 |
+
],
|
| 228 |
+
"eos_token": {
|
| 229 |
+
"content": "<|im_end|>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false
|
| 234 |
+
},
|
| 235 |
+
"pad_token": {
|
| 236 |
+
"content": "<|endoftext|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false
|
| 241 |
+
}
|
| 242 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0fdbfcd4c3fdeaafbe0a50e802fc485461636d91bee316eb11b560d2d3d8544
|
| 3 |
+
size 11428596
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "<|mem0|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<|mem1|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<|mem2|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<|mem3|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"151673": {
|
| 246 |
+
"content": "<|mem4|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"151674": {
|
| 254 |
+
"content": "<|mem5|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"151675": {
|
| 262 |
+
"content": "<|mem6|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"151676": {
|
| 270 |
+
"content": "<|mem7|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"151677": {
|
| 278 |
+
"content": "<|mem8|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"151678": {
|
| 286 |
+
"content": "<|mem9|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"151679": {
|
| 294 |
+
"content": "<|mem10|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"151680": {
|
| 302 |
+
"content": "<|mem11|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"151681": {
|
| 310 |
+
"content": "<|mem12|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"151682": {
|
| 318 |
+
"content": "<|mem13|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"151683": {
|
| 326 |
+
"content": "<|mem14|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"151684": {
|
| 334 |
+
"content": "<|mem15|>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"151685": {
|
| 342 |
+
"content": "<|mem16|>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"151686": {
|
| 350 |
+
"content": "<|mem17|>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"151687": {
|
| 358 |
+
"content": "<|mem18|>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"151688": {
|
| 366 |
+
"content": "<|mem19|>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"151689": {
|
| 374 |
+
"content": "<|mem20|>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"151690": {
|
| 382 |
+
"content": "<|mem21|>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"151691": {
|
| 390 |
+
"content": "<|mem22|>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"151692": {
|
| 398 |
+
"content": "<|mem23|>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"151693": {
|
| 406 |
+
"content": "<|mem24|>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"151694": {
|
| 414 |
+
"content": "<|mem25|>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"151695": {
|
| 422 |
+
"content": "<|mem26|>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"151696": {
|
| 430 |
+
"content": "<|mem27|>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"151697": {
|
| 438 |
+
"content": "<|mem28|>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"151698": {
|
| 446 |
+
"content": "<|mem29|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"151699": {
|
| 454 |
+
"content": "<|mem30|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"151700": {
|
| 462 |
+
"content": "<|mem31|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
}
|
| 469 |
+
},
|
| 470 |
+
"additional_special_tokens": [
|
| 471 |
+
"<|mem0|>",
|
| 472 |
+
"<|mem1|>",
|
| 473 |
+
"<|mem2|>",
|
| 474 |
+
"<|mem3|>",
|
| 475 |
+
"<|mem4|>",
|
| 476 |
+
"<|mem5|>",
|
| 477 |
+
"<|mem6|>",
|
| 478 |
+
"<|mem7|>",
|
| 479 |
+
"<|mem8|>",
|
| 480 |
+
"<|mem9|>",
|
| 481 |
+
"<|mem10|>",
|
| 482 |
+
"<|mem11|>",
|
| 483 |
+
"<|mem12|>",
|
| 484 |
+
"<|mem13|>",
|
| 485 |
+
"<|mem14|>",
|
| 486 |
+
"<|mem15|>",
|
| 487 |
+
"<|mem16|>",
|
| 488 |
+
"<|mem17|>",
|
| 489 |
+
"<|mem18|>",
|
| 490 |
+
"<|mem19|>",
|
| 491 |
+
"<|mem20|>",
|
| 492 |
+
"<|mem21|>",
|
| 493 |
+
"<|mem22|>",
|
| 494 |
+
"<|mem23|>",
|
| 495 |
+
"<|mem24|>",
|
| 496 |
+
"<|mem25|>",
|
| 497 |
+
"<|mem26|>",
|
| 498 |
+
"<|mem27|>",
|
| 499 |
+
"<|mem28|>",
|
| 500 |
+
"<|mem29|>",
|
| 501 |
+
"<|mem30|>",
|
| 502 |
+
"<|mem31|>"
|
| 503 |
+
],
|
| 504 |
+
"bos_token": null,
|
| 505 |
+
"clean_up_tokenization_spaces": false,
|
| 506 |
+
"eos_token": "<|im_end|>",
|
| 507 |
+
"errors": "replace",
|
| 508 |
+
"extra_special_tokens": {},
|
| 509 |
+
"model_max_length": 262144,
|
| 510 |
+
"pad_token": "<|endoftext|>",
|
| 511 |
+
"processor_class": "Qwen3VLProcessor",
|
| 512 |
+
"split_special_tokens": false,
|
| 513 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 514 |
+
"unk_token": null,
|
| 515 |
+
"use_fast": true
|
| 516 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|