diff --git a/finetune/checkpoints/checkpoint-192/README.md b/finetune/checkpoints/checkpoint-192/README.md
deleted file mode 100644
index b3b2757edb8bd847d0ea95e1c5932f20c07ba195..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-192/adapter_config.json b/finetune/checkpoints/checkpoint-192/adapter_config.json
deleted file mode 100644
index e5c54e178948d109f1365f361e4239f5a8a8e901..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "Qwen/Qwen3.5-9B",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "up_proj",
- "k_proj",
- "o_proj",
- "v_proj",
- "out_proj",
- "in_proj_qkv",
- "in_proj_z",
- "in_proj_b",
- "down_proj",
- "q_proj",
- "gate_proj",
- "in_proj_a"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-192/adapter_model.safetensors b/finetune/checkpoints/checkpoint-192/adapter_model.safetensors
deleted file mode 100644
index a990afaef83c8c3d81891b62ead6e01d680e4817..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e07e0b5a0d2334b84ef4a982b94e1c2ef612da46da07cfe4930289e2855e5741
-size 86624424
diff --git a/finetune/checkpoints/checkpoint-192/chat_template.jinja b/finetune/checkpoints/checkpoint-192/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-192/optimizer.pt b/finetune/checkpoints/checkpoint-192/optimizer.pt
deleted file mode 100644
index c1910fcdd89e140db95de46669e885d224f3705e..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1524a0b0fe341db800227e4b99364b7b34f4716e82f57b5f64bb72453ed6f30
-size 173539507
diff --git a/finetune/checkpoints/checkpoint-192/rng_state.pth b/finetune/checkpoints/checkpoint-192/rng_state.pth
deleted file mode 100644
index 603eda639b22a3fa857c86b12b35470397e4861a..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7867f112d09bb82ff1c3b176d45ad04fc116373ec5e870377e2c4ed1ad92f934
-size 14645
diff --git a/finetune/checkpoints/checkpoint-192/scheduler.pt b/finetune/checkpoints/checkpoint-192/scheduler.pt
deleted file mode 100644
index 09043717b4aa8721bde1df9645c9d5874b971cbd..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa84f260a89ac768c794df2a0bc4940cdffb529c8e321e51dfbdb2e00433d23c
-size 1465
diff --git a/finetune/checkpoints/checkpoint-192/tokenizer.json b/finetune/checkpoints/checkpoint-192/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/checkpoints/checkpoint-192/tokenizer_config.json b/finetune/checkpoints/checkpoint-192/tokenizer_config.json
deleted file mode 100644
index ab901d8dd18462b5a5243a09a182e68f7e37940b..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": false,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/checkpoints/checkpoint-192/trainer_state.json b/finetune/checkpoints/checkpoint-192/trainer_state.json
deleted file mode 100644
index 253b4e3ab82150a4157fa5b8fb73699111712c7a..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/trainer_state.json
+++ /dev/null
@@ -1,224 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 2.0,
- "eval_steps": 500,
- "global_step": 192,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.5058588825166226,
- "epoch": 0.10512483574244415,
- "grad_norm": 1.796875,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.7537630081176758,
- "mean_token_accuracy": 0.695327178388834,
- "num_tokens": 3808.0,
- "step": 10
- },
- {
- "entropy": 1.316319726407528,
- "epoch": 0.2102496714848883,
- "grad_norm": 1.390625,
- "learning_rate": 0.00018680555555555556,
- "loss": 1.4752570152282716,
- "mean_token_accuracy": 0.7272207736968994,
- "num_tokens": 7522.0,
- "step": 20
- },
- {
- "entropy": 1.3150447681546211,
- "epoch": 0.31537450722733246,
- "grad_norm": 1.3984375,
- "learning_rate": 0.00017986111111111113,
- "loss": 1.404660415649414,
- "mean_token_accuracy": 0.7220224224030971,
- "num_tokens": 11407.0,
- "step": 30
- },
- {
- "entropy": 1.225712712854147,
- "epoch": 0.4204993429697766,
- "grad_norm": 1.140625,
- "learning_rate": 0.00017291666666666668,
- "loss": 1.3144322395324708,
- "mean_token_accuracy": 0.7446377977728844,
- "num_tokens": 15194.0,
- "step": 40
- },
- {
- "entropy": 1.3306574214249849,
- "epoch": 0.5256241787122208,
- "grad_norm": 1.390625,
- "learning_rate": 0.00016597222222222225,
- "loss": 1.442171287536621,
- "mean_token_accuracy": 0.7188469670712948,
- "num_tokens": 19221.0,
- "step": 50
- },
- {
- "entropy": 1.2213972710072993,
- "epoch": 0.6307490144546649,
- "grad_norm": 1.25,
- "learning_rate": 0.00015902777777777776,
- "loss": 1.3555883407592773,
- "mean_token_accuracy": 0.7323203787207604,
- "num_tokens": 23135.0,
- "step": 60
- },
- {
- "entropy": 1.236185147613287,
- "epoch": 0.735873850197109,
- "grad_norm": 1.2890625,
- "learning_rate": 0.00015208333333333333,
- "loss": 1.3239954948425292,
- "mean_token_accuracy": 0.7413535274565219,
- "num_tokens": 26938.0,
- "step": 70
- },
- {
- "entropy": 1.1433476515114307,
- "epoch": 0.8409986859395532,
- "grad_norm": 1.1875,
- "learning_rate": 0.00014513888888888888,
- "loss": 1.2469322204589843,
- "mean_token_accuracy": 0.7549085400998592,
- "num_tokens": 30527.0,
- "step": 80
- },
- {
- "entropy": 1.283092799782753,
- "epoch": 0.9461235216819974,
- "grad_norm": 1.21875,
- "learning_rate": 0.00013819444444444445,
- "loss": 1.4147074699401856,
- "mean_token_accuracy": 0.7189013145864009,
- "num_tokens": 34654.0,
- "step": 90
- },
- {
- "entropy": 1.2251756056530836,
- "epoch": 1.0420499342969776,
- "grad_norm": 1.0078125,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.1694912910461426,
- "mean_token_accuracy": 0.75513191827356,
- "num_tokens": 38292.0,
- "step": 100
- },
- {
- "entropy": 0.9808842208236456,
- "epoch": 1.1471747700394217,
- "grad_norm": 1.390625,
- "learning_rate": 0.00012430555555555556,
- "loss": 0.9646660804748535,
- "mean_token_accuracy": 0.7965455286204814,
- "num_tokens": 42119.0,
- "step": 110
- },
- {
- "entropy": 0.895855213701725,
- "epoch": 1.2522996057818658,
- "grad_norm": 1.625,
- "learning_rate": 0.00011736111111111112,
- "loss": 0.9326272964477539,
- "mean_token_accuracy": 0.7989173181354999,
- "num_tokens": 46121.0,
- "step": 120
- },
- {
- "entropy": 0.8705711856484413,
- "epoch": 1.3574244415243102,
- "grad_norm": 1.8125,
- "learning_rate": 0.00011041666666666668,
- "loss": 0.8961386680603027,
- "mean_token_accuracy": 0.8044699378311634,
- "num_tokens": 50090.0,
- "step": 130
- },
- {
- "entropy": 0.8594769395887851,
- "epoch": 1.4625492772667543,
- "grad_norm": 1.6171875,
- "learning_rate": 0.00010347222222222223,
- "loss": 0.8508189201354981,
- "mean_token_accuracy": 0.8186739608645439,
- "num_tokens": 53919.0,
- "step": 140
- },
- {
- "entropy": 0.8401138111948967,
- "epoch": 1.5676741130091985,
- "grad_norm": 1.7578125,
- "learning_rate": 9.652777777777779e-05,
- "loss": 0.8900316238403321,
- "mean_token_accuracy": 0.8109646178781986,
- "num_tokens": 57865.0,
- "step": 150
- },
- {
- "entropy": 0.8799884164705872,
- "epoch": 1.6727989487516426,
- "grad_norm": 1.9765625,
- "learning_rate": 8.958333333333335e-05,
- "loss": 0.8930209159851075,
- "mean_token_accuracy": 0.8081811979413033,
- "num_tokens": 61745.0,
- "step": 160
- },
- {
- "entropy": 0.8651461038738489,
- "epoch": 1.7779237844940867,
- "grad_norm": 1.625,
- "learning_rate": 8.263888888888889e-05,
- "loss": 0.870454978942871,
- "mean_token_accuracy": 0.8074543043971062,
- "num_tokens": 65643.0,
- "step": 170
- },
- {
- "entropy": 0.8021717140451073,
- "epoch": 1.8830486202365309,
- "grad_norm": 2.109375,
- "learning_rate": 7.569444444444445e-05,
- "loss": 0.8372815132141114,
- "mean_token_accuracy": 0.8185677900910378,
- "num_tokens": 69253.0,
- "step": 180
- },
- {
- "entropy": 0.8461722563952208,
- "epoch": 1.988173455978975,
- "grad_norm": 1.9609375,
- "learning_rate": 6.875e-05,
- "loss": 0.8477604866027832,
- "mean_token_accuracy": 0.821676817536354,
- "num_tokens": 73086.0,
- "step": 190
- }
- ],
- "logging_steps": 10,
- "max_steps": 288,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": false
- },
- "attributes": {}
- }
- },
- "total_flos": 3517439958097920.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/checkpoints/checkpoint-192/training_args.bin b/finetune/checkpoints/checkpoint-192/training_args.bin
deleted file mode 100644
index 82ed50d187cfd749d575b4f8cea3be4f247c6008..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-192/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777
diff --git a/finetune/checkpoints/checkpoint-288/README.md b/finetune/checkpoints/checkpoint-288/README.md
deleted file mode 100644
index b3b2757edb8bd847d0ea95e1c5932f20c07ba195..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-288/adapter_config.json b/finetune/checkpoints/checkpoint-288/adapter_config.json
deleted file mode 100644
index e5c54e178948d109f1365f361e4239f5a8a8e901..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "Qwen/Qwen3.5-9B",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "up_proj",
- "k_proj",
- "o_proj",
- "v_proj",
- "out_proj",
- "in_proj_qkv",
- "in_proj_z",
- "in_proj_b",
- "down_proj",
- "q_proj",
- "gate_proj",
- "in_proj_a"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-288/adapter_model.safetensors b/finetune/checkpoints/checkpoint-288/adapter_model.safetensors
deleted file mode 100644
index a2a868d420a5449cd93c11d0fc1f139e05835856..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7d88cb1cdd1237abdb5933ccf30096da0861d6ac0874c743f5de09abd5293c06
-size 86624424
diff --git a/finetune/checkpoints/checkpoint-288/chat_template.jinja b/finetune/checkpoints/checkpoint-288/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-288/optimizer.pt b/finetune/checkpoints/checkpoint-288/optimizer.pt
deleted file mode 100644
index 1711ecbd97c3af021d7a0f4f00255d7ac0cbaf0f..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:189edcd603f7bbddb01c5754b74224f95ea9def898c5f111090bc5b61d82ebe1
-size 173539507
diff --git a/finetune/checkpoints/checkpoint-288/rng_state.pth b/finetune/checkpoints/checkpoint-288/rng_state.pth
deleted file mode 100644
index ae7fd9830445fcb7c03b6bf5a294a566d54abb8c..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1de14d45bf40451ecad8cc71ddb5f3014594537a7f4f59d093126e25120b911
-size 14645
diff --git a/finetune/checkpoints/checkpoint-288/scheduler.pt b/finetune/checkpoints/checkpoint-288/scheduler.pt
deleted file mode 100644
index b0fe5276eb51e220ced70aae8e045635ce002899..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db65c34a575612e43bcfbbcdee111aa92a8a1578c29689cbfb7e5bcc00cf526d
-size 1465
diff --git a/finetune/checkpoints/checkpoint-288/tokenizer.json b/finetune/checkpoints/checkpoint-288/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/checkpoints/checkpoint-288/tokenizer_config.json b/finetune/checkpoints/checkpoint-288/tokenizer_config.json
deleted file mode 100644
index ab901d8dd18462b5a5243a09a182e68f7e37940b..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": false,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/checkpoints/checkpoint-288/trainer_state.json b/finetune/checkpoints/checkpoint-288/trainer_state.json
deleted file mode 100644
index 644e2e9c971ccc842b51782198920e9a01f509f4..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/trainer_state.json
+++ /dev/null
@@ -1,314 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 3.0,
- "eval_steps": 500,
- "global_step": 288,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.5058588825166226,
- "epoch": 0.10512483574244415,
- "grad_norm": 1.796875,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.7537630081176758,
- "mean_token_accuracy": 0.695327178388834,
- "num_tokens": 3808.0,
- "step": 10
- },
- {
- "entropy": 1.316319726407528,
- "epoch": 0.2102496714848883,
- "grad_norm": 1.390625,
- "learning_rate": 0.00018680555555555556,
- "loss": 1.4752570152282716,
- "mean_token_accuracy": 0.7272207736968994,
- "num_tokens": 7522.0,
- "step": 20
- },
- {
- "entropy": 1.3150447681546211,
- "epoch": 0.31537450722733246,
- "grad_norm": 1.3984375,
- "learning_rate": 0.00017986111111111113,
- "loss": 1.404660415649414,
- "mean_token_accuracy": 0.7220224224030971,
- "num_tokens": 11407.0,
- "step": 30
- },
- {
- "entropy": 1.225712712854147,
- "epoch": 0.4204993429697766,
- "grad_norm": 1.140625,
- "learning_rate": 0.00017291666666666668,
- "loss": 1.3144322395324708,
- "mean_token_accuracy": 0.7446377977728844,
- "num_tokens": 15194.0,
- "step": 40
- },
- {
- "entropy": 1.3306574214249849,
- "epoch": 0.5256241787122208,
- "grad_norm": 1.390625,
- "learning_rate": 0.00016597222222222225,
- "loss": 1.442171287536621,
- "mean_token_accuracy": 0.7188469670712948,
- "num_tokens": 19221.0,
- "step": 50
- },
- {
- "entropy": 1.2213972710072993,
- "epoch": 0.6307490144546649,
- "grad_norm": 1.25,
- "learning_rate": 0.00015902777777777776,
- "loss": 1.3555883407592773,
- "mean_token_accuracy": 0.7323203787207604,
- "num_tokens": 23135.0,
- "step": 60
- },
- {
- "entropy": 1.236185147613287,
- "epoch": 0.735873850197109,
- "grad_norm": 1.2890625,
- "learning_rate": 0.00015208333333333333,
- "loss": 1.3239954948425292,
- "mean_token_accuracy": 0.7413535274565219,
- "num_tokens": 26938.0,
- "step": 70
- },
- {
- "entropy": 1.1433476515114307,
- "epoch": 0.8409986859395532,
- "grad_norm": 1.1875,
- "learning_rate": 0.00014513888888888888,
- "loss": 1.2469322204589843,
- "mean_token_accuracy": 0.7549085400998592,
- "num_tokens": 30527.0,
- "step": 80
- },
- {
- "entropy": 1.283092799782753,
- "epoch": 0.9461235216819974,
- "grad_norm": 1.21875,
- "learning_rate": 0.00013819444444444445,
- "loss": 1.4147074699401856,
- "mean_token_accuracy": 0.7189013145864009,
- "num_tokens": 34654.0,
- "step": 90
- },
- {
- "entropy": 1.2251756056530836,
- "epoch": 1.0420499342969776,
- "grad_norm": 1.0078125,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.1694912910461426,
- "mean_token_accuracy": 0.75513191827356,
- "num_tokens": 38292.0,
- "step": 100
- },
- {
- "entropy": 0.9808842208236456,
- "epoch": 1.1471747700394217,
- "grad_norm": 1.390625,
- "learning_rate": 0.00012430555555555556,
- "loss": 0.9646660804748535,
- "mean_token_accuracy": 0.7965455286204814,
- "num_tokens": 42119.0,
- "step": 110
- },
- {
- "entropy": 0.895855213701725,
- "epoch": 1.2522996057818658,
- "grad_norm": 1.625,
- "learning_rate": 0.00011736111111111112,
- "loss": 0.9326272964477539,
- "mean_token_accuracy": 0.7989173181354999,
- "num_tokens": 46121.0,
- "step": 120
- },
- {
- "entropy": 0.8705711856484413,
- "epoch": 1.3574244415243102,
- "grad_norm": 1.8125,
- "learning_rate": 0.00011041666666666668,
- "loss": 0.8961386680603027,
- "mean_token_accuracy": 0.8044699378311634,
- "num_tokens": 50090.0,
- "step": 130
- },
- {
- "entropy": 0.8594769395887851,
- "epoch": 1.4625492772667543,
- "grad_norm": 1.6171875,
- "learning_rate": 0.00010347222222222223,
- "loss": 0.8508189201354981,
- "mean_token_accuracy": 0.8186739608645439,
- "num_tokens": 53919.0,
- "step": 140
- },
- {
- "entropy": 0.8401138111948967,
- "epoch": 1.5676741130091985,
- "grad_norm": 1.7578125,
- "learning_rate": 9.652777777777779e-05,
- "loss": 0.8900316238403321,
- "mean_token_accuracy": 0.8109646178781986,
- "num_tokens": 57865.0,
- "step": 150
- },
- {
- "entropy": 0.8799884164705872,
- "epoch": 1.6727989487516426,
- "grad_norm": 1.9765625,
- "learning_rate": 8.958333333333335e-05,
- "loss": 0.8930209159851075,
- "mean_token_accuracy": 0.8081811979413033,
- "num_tokens": 61745.0,
- "step": 160
- },
- {
- "entropy": 0.8651461038738489,
- "epoch": 1.7779237844940867,
- "grad_norm": 1.625,
- "learning_rate": 8.263888888888889e-05,
- "loss": 0.870454978942871,
- "mean_token_accuracy": 0.8074543043971062,
- "num_tokens": 65643.0,
- "step": 170
- },
- {
- "entropy": 0.8021717140451073,
- "epoch": 1.8830486202365309,
- "grad_norm": 2.109375,
- "learning_rate": 7.569444444444445e-05,
- "loss": 0.8372815132141114,
- "mean_token_accuracy": 0.8185677900910378,
- "num_tokens": 69253.0,
- "step": 180
- },
- {
- "entropy": 0.8461722563952208,
- "epoch": 1.988173455978975,
- "grad_norm": 1.9609375,
- "learning_rate": 6.875e-05,
- "loss": 0.8477604866027832,
- "mean_token_accuracy": 0.821676817536354,
- "num_tokens": 73086.0,
- "step": 190
- },
- {
- "entropy": 0.6834010038882086,
- "epoch": 2.084099868593955,
- "grad_norm": 1.640625,
- "learning_rate": 6.180555555555556e-05,
- "loss": 0.5151080131530762,
- "mean_token_accuracy": 0.8863431843992782,
- "num_tokens": 76490.0,
- "step": 200
- },
- {
- "entropy": 0.5644423710182309,
- "epoch": 2.1892247043363993,
- "grad_norm": 2.4375,
- "learning_rate": 5.486111111111112e-05,
- "loss": 0.523468017578125,
- "mean_token_accuracy": 0.8785075314342976,
- "num_tokens": 80430.0,
- "step": 210
- },
- {
- "entropy": 0.5120254509150982,
- "epoch": 2.2943495400788434,
- "grad_norm": 1.6796875,
- "learning_rate": 4.791666666666667e-05,
- "loss": 0.43973474502563475,
- "mean_token_accuracy": 0.900006202608347,
- "num_tokens": 84261.0,
- "step": 220
- },
- {
- "entropy": 0.6139889739453792,
- "epoch": 2.3994743758212875,
- "grad_norm": 2.03125,
- "learning_rate": 4.0972222222222225e-05,
- "loss": 0.49155173301696775,
- "mean_token_accuracy": 0.8851348020136356,
- "num_tokens": 88367.0,
- "step": 230
- },
- {
- "entropy": 0.548260616324842,
- "epoch": 2.5045992115637317,
- "grad_norm": 2.109375,
- "learning_rate": 3.402777777777778e-05,
- "loss": 0.45668373107910154,
- "mean_token_accuracy": 0.8958614394068718,
- "num_tokens": 92116.0,
- "step": 240
- },
- {
- "entropy": 0.524461186490953,
- "epoch": 2.6097240473061762,
- "grad_norm": 2.25,
- "learning_rate": 2.7083333333333332e-05,
- "loss": 0.4536457538604736,
- "mean_token_accuracy": 0.8967262022197247,
- "num_tokens": 96008.0,
- "step": 250
- },
- {
- "entropy": 0.5277848264202476,
- "epoch": 2.7148488830486204,
- "grad_norm": 2.625,
- "learning_rate": 2.013888888888889e-05,
- "loss": 0.4624601364135742,
- "mean_token_accuracy": 0.8950574725866318,
- "num_tokens": 99859.0,
- "step": 260
- },
- {
- "entropy": 0.5569793220609427,
- "epoch": 2.8199737187910645,
- "grad_norm": 2.078125,
- "learning_rate": 1.3194444444444446e-05,
- "loss": 0.4798299312591553,
- "mean_token_accuracy": 0.8920079082250595,
- "num_tokens": 103783.0,
- "step": 270
- },
- {
- "entropy": 0.5342973008751869,
- "epoch": 2.9250985545335086,
- "grad_norm": 1.96875,
- "learning_rate": 6.25e-06,
- "loss": 0.44893660545349123,
- "mean_token_accuracy": 0.8974449247121811,
- "num_tokens": 107478.0,
- "step": 280
- }
- ],
- "logging_steps": 10,
- "max_steps": 288,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": true
- },
- "attributes": {}
- }
- },
- "total_flos": 5276159937146880.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/checkpoints/checkpoint-288/training_args.bin b/finetune/checkpoints/checkpoint-288/training_args.bin
deleted file mode 100644
index 82ed50d187cfd749d575b4f8cea3be4f247c6008..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-288/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777
diff --git a/finetune/checkpoints/checkpoint-96/README.md b/finetune/checkpoints/checkpoint-96/README.md
deleted file mode 100644
index b3b2757edb8bd847d0ea95e1c5932f20c07ba195..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-96/adapter_config.json b/finetune/checkpoints/checkpoint-96/adapter_config.json
deleted file mode 100644
index e5c54e178948d109f1365f361e4239f5a8a8e901..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "Qwen/Qwen3.5-9B",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "up_proj",
- "k_proj",
- "o_proj",
- "v_proj",
- "out_proj",
- "in_proj_qkv",
- "in_proj_z",
- "in_proj_b",
- "down_proj",
- "q_proj",
- "gate_proj",
- "in_proj_a"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-96/adapter_model.safetensors b/finetune/checkpoints/checkpoint-96/adapter_model.safetensors
deleted file mode 100644
index 49f94b0f6e2da13a5a6a5a78e395c49db83a2e31..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f03e779a43975dcdd86cdb41004659692e771ca7880c0c8404b714c658c6af0e
-size 86624424
diff --git a/finetune/checkpoints/checkpoint-96/chat_template.jinja b/finetune/checkpoints/checkpoint-96/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/checkpoints/checkpoint-96/optimizer.pt b/finetune/checkpoints/checkpoint-96/optimizer.pt
deleted file mode 100644
index 20892d120e50260ef39c72c83c9a44680988479d..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d20760b2006a548a0307ad7cd2792b4ac6b093ec76f9b640f29a2d9d8b4faffd
-size 173539507
diff --git a/finetune/checkpoints/checkpoint-96/rng_state.pth b/finetune/checkpoints/checkpoint-96/rng_state.pth
deleted file mode 100644
index 1a1a0a58295391619d96d93128c0364b78cd2579..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2fc05a5af5e55dd07491a9c13f98e77a3b89980687c94a380940cea72c438db1
-size 14645
diff --git a/finetune/checkpoints/checkpoint-96/scheduler.pt b/finetune/checkpoints/checkpoint-96/scheduler.pt
deleted file mode 100644
index af66f7d5b839c74cf02b9397e4aeda47636aa78e..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:26175424728d92cc8b818d24add62cebe17e0a76e269611dcabb93101acd685b
-size 1465
diff --git a/finetune/checkpoints/checkpoint-96/tokenizer.json b/finetune/checkpoints/checkpoint-96/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/checkpoints/checkpoint-96/tokenizer_config.json b/finetune/checkpoints/checkpoint-96/tokenizer_config.json
deleted file mode 100644
index ab901d8dd18462b5a5243a09a182e68f7e37940b..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": false,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/checkpoints/checkpoint-96/trainer_state.json b/finetune/checkpoints/checkpoint-96/trainer_state.json
deleted file mode 100644
index 0816dacc30abb320b9a10ed08edef9692944cebb..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/trainer_state.json
+++ /dev/null
@@ -1,124 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 1.0,
- "eval_steps": 500,
- "global_step": 96,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.5058588825166226,
- "epoch": 0.10512483574244415,
- "grad_norm": 1.796875,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.7537630081176758,
- "mean_token_accuracy": 0.695327178388834,
- "num_tokens": 3808.0,
- "step": 10
- },
- {
- "entropy": 1.316319726407528,
- "epoch": 0.2102496714848883,
- "grad_norm": 1.390625,
- "learning_rate": 0.00018680555555555556,
- "loss": 1.4752570152282716,
- "mean_token_accuracy": 0.7272207736968994,
- "num_tokens": 7522.0,
- "step": 20
- },
- {
- "entropy": 1.3150447681546211,
- "epoch": 0.31537450722733246,
- "grad_norm": 1.3984375,
- "learning_rate": 0.00017986111111111113,
- "loss": 1.404660415649414,
- "mean_token_accuracy": 0.7220224224030971,
- "num_tokens": 11407.0,
- "step": 30
- },
- {
- "entropy": 1.225712712854147,
- "epoch": 0.4204993429697766,
- "grad_norm": 1.140625,
- "learning_rate": 0.00017291666666666668,
- "loss": 1.3144322395324708,
- "mean_token_accuracy": 0.7446377977728844,
- "num_tokens": 15194.0,
- "step": 40
- },
- {
- "entropy": 1.3306574214249849,
- "epoch": 0.5256241787122208,
- "grad_norm": 1.390625,
- "learning_rate": 0.00016597222222222225,
- "loss": 1.442171287536621,
- "mean_token_accuracy": 0.7188469670712948,
- "num_tokens": 19221.0,
- "step": 50
- },
- {
- "entropy": 1.2213972710072993,
- "epoch": 0.6307490144546649,
- "grad_norm": 1.25,
- "learning_rate": 0.00015902777777777776,
- "loss": 1.3555883407592773,
- "mean_token_accuracy": 0.7323203787207604,
- "num_tokens": 23135.0,
- "step": 60
- },
- {
- "entropy": 1.236185147613287,
- "epoch": 0.735873850197109,
- "grad_norm": 1.2890625,
- "learning_rate": 0.00015208333333333333,
- "loss": 1.3239954948425292,
- "mean_token_accuracy": 0.7413535274565219,
- "num_tokens": 26938.0,
- "step": 70
- },
- {
- "entropy": 1.1433476515114307,
- "epoch": 0.8409986859395532,
- "grad_norm": 1.1875,
- "learning_rate": 0.00014513888888888888,
- "loss": 1.2469322204589843,
- "mean_token_accuracy": 0.7549085400998592,
- "num_tokens": 30527.0,
- "step": 80
- },
- {
- "entropy": 1.283092799782753,
- "epoch": 0.9461235216819974,
- "grad_norm": 1.21875,
- "learning_rate": 0.00013819444444444445,
- "loss": 1.4147074699401856,
- "mean_token_accuracy": 0.7189013145864009,
- "num_tokens": 34654.0,
- "step": 90
- }
- ],
- "logging_steps": 10,
- "max_steps": 288,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": false
- },
- "attributes": {}
- }
- },
- "total_flos": 1758719979048960.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/checkpoints/checkpoint-96/training_args.bin b/finetune/checkpoints/checkpoint-96/training_args.bin
deleted file mode 100644
index 82ed50d187cfd749d575b4f8cea3be4f247c6008..0000000000000000000000000000000000000000
--- a/finetune/checkpoints/checkpoint-96/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777
diff --git a/finetune/style_checkpoint/checkpoint-132/README.md b/finetune/style_checkpoint/checkpoint-132/README.md
deleted file mode 100644
index c04daeefd1ca39da6d2f92e69e0d8ccf060b8064..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-132/adapter_config.json b/finetune/style_checkpoint/checkpoint-132/adapter_config.json
deleted file mode 100644
index dab930e22607ffa6b85b79b0a0a737bebb3c8d92..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "C:\\Users\\Ifmanzhang\\Documents\\GitHub\\RepE\\merged_model",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "in_proj_a",
- "up_proj",
- "in_proj_z",
- "in_proj_qkv",
- "down_proj",
- "o_proj",
- "gate_proj",
- "out_proj",
- "in_proj_b",
- "v_proj",
- "q_proj",
- "k_proj"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-132/adapter_model.safetensors b/finetune/style_checkpoint/checkpoint-132/adapter_model.safetensors
deleted file mode 100644
index 883f43f8508fec26f01996e2c8bd5304738e5675..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e39771f0f53ca759114efb681a1ed2041a68e81133e1fd79ca47e9260feefa8b
-size 86624424
diff --git a/finetune/style_checkpoint/checkpoint-132/chat_template.jinja b/finetune/style_checkpoint/checkpoint-132/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-132/optimizer.pt b/finetune/style_checkpoint/checkpoint-132/optimizer.pt
deleted file mode 100644
index 5ef37c2a0e279fa4ab68c868ff227e709f53845f..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8a8fc7ac39ead78fd5404103fd69eb5af92b12e8f12deb71bd1216c4839b55a
-size 173539507
diff --git a/finetune/style_checkpoint/checkpoint-132/rng_state.pth b/finetune/style_checkpoint/checkpoint-132/rng_state.pth
deleted file mode 100644
index f399d6e16c42a03f155969c31b39188bc6305638..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55458227fb883b7277781facf9f9a8d32c2c5a33e955febaec1eaadf202c3636
-size 14645
diff --git a/finetune/style_checkpoint/checkpoint-132/scheduler.pt b/finetune/style_checkpoint/checkpoint-132/scheduler.pt
deleted file mode 100644
index b084230d832cd159c02fc1b0e1c3fc443079fcfa..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9fad155de9dcd6412030b755a69f4c04b30a98ba8375d5d62b5bea51173f91a5
-size 1465
diff --git a/finetune/style_checkpoint/checkpoint-132/tokenizer.json b/finetune/style_checkpoint/checkpoint-132/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/style_checkpoint/checkpoint-132/tokenizer_config.json b/finetune/style_checkpoint/checkpoint-132/tokenizer_config.json
deleted file mode 100644
index c487bad4ddddf9cfdb448b260a6ea942bb18a1b1..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": true,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/style_checkpoint/checkpoint-132/trainer_state.json b/finetune/style_checkpoint/checkpoint-132/trainer_state.json
deleted file mode 100644
index dbdbb6aea5789ade7a6fe654eed3b9d2def79753..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/trainer_state.json
+++ /dev/null
@@ -1,164 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 3.0,
- "eval_steps": 500,
- "global_step": 132,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.30109671279788,
- "epoch": 0.22857142857142856,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00018636363636363636,
- "loss": 1.69281063079834,
- "mean_token_accuracy": 0.7338378168642521,
- "num_tokens": 2779.0,
- "step": 10
- },
- {
- "entropy": 1.2120113119482994,
- "epoch": 0.45714285714285713,
- "grad_norm": 1.3359375,
- "learning_rate": 0.00017121212121212122,
- "loss": 1.1274803161621094,
- "mean_token_accuracy": 0.770654023438692,
- "num_tokens": 5529.0,
- "step": 20
- },
- {
- "entropy": 0.9645026199519634,
- "epoch": 0.6857142857142857,
- "grad_norm": 1.3203125,
- "learning_rate": 0.00015606060606060607,
- "loss": 1.0083338737487793,
- "mean_token_accuracy": 0.7900982514023781,
- "num_tokens": 8264.0,
- "step": 30
- },
- {
- "entropy": 1.001315427571535,
- "epoch": 0.9142857142857143,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00014090909090909093,
- "loss": 0.9876208305358887,
- "mean_token_accuracy": 0.7899081066250802,
- "num_tokens": 11028.0,
- "step": 40
- },
- {
- "entropy": 0.9025501891588553,
- "epoch": 1.1371428571428572,
- "grad_norm": 0.97265625,
- "learning_rate": 0.00012575757575757575,
- "loss": 0.7734798908233642,
- "mean_token_accuracy": 0.8246896488544269,
- "num_tokens": 13730.0,
- "step": 50
- },
- {
- "entropy": 0.7055704202502966,
- "epoch": 1.3657142857142857,
- "grad_norm": 1.453125,
- "learning_rate": 0.00011060606060606061,
- "loss": 0.6433767318725586,
- "mean_token_accuracy": 0.849166390299797,
- "num_tokens": 16506.0,
- "step": 60
- },
- {
- "entropy": 0.6749185953289271,
- "epoch": 1.5942857142857143,
- "grad_norm": 1.5078125,
- "learning_rate": 9.545454545454546e-05,
- "loss": 0.6674872398376465,
- "mean_token_accuracy": 0.8353129491209984,
- "num_tokens": 19267.0,
- "step": 70
- },
- {
- "entropy": 0.665529253333807,
- "epoch": 1.822857142857143,
- "grad_norm": 1.71875,
- "learning_rate": 8.03030303030303e-05,
- "loss": 0.6229500770568848,
- "mean_token_accuracy": 0.8385165937244892,
- "num_tokens": 22011.0,
- "step": 80
- },
- {
- "entropy": 0.6535426924626032,
- "epoch": 2.045714285714286,
- "grad_norm": 1.0546875,
- "learning_rate": 6.515151515151516e-05,
- "loss": 0.5569591522216797,
- "mean_token_accuracy": 0.8594398276928144,
- "num_tokens": 24693.0,
- "step": 90
- },
- {
- "entropy": 0.5231270018965006,
- "epoch": 2.2742857142857145,
- "grad_norm": 1.6796875,
- "learning_rate": 5e-05,
- "loss": 0.36677672863006594,
- "mean_token_accuracy": 0.9020668059587479,
- "num_tokens": 27463.0,
- "step": 100
- },
- {
- "entropy": 0.4256359253078699,
- "epoch": 2.5028571428571427,
- "grad_norm": 2.046875,
- "learning_rate": 3.484848484848485e-05,
- "loss": 0.35885071754455566,
- "mean_token_accuracy": 0.8996045172214509,
- "num_tokens": 30201.0,
- "step": 110
- },
- {
- "entropy": 0.404218702763319,
- "epoch": 2.7314285714285713,
- "grad_norm": 1.734375,
- "learning_rate": 1.9696969696969697e-05,
- "loss": 0.35897390842437743,
- "mean_token_accuracy": 0.9063410043716431,
- "num_tokens": 32955.0,
- "step": 120
- },
- {
- "entropy": 0.3963111503049731,
- "epoch": 2.96,
- "grad_norm": 2.0625,
- "learning_rate": 4.5454545454545455e-06,
- "loss": 0.3470670938491821,
- "mean_token_accuracy": 0.9018755808472634,
- "num_tokens": 35726.0,
- "step": 130
- }
- ],
- "logging_steps": 10,
- "max_steps": 132,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": true
- },
- "attributes": {}
- }
- },
- "total_flos": 1734301292636160.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/style_checkpoint/checkpoint-132/training_args.bin b/finetune/style_checkpoint/checkpoint-132/training_args.bin
deleted file mode 100644
index 7f27361f14f7dc02dec1eead2b3daa8836f3d029..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-132/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b18b6c96a47cb78062355feafacc9baa8fde5cfda40273867df5486f7917195d
-size 5713
diff --git a/finetune/style_checkpoint/checkpoint-44/README.md b/finetune/style_checkpoint/checkpoint-44/README.md
deleted file mode 100644
index c04daeefd1ca39da6d2f92e69e0d8ccf060b8064..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-44/adapter_config.json b/finetune/style_checkpoint/checkpoint-44/adapter_config.json
deleted file mode 100644
index dab930e22607ffa6b85b79b0a0a737bebb3c8d92..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "C:\\Users\\Ifmanzhang\\Documents\\GitHub\\RepE\\merged_model",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "in_proj_a",
- "up_proj",
- "in_proj_z",
- "in_proj_qkv",
- "down_proj",
- "o_proj",
- "gate_proj",
- "out_proj",
- "in_proj_b",
- "v_proj",
- "q_proj",
- "k_proj"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-44/adapter_model.safetensors b/finetune/style_checkpoint/checkpoint-44/adapter_model.safetensors
deleted file mode 100644
index 7e3302e9cb3d3c6ffb2104b08de129b7d055b0cd..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fbf525e8ecdc16097d8dacc4631ed12a9eb4a2927e12e67a7722ae59ecfa9cc6
-size 86624424
diff --git a/finetune/style_checkpoint/checkpoint-44/chat_template.jinja b/finetune/style_checkpoint/checkpoint-44/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-44/optimizer.pt b/finetune/style_checkpoint/checkpoint-44/optimizer.pt
deleted file mode 100644
index c1e978c62a535c08268a039e429f05592fd9ef67..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e0c393eb649466fef43e60bd28f3fa487141df8e06fbbac4c1ef81fdb3041786
-size 173539507
diff --git a/finetune/style_checkpoint/checkpoint-44/rng_state.pth b/finetune/style_checkpoint/checkpoint-44/rng_state.pth
deleted file mode 100644
index 01ae0bf3e341260f3f4504b605a4800882e82dcb..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39fe84eb65ca8488e36557b0ca39dd485c262ba68865254ec0e97dc4ec1802dc
-size 14645
diff --git a/finetune/style_checkpoint/checkpoint-44/scheduler.pt b/finetune/style_checkpoint/checkpoint-44/scheduler.pt
deleted file mode 100644
index e5eed34cc70f13efe86a0c72b5392a3a500efb14..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:684b18ac87e0850864bd572ca1fafdd31679c7be29c45c60ca9b0c390bed175b
-size 1465
diff --git a/finetune/style_checkpoint/checkpoint-44/tokenizer.json b/finetune/style_checkpoint/checkpoint-44/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/style_checkpoint/checkpoint-44/tokenizer_config.json b/finetune/style_checkpoint/checkpoint-44/tokenizer_config.json
deleted file mode 100644
index c487bad4ddddf9cfdb448b260a6ea942bb18a1b1..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": true,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/style_checkpoint/checkpoint-44/trainer_state.json b/finetune/style_checkpoint/checkpoint-44/trainer_state.json
deleted file mode 100644
index 0a6935661abc8de791e2bed0f7015e7ecfe5f49c..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/trainer_state.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 1.0,
- "eval_steps": 500,
- "global_step": 44,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.30109671279788,
- "epoch": 0.22857142857142856,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00018636363636363636,
- "loss": 1.69281063079834,
- "mean_token_accuracy": 0.7338378168642521,
- "num_tokens": 2779.0,
- "step": 10
- },
- {
- "entropy": 1.2120113119482994,
- "epoch": 0.45714285714285713,
- "grad_norm": 1.3359375,
- "learning_rate": 0.00017121212121212122,
- "loss": 1.1274803161621094,
- "mean_token_accuracy": 0.770654023438692,
- "num_tokens": 5529.0,
- "step": 20
- },
- {
- "entropy": 0.9645026199519634,
- "epoch": 0.6857142857142857,
- "grad_norm": 1.3203125,
- "learning_rate": 0.00015606060606060607,
- "loss": 1.0083338737487793,
- "mean_token_accuracy": 0.7900982514023781,
- "num_tokens": 8264.0,
- "step": 30
- },
- {
- "entropy": 1.001315427571535,
- "epoch": 0.9142857142857143,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00014090909090909093,
- "loss": 0.9876208305358887,
- "mean_token_accuracy": 0.7899081066250802,
- "num_tokens": 11028.0,
- "step": 40
- }
- ],
- "logging_steps": 10,
- "max_steps": 132,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": false
- },
- "attributes": {}
- }
- },
- "total_flos": 578100430878720.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/style_checkpoint/checkpoint-44/training_args.bin b/finetune/style_checkpoint/checkpoint-44/training_args.bin
deleted file mode 100644
index 7f27361f14f7dc02dec1eead2b3daa8836f3d029..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-44/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b18b6c96a47cb78062355feafacc9baa8fde5cfda40273867df5486f7917195d
-size 5713
diff --git a/finetune/style_checkpoint/checkpoint-88/README.md b/finetune/style_checkpoint/checkpoint-88/README.md
deleted file mode 100644
index c04daeefd1ca39da6d2f92e69e0d8ccf060b8064..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/README.md
+++ /dev/null
@@ -1,209 +0,0 @@
----
-base_model: C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-
-
-
-
-## Model Details
-
-### Model Description
-
-
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-
-
-### Direct Use
-
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-
-
-[More Information Needed]
-
-### Recommendations
-
-
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-
-
-[More Information Needed]
-
-### Training Procedure
-
-
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed]
-
-#### Speeds, Sizes, Times [optional]
-
-
-
-[More Information Needed]
-
-## Evaluation
-
-
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-
-
-[More Information Needed]
-
-#### Factors
-
-
-
-[More Information Needed]
-
-#### Metrics
-
-
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-
-
-[More Information Needed]
-
-## Environmental Impact
-
-
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-88/adapter_config.json b/finetune/style_checkpoint/checkpoint-88/adapter_config.json
deleted file mode 100644
index dab930e22607ffa6b85b79b0a0a737bebb3c8d92..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/adapter_config.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
- "alora_invocation_tokens": null,
- "alpha_pattern": {},
- "arrow_config": null,
- "auto_mapping": null,
- "base_model_name_or_path": "C:\\Users\\Ifmanzhang\\Documents\\GitHub\\RepE\\merged_model",
- "bias": "none",
- "corda_config": null,
- "ensure_weight_tying": false,
- "eva_config": null,
- "exclude_modules": null,
- "fan_in_fan_out": false,
- "inference_mode": true,
- "init_lora_weights": true,
- "layer_replication": null,
- "layers_pattern": null,
- "layers_to_transform": null,
- "loftq_config": {},
- "lora_alpha": 32,
- "lora_bias": false,
- "lora_dropout": 0.05,
- "lora_ga_config": null,
- "megatron_config": null,
- "megatron_core": "megatron.core",
- "modules_to_save": null,
- "peft_type": "LORA",
- "peft_version": "0.19.1",
- "qalora_group_size": 16,
- "r": 16,
- "rank_pattern": {},
- "revision": null,
- "target_modules": [
- "in_proj_a",
- "up_proj",
- "in_proj_z",
- "in_proj_qkv",
- "down_proj",
- "o_proj",
- "gate_proj",
- "out_proj",
- "in_proj_b",
- "v_proj",
- "q_proj",
- "k_proj"
- ],
- "target_parameters": null,
- "task_type": "CAUSAL_LM",
- "trainable_token_indices": null,
- "use_bdlora": null,
- "use_dora": false,
- "use_qalora": false,
- "use_rslora": false
-}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-88/adapter_model.safetensors b/finetune/style_checkpoint/checkpoint-88/adapter_model.safetensors
deleted file mode 100644
index 5ea42a535c28a9ffec898939bc6fea87e2c5a5ce..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/adapter_model.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20987dd5ee42db82d2ee7a36c3946bd46bf1322676e20e213c09fecb8fa17b85
-size 86624424
diff --git a/finetune/style_checkpoint/checkpoint-88/chat_template.jinja b/finetune/style_checkpoint/checkpoint-88/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/finetune/style_checkpoint/checkpoint-88/optimizer.pt b/finetune/style_checkpoint/checkpoint-88/optimizer.pt
deleted file mode 100644
index 13909a4ad1a8f5d8d8a0f632402a14af2280f161..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b7601033c5f044d5c7d30a1a523fd76f8e63bfed7c6efe8eda9598e963da2d7d
-size 173539507
diff --git a/finetune/style_checkpoint/checkpoint-88/rng_state.pth b/finetune/style_checkpoint/checkpoint-88/rng_state.pth
deleted file mode 100644
index 0222025563c5966a6d09b07d7aef0020722f344f..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/rng_state.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1be481a9c3564c2cb0c9788473d7597b8abdb4e2715a65d53890f04d3387449a
-size 14645
diff --git a/finetune/style_checkpoint/checkpoint-88/scheduler.pt b/finetune/style_checkpoint/checkpoint-88/scheduler.pt
deleted file mode 100644
index a43b629344bf0a4197423dfe8456d59f6ab0ed35..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:054e5a002a383e39c553bf9255fa4db9738a25eda28b6d1003e6465b13063a37
-size 1465
diff --git a/finetune/style_checkpoint/checkpoint-88/tokenizer.json b/finetune/style_checkpoint/checkpoint-88/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/finetune/style_checkpoint/checkpoint-88/tokenizer_config.json b/finetune/style_checkpoint/checkpoint-88/tokenizer_config.json
deleted file mode 100644
index c487bad4ddddf9cfdb448b260a6ea942bb18a1b1..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": true,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/finetune/style_checkpoint/checkpoint-88/trainer_state.json b/finetune/style_checkpoint/checkpoint-88/trainer_state.json
deleted file mode 100644
index 970a523c59783bd26fe94aff317d126e56596eea..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/trainer_state.json
+++ /dev/null
@@ -1,114 +0,0 @@
-{
- "best_global_step": null,
- "best_metric": null,
- "best_model_checkpoint": null,
- "epoch": 2.0,
- "eval_steps": 500,
- "global_step": 88,
- "is_hyper_param_search": false,
- "is_local_process_zero": true,
- "is_world_process_zero": true,
- "log_history": [
- {
- "entropy": 1.30109671279788,
- "epoch": 0.22857142857142856,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00018636363636363636,
- "loss": 1.69281063079834,
- "mean_token_accuracy": 0.7338378168642521,
- "num_tokens": 2779.0,
- "step": 10
- },
- {
- "entropy": 1.2120113119482994,
- "epoch": 0.45714285714285713,
- "grad_norm": 1.3359375,
- "learning_rate": 0.00017121212121212122,
- "loss": 1.1274803161621094,
- "mean_token_accuracy": 0.770654023438692,
- "num_tokens": 5529.0,
- "step": 20
- },
- {
- "entropy": 0.9645026199519634,
- "epoch": 0.6857142857142857,
- "grad_norm": 1.3203125,
- "learning_rate": 0.00015606060606060607,
- "loss": 1.0083338737487793,
- "mean_token_accuracy": 0.7900982514023781,
- "num_tokens": 8264.0,
- "step": 30
- },
- {
- "entropy": 1.001315427571535,
- "epoch": 0.9142857142857143,
- "grad_norm": 1.2109375,
- "learning_rate": 0.00014090909090909093,
- "loss": 0.9876208305358887,
- "mean_token_accuracy": 0.7899081066250802,
- "num_tokens": 11028.0,
- "step": 40
- },
- {
- "entropy": 0.9025501891588553,
- "epoch": 1.1371428571428572,
- "grad_norm": 0.97265625,
- "learning_rate": 0.00012575757575757575,
- "loss": 0.7734798908233642,
- "mean_token_accuracy": 0.8246896488544269,
- "num_tokens": 13730.0,
- "step": 50
- },
- {
- "entropy": 0.7055704202502966,
- "epoch": 1.3657142857142857,
- "grad_norm": 1.453125,
- "learning_rate": 0.00011060606060606061,
- "loss": 0.6433767318725586,
- "mean_token_accuracy": 0.849166390299797,
- "num_tokens": 16506.0,
- "step": 60
- },
- {
- "entropy": 0.6749185953289271,
- "epoch": 1.5942857142857143,
- "grad_norm": 1.5078125,
- "learning_rate": 9.545454545454546e-05,
- "loss": 0.6674872398376465,
- "mean_token_accuracy": 0.8353129491209984,
- "num_tokens": 19267.0,
- "step": 70
- },
- {
- "entropy": 0.665529253333807,
- "epoch": 1.822857142857143,
- "grad_norm": 1.71875,
- "learning_rate": 8.03030303030303e-05,
- "loss": 0.6229500770568848,
- "mean_token_accuracy": 0.8385165937244892,
- "num_tokens": 22011.0,
- "step": 80
- }
- ],
- "logging_steps": 10,
- "max_steps": 132,
- "num_input_tokens_seen": 0,
- "num_train_epochs": 3,
- "save_steps": 500,
- "stateful_callbacks": {
- "TrainerControl": {
- "args": {
- "should_epoch_stop": false,
- "should_evaluate": false,
- "should_log": false,
- "should_save": true,
- "should_training_stop": false
- },
- "attributes": {}
- }
- },
- "total_flos": 1156200861757440.0,
- "train_batch_size": 1,
- "trial_name": null,
- "trial_params": null
-}
diff --git a/finetune/style_checkpoint/checkpoint-88/training_args.bin b/finetune/style_checkpoint/checkpoint-88/training_args.bin
deleted file mode 100644
index 7f27361f14f7dc02dec1eead2b3daa8836f3d029..0000000000000000000000000000000000000000
--- a/finetune/style_checkpoint/checkpoint-88/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b18b6c96a47cb78062355feafacc9baa8fde5cfda40273867df5486f7917195d
-size 5713
diff --git a/merged_model/chat_template.jinja b/merged_model/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/merged_model/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/merged_model/config.json b/merged_model/config.json
deleted file mode 100644
index bfe9aff6836f47b01a5dfb2f7c9b3af3b28435fc..0000000000000000000000000000000000000000
--- a/merged_model/config.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
- "architectures": [
- "Qwen3_5ForCausalLM"
- ],
- "attention_bias": false,
- "attention_dropout": 0.0,
- "attn_output_gate": true,
- "bos_token_id": null,
- "dtype": "bfloat16",
- "eos_token_id": 248044,
- "full_attention_interval": 4,
- "head_dim": 256,
- "hidden_act": "silu",
- "hidden_size": 4096,
- "initializer_range": 0.02,
- "intermediate_size": 12288,
- "layer_types": [
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention"
- ],
- "linear_conv_kernel_dim": 4,
- "linear_key_head_dim": 128,
- "linear_num_key_heads": 16,
- "linear_num_value_heads": 32,
- "linear_value_head_dim": 128,
- "mamba_ssm_dtype": "float32",
- "max_position_embeddings": 262144,
- "mlp_only_layers": [],
- "model_type": "qwen3_5_text",
- "mtp_num_hidden_layers": 1,
- "mtp_use_dedicated_embeddings": false,
- "num_attention_heads": 16,
- "num_hidden_layers": 32,
- "num_key_value_heads": 4,
- "pad_token_id": null,
- "partial_rotary_factor": 0.25,
- "rms_norm_eps": 1e-06,
- "rope_parameters": {
- "mrope_interleaved": true,
- "mrope_section": [
- 11,
- 11,
- 10
- ],
- "partial_rotary_factor": 0.25,
- "rope_theta": 10000000,
- "rope_type": "default"
- },
- "tie_word_embeddings": false,
- "transformers_version": "5.6.2",
- "use_cache": true,
- "vocab_size": 248320
-}
diff --git a/merged_model/generation_config.json b/merged_model/generation_config.json
deleted file mode 100644
index a523850e65f4ef8369550f156b48326b667b46d1..0000000000000000000000000000000000000000
--- a/merged_model/generation_config.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "_from_model_config": true,
- "eos_token_id": 248044,
- "transformers_version": "5.6.2",
- "use_cache": true
-}
diff --git a/merged_model/model-00001-of-00005.safetensors b/merged_model/model-00001-of-00005.safetensors
deleted file mode 100644
index 7a1670492c725c5be68f6ca47956025cbe4b1cf5..0000000000000000000000000000000000000000
--- a/merged_model/model-00001-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd63614f1dc80dce2d83be3f3e69af1f8a0ebc8add9b8e0abf3910f563e44344
-size 2034237568
diff --git a/merged_model/model-00002-of-00005.safetensors b/merged_model/model-00002-of-00005.safetensors
deleted file mode 100644
index dafc56d49bffd932f688e6ed8212b69fd7bc48d1..0000000000000000000000000000000000000000
--- a/merged_model/model-00002-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8e10500e950d212654a43b5abb99eac3c34f55c68de8e0b86a2e6555a6c0d5a
-size 3999615808
diff --git a/merged_model/model-00003-of-00005.safetensors b/merged_model/model-00003-of-00005.safetensors
deleted file mode 100644
index 1d00560ee59fd7b8819a306d25a22b4d16d34ee8..0000000000000000000000000000000000000000
--- a/merged_model/model-00003-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:187b318d2223855135a11c2c66dfe7b881939d53a25a1e3df4774f5521468c15
-size 3997274128
diff --git a/merged_model/model-00004-of-00005.safetensors b/merged_model/model-00004-of-00005.safetensors
deleted file mode 100644
index e33e809d6eab41a9a4afebb97e564c8f37185086..0000000000000000000000000000000000000000
--- a/merged_model/model-00004-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bb71b004a2ad4ded13625d09db3dfd91f44ae587a4a47a81bb862fc58aa3ebdb
-size 3997290904
diff --git a/merged_model/model-00005-of-00005.safetensors b/merged_model/model-00005-of-00005.safetensors
deleted file mode 100644
index b19404bab298deaee07f0e7dd90eb168aeb35d13..0000000000000000000000000000000000000000
--- a/merged_model/model-00005-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:42a879038976609a1780f318e227eb809036b8ed79fdc3bf48026a9bdb713965
-size 3879244000
diff --git a/merged_model/model.safetensors.index.json b/merged_model/model.safetensors.index.json
deleted file mode 100644
index 094a22c4de28768fbbcf633cf516e12452a52354..0000000000000000000000000000000000000000
--- a/merged_model/model.safetensors.index.json
+++ /dev/null
@@ -1,435 +0,0 @@
-{
- "metadata": {
- "total_parameters": 8953803264,
- "total_size": 17907606528
- },
- "weight_map": {
- "lm_head.weight": "model-00001-of-00005.safetensors",
- "model.language_model.embed_tokens.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.23.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.4.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.norm.weight": "model-00005-of-00005.safetensors"
- }
-}
diff --git a/merged_model/tokenizer.json b/merged_model/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/merged_model/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/merged_model/tokenizer_config.json b/merged_model/tokenizer_config.json
deleted file mode 100644
index ab901d8dd18462b5a5243a09a182e68f7e37940b..0000000000000000000000000000000000000000
--- a/merged_model/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": false,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}
diff --git a/merged_model_v2/chat_template.jinja b/merged_model_v2/chat_template.jinja
deleted file mode 100644
index 945efe1d21131a610bda2fa5b29fa0f61027139f..0000000000000000000000000000000000000000
--- a/merged_model_v2/chat_template.jinja
+++ /dev/null
@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
- {%- if content is string %}
- {{- content }}
- {%- elif content is iterable and content is not mapping %}
- {%- for item in content %}
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain images.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set image_count.value = image_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
- {%- elif 'video' in item or item.type == 'video' %}
- {%- if is_system_content %}
- {{- raise_exception('System message cannot contain videos.') }}
- {%- endif %}
- {%- if do_vision_count %}
- {%- set video_count.value = video_count.value + 1 %}
- {%- endif %}
- {%- if add_vision_id %}
- {{- 'Video ' ~ video_count.value ~ ': ' }}
- {%- endif %}
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
- {%- elif 'text' in item %}
- {{- item.text }}
- {%- else %}
- {{- raise_exception('Unexpected item type in content.') }}
- {%- endif %}
- {%- endfor %}
- {%- elif content is none or content is undefined %}
- {{- '' }}
- {%- else %}
- {{- raise_exception('Unexpected content type.') }}
- {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
- {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
- {{- '<|im_start|>system\n' }}
- {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
- {%- for tool in tools %}
- {{- "\n" }}
- {{- tool | tojson }}
- {%- endfor %}
- {{- "\n" }}
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {%- if content %}
- {{- '\n\n' + content }}
- {%- endif %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
-{%- else %}
- {%- if messages[0].role == 'system' %}
- {%- set content = render_content(messages[0].content, false, true)|trim %}
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
- {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
- {%- set index = (messages|length - 1) - loop.index0 %}
- {%- if ns.multi_step_tool and message.role == "user" %}
- {%- set content = render_content(message.content, false)|trim %}
- {%- if not(content.startswith('') and content.endswith('')) %}
- {%- set ns.multi_step_tool = false %}
- {%- set ns.last_query_index = index %}
- {%- endif %}
- {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
- {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
- {%- set content = render_content(message.content, true)|trim %}
- {%- if message.role == "system" %}
- {%- if not loop.first %}
- {{- raise_exception('System message must be at the beginning.') }}
- {%- endif %}
- {%- elif message.role == "user" %}
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
- {%- elif message.role == "assistant" %}
- {%- set reasoning_content = '' %}
- {%- if message.reasoning_content is string %}
- {%- set reasoning_content = message.reasoning_content %}
- {%- else %}
- {%- if '' in content %}
- {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
- {%- set content = content.split('')[-1].lstrip('\n') %}
- {%- endif %}
- {%- endif %}
- {%- set reasoning_content = reasoning_content|trim %}
- {%- if loop.index0 > ns.last_query_index %}
- {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
- {%- else %}
- {{- '<|im_start|>' + message.role + '\n' + content }}
- {%- endif %}
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
- {%- for tool_call in message.tool_calls %}
- {%- if tool_call.function is defined %}
- {%- set tool_call = tool_call.function %}
- {%- endif %}
- {%- if loop.first %}
- {%- if content|trim %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n\n' }}
- {%- endif %}
- {%- else %}
- {{- '\n\n\n' }}
- {%- endif %}
- {%- if tool_call.arguments is defined %}
- {%- for args_name, args_value in tool_call.arguments|items %}
- {{- '\n' }}
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
- {{- args_value }}
- {{- '\n\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '\n' }}
- {%- endfor %}
- {%- endif %}
- {{- '<|im_end|>\n' }}
- {%- elif message.role == "tool" %}
- {%- if loop.previtem and loop.previtem.role != "tool" %}
- {{- '<|im_start|>user' }}
- {%- endif %}
- {{- '\n\n' }}
- {{- content }}
- {{- '\n' }}
- {%- if not loop.last and loop.nextitem.role != "tool" %}
- {{- '<|im_end|>\n' }}
- {%- elif loop.last %}
- {{- '<|im_end|>\n' }}
- {%- endif %}
- {%- else %}
- {{- raise_exception('Unexpected message role.') }}
- {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
- {{- '<|im_start|>assistant\n' }}
- {%- if enable_thinking is defined and enable_thinking is false %}
- {{- '\n\n\n\n' }}
- {%- else %}
- {{- '\n' }}
- {%- endif %}
-{%- endif %}
\ No newline at end of file
diff --git a/merged_model_v2/config.json b/merged_model_v2/config.json
deleted file mode 100644
index bfe9aff6836f47b01a5dfb2f7c9b3af3b28435fc..0000000000000000000000000000000000000000
--- a/merged_model_v2/config.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
- "architectures": [
- "Qwen3_5ForCausalLM"
- ],
- "attention_bias": false,
- "attention_dropout": 0.0,
- "attn_output_gate": true,
- "bos_token_id": null,
- "dtype": "bfloat16",
- "eos_token_id": 248044,
- "full_attention_interval": 4,
- "head_dim": 256,
- "hidden_act": "silu",
- "hidden_size": 4096,
- "initializer_range": 0.02,
- "intermediate_size": 12288,
- "layer_types": [
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention",
- "linear_attention",
- "linear_attention",
- "linear_attention",
- "full_attention"
- ],
- "linear_conv_kernel_dim": 4,
- "linear_key_head_dim": 128,
- "linear_num_key_heads": 16,
- "linear_num_value_heads": 32,
- "linear_value_head_dim": 128,
- "mamba_ssm_dtype": "float32",
- "max_position_embeddings": 262144,
- "mlp_only_layers": [],
- "model_type": "qwen3_5_text",
- "mtp_num_hidden_layers": 1,
- "mtp_use_dedicated_embeddings": false,
- "num_attention_heads": 16,
- "num_hidden_layers": 32,
- "num_key_value_heads": 4,
- "pad_token_id": null,
- "partial_rotary_factor": 0.25,
- "rms_norm_eps": 1e-06,
- "rope_parameters": {
- "mrope_interleaved": true,
- "mrope_section": [
- 11,
- 11,
- 10
- ],
- "partial_rotary_factor": 0.25,
- "rope_theta": 10000000,
- "rope_type": "default"
- },
- "tie_word_embeddings": false,
- "transformers_version": "5.6.2",
- "use_cache": true,
- "vocab_size": 248320
-}
diff --git a/merged_model_v2/generation_config.json b/merged_model_v2/generation_config.json
deleted file mode 100644
index a523850e65f4ef8369550f156b48326b667b46d1..0000000000000000000000000000000000000000
--- a/merged_model_v2/generation_config.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "_from_model_config": true,
- "eos_token_id": 248044,
- "transformers_version": "5.6.2",
- "use_cache": true
-}
diff --git a/merged_model_v2/model-00001-of-00005.safetensors b/merged_model_v2/model-00001-of-00005.safetensors
deleted file mode 100644
index 7a1670492c725c5be68f6ca47956025cbe4b1cf5..0000000000000000000000000000000000000000
--- a/merged_model_v2/model-00001-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd63614f1dc80dce2d83be3f3e69af1f8a0ebc8add9b8e0abf3910f563e44344
-size 2034237568
diff --git a/merged_model_v2/model-00002-of-00005.safetensors b/merged_model_v2/model-00002-of-00005.safetensors
deleted file mode 100644
index 9869f487bbd7f59debcd7b2d720ac3abeaac9ee4..0000000000000000000000000000000000000000
--- a/merged_model_v2/model-00002-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:400f775045bc28fb3624c2ecd516306deabce04e10843832893257ab383bfe88
-size 3999615808
diff --git a/merged_model_v2/model-00003-of-00005.safetensors b/merged_model_v2/model-00003-of-00005.safetensors
deleted file mode 100644
index 3c0a916aaafd47a2d1632c8813853d5e46d94730..0000000000000000000000000000000000000000
--- a/merged_model_v2/model-00003-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d4b0f31efa766606421c328df3a151eec8fb83aff99cab4a166bcc8b051b2df
-size 3997274128
diff --git a/merged_model_v2/model-00004-of-00005.safetensors b/merged_model_v2/model-00004-of-00005.safetensors
deleted file mode 100644
index 13a7774fcd5d3f2c345c8f28edae7fae4f8bf7ac..0000000000000000000000000000000000000000
--- a/merged_model_v2/model-00004-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86b9b7e75f24c77cb2e259cd38f786c78aa2ef419b3ebc616b7b4bbde4eda44a
-size 3997290904
diff --git a/merged_model_v2/model-00005-of-00005.safetensors b/merged_model_v2/model-00005-of-00005.safetensors
deleted file mode 100644
index 5a04bc4916630f037fa6a08f2df3c87340ef0f14..0000000000000000000000000000000000000000
--- a/merged_model_v2/model-00005-of-00005.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3fccb3444ef786576bc8248659e931208160d1119570f23da6839da3a0a77273
-size 3879244000
diff --git a/merged_model_v2/model.safetensors.index.json b/merged_model_v2/model.safetensors.index.json
deleted file mode 100644
index 094a22c4de28768fbbcf633cf516e12452a52354..0000000000000000000000000000000000000000
--- a/merged_model_v2/model.safetensors.index.json
+++ /dev/null
@@ -1,435 +0,0 @@
-{
- "metadata": {
- "total_parameters": 8953803264,
- "total_size": 17907606528
- },
- "weight_map": {
- "lm_head.weight": "model-00001-of-00005.safetensors",
- "model.language_model.embed_tokens.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.A_log": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
- "model.language_model.layers.23.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.A_log": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
- "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
- "model.language_model.layers.4.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.4.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.A_log": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
- "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
- "model.language_model.norm.weight": "model-00005-of-00005.safetensors"
- }
-}
diff --git a/merged_model_v2/tokenizer.json b/merged_model_v2/tokenizer.json
deleted file mode 100644
index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000
--- a/merged_model_v2/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
diff --git a/merged_model_v2/tokenizer_config.json b/merged_model_v2/tokenizer_config.json
deleted file mode 100644
index c487bad4ddddf9cfdb448b260a6ea942bb18a1b1..0000000000000000000000000000000000000000
--- a/merged_model_v2/tokenizer_config.json
+++ /dev/null
@@ -1,32 +0,0 @@
-{
- "add_prefix_space": false,
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "backend": "tokenizers",
- "bos_token": null,
- "clean_up_tokenization_spaces": false,
- "eos_token": "<|im_end|>",
- "errors": "replace",
- "image_token": "<|image_pad|>",
- "is_local": true,
- "local_files_only": false,
- "model_max_length": 262144,
- "model_specific_special_tokens": {
- "audio_bos_token": "<|audio_start|>",
- "audio_eos_token": "<|audio_end|>",
- "audio_token": "<|audio_pad|>",
- "image_token": "<|image_pad|>",
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
- },
- "pad_token": "<|endoftext|>",
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
- "split_special_tokens": false,
- "tokenizer_class": "Qwen2Tokenizer",
- "unk_token": null,
- "video_token": "<|video_pad|>",
- "vision_bos_token": "<|vision_start|>",
- "vision_eos_token": "<|vision_end|>"
-}