diff --git a/README.md b/README.md index f40a4e60913e698b317c65c63ca180e0c97af8b3..5c59a3f112fb554cab5783267ec49912706b11f8 100644 --- a/README.md +++ b/README.md @@ -60,50 +60,42 @@ frames and actions) and returns the next **200 ms of keyboard and mouse actions* 33 ms each, plus one mouse movement and scroll for the whole chunk. The model may think before it acts. -This repository contains eight checkpoints, the inference client, and the standard system-prompt -template. It is everything needed to serve a checkpoint and run it in a game; it contains no -training code. Paper results and analysis are on the [project page](https://gamescaling.github.io). +This repository contains the inference client and the standard system-prompt template; each of the +eight checkpoints is its own repository (below). Together they are everything needed to serve a +checkpoint and run it in a game; there is no training code. Paper results and analysis are on the [project page](https://gamescaling.github.io). ## Checkpoints -| Model | Folder | Weights | GPUs (bf16) | -|---|---|---:|:---:| -| GameScaling-0.8B-S1 | `models/0p8b_s1_1600h_gs6736` | 2.2 GB | 1 | -| GameScaling-0.8B-S3 | `models/0p8b_s3_1600h_gs6760` | 2.2 GB | 1 | -| GameScaling-2B-S1 | `models/2b_s1_1600h_gs6736` | 5.4 GB | 1 | -| GameScaling-2B-S3 | `models/2b_s3_1600h_gs6760` | 5.4 GB | 1 | -| GameScaling-9B-S1 | `models/9b_s1_1600h_gs6736` | 18.8 GB | 1 | -| GameScaling-9B-S3 | `models/9b_s3_1600h_gs6760` | 18.8 GB | 1 | -| GameScaling-27B-S1 | `models/27b_s1_1600h_gs6995` | 54.7 GB | 2 (tensor parallel) | -| GameScaling-27B-S3 | `models/27b_s3_1600h_gs7020` | 54.7 GB | 2 (tensor parallel) | +| Model | Training steps | Weights | GPUs (bf16) | +|---|---:|---:|:---:| +| [GameScaling-0.8B-S1](https://huggingface.co/THUSI-Lab/GameScaling-0.8B-S1) | 6,736 | 2.2 GB | 1 | +| [GameScaling-0.8B-S3](https://huggingface.co/THUSI-Lab/GameScaling-0.8B-S3) | 6,760 | 2.2 GB | 1 | +| [GameScaling-2B-S1](https://huggingface.co/THUSI-Lab/GameScaling-2B-S1) | 6,736 | 5.4 GB | 1 | +| [GameScaling-2B-S3](https://huggingface.co/THUSI-Lab/GameScaling-2B-S3) | 6,760 | 5.4 GB | 1 | +| [GameScaling-9B-S1](https://huggingface.co/THUSI-Lab/GameScaling-9B-S1) | 6,736 | 18.8 GB | 1 | +| [GameScaling-9B-S3](https://huggingface.co/THUSI-Lab/GameScaling-9B-S3) | 6,760 | 18.8 GB | 1 | +| [GameScaling-27B-S1](https://huggingface.co/THUSI-Lab/GameScaling-27B-S1) | 6,995 | 54.7 GB | 2 (tensor parallel) | +| [GameScaling-27B-S3](https://huggingface.co/THUSI-Lab/GameScaling-27B-S3) | 7,020 | 54.7 GB | 2 (tensor parallel) | - **S1** is trained on Minecraft gameplay only. **S3** is a balanced mixture: 27% Minecraft, the rest from other games. All checkpoints use 1,600 h of gameplay. -- Folder names are `__h_gs`. Weights are bfloat16, from the - Qwen3.5-0.8B / 2B / 9B / 27B backbones. +- Weights are bfloat16, from the Qwen3.5-0.8B / 2B / 9B / 27B backbones. ## File tree ```text +THUSI-Lab/GameScaling-- one repository per checkpoint +├── config.json Qwen3.5 architecture, bfloat16 +├── model.safetensors weights (27B: 2 shards + index) +├── chat_template.jinja required, renders history turns +├── tokenizer.json +├── tokenizer_config.json +├── generation_config.json +├── preprocessor_config.json +├── processor_config.json +└── video_preprocessor_config.json + THUSI-Lab/GameScaling -├── models/ eight checkpoints, one folder each -│ ├── 0p8b_s1_1600h_gs6736/ -│ │ ├── config.json Qwen3.5 architecture, bfloat16 -│ │ ├── model.safetensors weights (27B: 2 shards + index) -│ │ ├── chat_template.jinja required, renders history turns -│ │ ├── tokenizer.json -│ │ ├── tokenizer_config.json -│ │ ├── generation_config.json -│ │ ├── preprocessor_config.json -│ │ ├── processor_config.json -│ │ └── video_preprocessor_config.json -│ ├── 0p8b_s3_1600h_gs6760/ -│ ├── 2b_s1_1600h_gs6736/ -│ ├── 2b_s3_1600h_gs6760/ -│ ├── 9b_s1_1600h_gs6736/ -│ ├── 9b_s3_1600h_gs6760/ -│ ├── 27b_s1_1600h_gs6995/ -│ └── 27b_s3_1600h_gs7020/ ├── prompts/ │ ├── system_prompt_template.txt standard prompt, 3 slots (§2) │ └── example_doom_battle1.txt complete Doom prompt (§2) @@ -125,23 +117,27 @@ THUSI-Lab/GameScaling ## 1. Download and serve -Download only the checkpoint you need: +Download the client and scripts from this repository: ```bash pip install -U huggingface_hub -huggingface-cli download THUSI-Lab/GameScaling \ - --include "models/9b_s1_1600h_gs6736/*" "gamescaling/*" "prompts/*" "scripts/*" \ - "examples/*" "tests/*" "requirements.txt" \ - --local-dir ./GameScaling +huggingface-cli download THUSI-Lab/GameScaling --exclude "assets/*" --local-dir ./GameScaling cd GameScaling ``` -Serve it with vLLM (tested with 0.17.0): +Serve a checkpoint with vLLM (tested with 0.17.0); vLLM fetches the weights from its repository: ```bash pip install "vllm>=0.17" -bash scripts/serve_vllm.sh models/9b_s1_1600h_gs6736 8000 # 0.8B-9B fit on one GPU -bash scripts/serve_vllm.sh models/27b_s1_1600h_gs6995 8000 2 # 27B: tensor parallel 2 +bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-9B-S1 8000 # 0.8B-9B fit on one GPU +bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-27B-S1 8000 2 # 27B: tensor parallel 2 +``` + +To keep the weights in a local folder instead, download the checkpoint repository and pass its path: + +```bash +huggingface-cli download THUSI-Lab/GameScaling-9B-S1 --local-dir ./GameScaling-9B-S1 +bash scripts/serve_vllm.sh ./GameScaling-9B-S1 8000 ``` `serve_vllm.sh CKPT [PORT] [TP]` starts vLLM with `--served-model-name gamescaling`, bfloat16, @@ -159,7 +155,7 @@ python tests/test_core.py # offline checks, no server ne Things to keep as shipped: -- **Chat template.** Use the `chat_template.jinja` in the checkpoint folder (vLLM loads it by +- **Chat template.** Use the `chat_template.jinja` in the checkpoint repository (vLLM loads it by default). Do not replace it with the stock Qwen template: this one renders past turns without reasoning as `\n\n\n\n<|action_start|>...`, token-for-token as in training. - **Special tokens.** Requests must set `skip_special_tokens: false`, or the server strips the diff --git a/examples/run_example.py b/examples/run_example.py index e843aecadf3958c2011ec97c518b4ebb91e64cfc..e6dfd24cb205cb8934e9c5b43c416b6140ee72cf 100644 --- a/examples/run_example.py +++ b/examples/run_example.py @@ -5,7 +5,7 @@ GameScaling-9B-S3, and `examples/doom_battle1_action.txt` is the reply the model gave on that frame (a monster just left of the crosshair: turn left and fire). python examples/run_example.py --offline # parse the reference reply only - bash scripts/serve_vllm.sh models/9b_s3_1600h_gs6760 8000 + bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-9B-S3 8000 python examples/run_example.py # prefill python examples/run_example.py --no-reasoning # prefill \\n\\n diff --git a/models/0p8b_s1_1600h_gs6736/chat_template.jinja b/models/0p8b_s1_1600h_gs6736/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/0p8b_s1_1600h_gs6736/config.json b/models/0p8b_s1_1600h_gs6736/config.json deleted file mode 100644 index 0b4f7fab67dee310ad4a9321ac18549dabb1b344..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/config.json +++ /dev/null @@ -1,104 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 1024, - "initializer_range": 0.02, - "intermediate_size": 3584, - "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_conv_kernel_dim": 4, - "linear_key_head_dim": 128, - "linear_num_key_heads": 16, - "linear_num_value_heads": 16, - "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": 8, - "num_hidden_layers": 24, - "num_key_value_heads": 2, - "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": true, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": true, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 12, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 768, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 3072, - "model_type": "qwen3_5_vision", - "num_heads": 12, - "num_position_embeddings": 2304, - "out_hidden_size": 1024, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/0p8b_s1_1600h_gs6736/generation_config.json b/models/0p8b_s1_1600h_gs6736/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/0p8b_s1_1600h_gs6736/model.safetensors b/models/0p8b_s1_1600h_gs6736/model.safetensors deleted file mode 100644 index d108aa9cef83a2621379b703c73cdb91b6b7527e..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b2986b2a0deec5dd76c8c72946e7f65daf4b695c76c9b01c4f5fff9433dbeb67 -size 2214590296 diff --git a/models/0p8b_s1_1600h_gs6736/preprocessor_config.json b/models/0p8b_s1_1600h_gs6736/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/0p8b_s1_1600h_gs6736/processor_config.json b/models/0p8b_s1_1600h_gs6736/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/0p8b_s1_1600h_gs6736/tokenizer.json b/models/0p8b_s1_1600h_gs6736/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/0p8b_s1_1600h_gs6736/tokenizer_config.json b/models/0p8b_s1_1600h_gs6736/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/0p8b_s1_1600h_gs6736/video_preprocessor_config.json b/models/0p8b_s1_1600h_gs6736/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/0p8b_s1_1600h_gs6736/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/0p8b_s3_1600h_gs6760/chat_template.jinja b/models/0p8b_s3_1600h_gs6760/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/0p8b_s3_1600h_gs6760/config.json b/models/0p8b_s3_1600h_gs6760/config.json deleted file mode 100644 index 0b4f7fab67dee310ad4a9321ac18549dabb1b344..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/config.json +++ /dev/null @@ -1,104 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 1024, - "initializer_range": 0.02, - "intermediate_size": 3584, - "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_conv_kernel_dim": 4, - "linear_key_head_dim": 128, - "linear_num_key_heads": 16, - "linear_num_value_heads": 16, - "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": 8, - "num_hidden_layers": 24, - "num_key_value_heads": 2, - "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": true, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": true, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 12, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 768, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 3072, - "model_type": "qwen3_5_vision", - "num_heads": 12, - "num_position_embeddings": 2304, - "out_hidden_size": 1024, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/0p8b_s3_1600h_gs6760/generation_config.json b/models/0p8b_s3_1600h_gs6760/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/0p8b_s3_1600h_gs6760/model.safetensors b/models/0p8b_s3_1600h_gs6760/model.safetensors deleted file mode 100644 index 95f3a1f3a79fe73b52943313fb7bdd8e3f2d62c1..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d553c0796833691e32277a937db649eaac39bae9a0028a63c964c12a261c2dfa -size 2214590296 diff --git a/models/0p8b_s3_1600h_gs6760/preprocessor_config.json b/models/0p8b_s3_1600h_gs6760/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/0p8b_s3_1600h_gs6760/processor_config.json b/models/0p8b_s3_1600h_gs6760/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/0p8b_s3_1600h_gs6760/tokenizer.json b/models/0p8b_s3_1600h_gs6760/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/0p8b_s3_1600h_gs6760/tokenizer_config.json b/models/0p8b_s3_1600h_gs6760/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/0p8b_s3_1600h_gs6760/video_preprocessor_config.json b/models/0p8b_s3_1600h_gs6760/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/0p8b_s3_1600h_gs6760/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/27b_s1_1600h_gs6995/chat_template.jinja b/models/27b_s1_1600h_gs6995/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/27b_s1_1600h_gs6995/config.json b/models/27b_s1_1600h_gs6995/config.json deleted file mode 100644 index 917fdda9a2036f3174e01a10578f076436e5e1b8..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/config.json +++ /dev/null @@ -1,144 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 5120, - "initializer_range": 0.02, - "intermediate_size": 17408, - "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_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": 48, - "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": 24, - "num_hidden_layers": 64, - "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, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": false, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 27, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1152, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4304, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 5120, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/27b_s1_1600h_gs6995/generation_config.json b/models/27b_s1_1600h_gs6995/generation_config.json deleted file mode 100644 index b49b15c44e72a9b7fe46d127986faacdb6ab8eec..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/generation_config.json +++ /dev/null @@ -1,13 +0,0 @@ -{ - "bos_token_id": 248044, - "do_sample": true, - "eos_token_id": [ - 248046, - 248044 - ], - "pad_token_id": 248044, - "temperature": 0.6, - "top_k": 20, - "top_p": 0.95, - "transformers_version": "5.14.1" -} diff --git a/models/27b_s1_1600h_gs6995/model-00001-of-00002.safetensors b/models/27b_s1_1600h_gs6995/model-00001-of-00002.safetensors deleted file mode 100644 index c333d3b430f228e024a028e246402d52325cda8e..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/model-00001-of-00002.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:170b268eccf87f9c19d81bae8b78672aba2d996a159192dc7c83ac6a2a5c6d0d -size 49935066216 diff --git a/models/27b_s1_1600h_gs6995/model-00002-of-00002.safetensors b/models/27b_s1_1600h_gs6995/model-00002-of-00002.safetensors deleted file mode 100644 index 545cc97837378c1123b50f8cc7f9d20fd0c18f92..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/model-00002-of-00002.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:753c79c6f45331d98f0be24b72df6defbfd8daa5d583b3edf203fc417b83a222 -size 4778542568 diff --git a/models/27b_s1_1600h_gs6995/model.safetensors.index.json b/models/27b_s1_1600h_gs6995/model.safetensors.index.json deleted file mode 100644 index 34f12f9fe39c33ecf672ad8f34bd1fcc0a87e15a..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/model.safetensors.index.json +++ /dev/null @@ -1,1192 +0,0 @@ -{ - "metadata": { - "total_parameters": 27356728560, - "total_size": 54713457120 - }, - "weight_map": { - "lm_head.weight": "model-00001-of-00002.safetensors", - "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.48.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.50.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.51.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.52.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.53.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.54.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.55.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.56.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.57.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.58.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.59.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.60.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.61.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.62.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.63.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.norm.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", - "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", - "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", - "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", - "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", - "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", - "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", - "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", - "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", - "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", - "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" - } -} diff --git a/models/27b_s1_1600h_gs6995/preprocessor_config.json b/models/27b_s1_1600h_gs6995/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/27b_s1_1600h_gs6995/processor_config.json b/models/27b_s1_1600h_gs6995/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/27b_s1_1600h_gs6995/tokenizer.json b/models/27b_s1_1600h_gs6995/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/27b_s1_1600h_gs6995/tokenizer_config.json b/models/27b_s1_1600h_gs6995/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/27b_s1_1600h_gs6995/video_preprocessor_config.json b/models/27b_s1_1600h_gs6995/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/27b_s1_1600h_gs6995/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/27b_s3_1600h_gs7020/chat_template.jinja b/models/27b_s3_1600h_gs7020/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/27b_s3_1600h_gs7020/config.json b/models/27b_s3_1600h_gs7020/config.json deleted file mode 100644 index 917fdda9a2036f3174e01a10578f076436e5e1b8..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/config.json +++ /dev/null @@ -1,144 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 5120, - "initializer_range": 0.02, - "intermediate_size": 17408, - "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_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": 48, - "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": 24, - "num_hidden_layers": 64, - "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, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": false, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 27, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1152, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4304, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 5120, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/27b_s3_1600h_gs7020/generation_config.json b/models/27b_s3_1600h_gs7020/generation_config.json deleted file mode 100644 index b49b15c44e72a9b7fe46d127986faacdb6ab8eec..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/generation_config.json +++ /dev/null @@ -1,13 +0,0 @@ -{ - "bos_token_id": 248044, - "do_sample": true, - "eos_token_id": [ - 248046, - 248044 - ], - "pad_token_id": 248044, - "temperature": 0.6, - "top_k": 20, - "top_p": 0.95, - "transformers_version": "5.14.1" -} diff --git a/models/27b_s3_1600h_gs7020/model-00001-of-00002.safetensors b/models/27b_s3_1600h_gs7020/model-00001-of-00002.safetensors deleted file mode 100644 index 3d1f9c77f24aa6c14e8195e7a61fe7bb8cf178ae..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/model-00001-of-00002.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9138f232014c26a45fd8f8a519180eb9a986fdfc4ac2c8649635552dfc352f6e -size 29848868595 diff --git a/models/27b_s3_1600h_gs7020/model-00002-of-00002.safetensors b/models/27b_s3_1600h_gs7020/model-00002-of-00002.safetensors deleted file mode 100644 index 6e0b58c43a8cd03f222f403eafc3b9b12b5fa9b1..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/model-00002-of-00002.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f008fc3ec5f8a24ff6b2b9607030858a7ce24cec84dea98f5675e562e285187a -size 24864740005 diff --git a/models/27b_s3_1600h_gs7020/model.safetensors.index.json b/models/27b_s3_1600h_gs7020/model.safetensors.index.json deleted file mode 100644 index 3908f0db746a86aa3607a83022448b97a821eeb7..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/model.safetensors.index.json +++ /dev/null @@ -1,1191 +0,0 @@ -{ - "metadata": { - "total_size": 54713457120 - }, - "weight_map": { - "lm_head.weight": "model-00001-of-00002.safetensors", - "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.A_log": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.dt_bias": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.norm.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors", - "model.language_model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.62.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.63.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", - "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", - "model.language_model.norm.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", - "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", - "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", - "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", - "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", - "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", - "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", - "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors", - "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", - "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", - "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" - } -} \ No newline at end of file diff --git a/models/27b_s3_1600h_gs7020/preprocessor_config.json b/models/27b_s3_1600h_gs7020/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/27b_s3_1600h_gs7020/processor_config.json b/models/27b_s3_1600h_gs7020/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/27b_s3_1600h_gs7020/tokenizer.json b/models/27b_s3_1600h_gs7020/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/27b_s3_1600h_gs7020/tokenizer_config.json b/models/27b_s3_1600h_gs7020/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/27b_s3_1600h_gs7020/video_preprocessor_config.json b/models/27b_s3_1600h_gs7020/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/27b_s3_1600h_gs7020/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/2b_s1_1600h_gs6736/chat_template.jinja b/models/2b_s1_1600h_gs6736/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/2b_s1_1600h_gs6736/config.json b/models/2b_s1_1600h_gs6736/config.json deleted file mode 100644 index 7e5e8b6c56b2c847ca7ca5d4b7c677288f4fa42b..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/config.json +++ /dev/null @@ -1,104 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 2048, - "initializer_range": 0.02, - "intermediate_size": 6144, - "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_conv_kernel_dim": 4, - "linear_key_head_dim": 128, - "linear_num_key_heads": 16, - "linear_num_value_heads": 16, - "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": 8, - "num_hidden_layers": 24, - "num_key_value_heads": 2, - "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": true, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": true, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 24, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1024, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4096, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 2048, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/2b_s1_1600h_gs6736/generation_config.json b/models/2b_s1_1600h_gs6736/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/2b_s1_1600h_gs6736/model.safetensors b/models/2b_s1_1600h_gs6736/model.safetensors deleted file mode 100644 index a1b6e29fd27e468b927451c0db4c2ea8e836e7d5..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:320dd2f7e1804faceae76fbfd6bfb83f17c9294a369bebf07cf1f3278dec3351 -size 5443677680 diff --git a/models/2b_s1_1600h_gs6736/preprocessor_config.json b/models/2b_s1_1600h_gs6736/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/2b_s1_1600h_gs6736/processor_config.json b/models/2b_s1_1600h_gs6736/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/2b_s1_1600h_gs6736/tokenizer.json b/models/2b_s1_1600h_gs6736/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/2b_s1_1600h_gs6736/tokenizer_config.json b/models/2b_s1_1600h_gs6736/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/2b_s1_1600h_gs6736/video_preprocessor_config.json b/models/2b_s1_1600h_gs6736/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/2b_s1_1600h_gs6736/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/2b_s3_1600h_gs6760/chat_template.jinja b/models/2b_s3_1600h_gs6760/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/2b_s3_1600h_gs6760/config.json b/models/2b_s3_1600h_gs6760/config.json deleted file mode 100644 index 7e5e8b6c56b2c847ca7ca5d4b7c677288f4fa42b..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/config.json +++ /dev/null @@ -1,104 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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": 2048, - "initializer_range": 0.02, - "intermediate_size": 6144, - "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_conv_kernel_dim": 4, - "linear_key_head_dim": 128, - "linear_num_key_heads": 16, - "linear_num_value_heads": 16, - "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": 8, - "num_hidden_layers": 24, - "num_key_value_heads": 2, - "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": true, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": true, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 24, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1024, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4096, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 2048, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/2b_s3_1600h_gs6760/generation_config.json b/models/2b_s3_1600h_gs6760/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/2b_s3_1600h_gs6760/model.safetensors b/models/2b_s3_1600h_gs6760/model.safetensors deleted file mode 100644 index 42b0977d295cba83910dd46dfb6611b06c7e539b..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:97018239265aed03c16afa0f2acb035a428a3e66195a20518cf3c14dcfe289e8 -size 5443677680 diff --git a/models/2b_s3_1600h_gs6760/preprocessor_config.json b/models/2b_s3_1600h_gs6760/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/2b_s3_1600h_gs6760/processor_config.json b/models/2b_s3_1600h_gs6760/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/2b_s3_1600h_gs6760/tokenizer.json b/models/2b_s3_1600h_gs6760/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/2b_s3_1600h_gs6760/tokenizer_config.json b/models/2b_s3_1600h_gs6760/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/2b_s3_1600h_gs6760/video_preprocessor_config.json b/models/2b_s3_1600h_gs6760/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/2b_s3_1600h_gs6760/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/9b_s1_1600h_gs6736/chat_template.jinja b/models/9b_s1_1600h_gs6736/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/9b_s1_1600h_gs6736/config.json b/models/9b_s1_1600h_gs6736/config.json deleted file mode 100644 index 6d35c090be9c5bfef11d7c54527a83e15e176f41..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/config.json +++ /dev/null @@ -1,112 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": false, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 27, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1152, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4304, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 4096, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/9b_s1_1600h_gs6736/generation_config.json b/models/9b_s1_1600h_gs6736/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/9b_s1_1600h_gs6736/model.safetensors b/models/9b_s1_1600h_gs6736/model.safetensors deleted file mode 100644 index 14511ce8a0196d1bc213c9cd9aee13e81a1b102f..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b9998fba292179e90eb2d05107b6e3338ab9c4a0d351ef81fef6313d58771a01 -size 18819722392 diff --git a/models/9b_s1_1600h_gs6736/preprocessor_config.json b/models/9b_s1_1600h_gs6736/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/9b_s1_1600h_gs6736/processor_config.json b/models/9b_s1_1600h_gs6736/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/9b_s1_1600h_gs6736/tokenizer.json b/models/9b_s1_1600h_gs6736/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/9b_s1_1600h_gs6736/tokenizer_config.json b/models/9b_s1_1600h_gs6736/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/9b_s1_1600h_gs6736/video_preprocessor_config.json b/models/9b_s1_1600h_gs6736/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/9b_s1_1600h_gs6736/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file diff --git a/models/9b_s3_1600h_gs6760/chat_template.jinja b/models/9b_s3_1600h_gs6760/chat_template.jinja deleted file mode 100644 index f8d4dea148f8b55d87f4a49798a21706f212f7e9..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/chat_template.jinja +++ /dev/null @@ -1,134 +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 %} -{#- ICLR27-GameScaling CPT permissive template: - - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 - "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array - 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} -{%- 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 %} -{%- 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" %} - {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, - 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, - 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; - inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} - {%- if '' in content or '' in content %} - {{- '<|im_start|>' + message.role + '\n' + content }} - {%- else %} - {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\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' }} -{%- endif %} diff --git a/models/9b_s3_1600h_gs6760/config.json b/models/9b_s3_1600h_gs6760/config.json deleted file mode 100644 index 6d35c090be9c5bfef11d7c54527a83e15e176f41..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/config.json +++ /dev/null @@ -1,112 +0,0 @@ -{ - "architectures": [ - "Qwen3_5ForConditionalGeneration" - ], - "bos_token_id": null, - "dtype": "bfloat16", - "eos_token_id": 248046, - "image_token_id": 248056, - "model_type": "qwen3_5", - "pad_token_id": 248044, - "text_config": { - "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, - "use_cache": true, - "vocab_size": 248320 - }, - "tie_word_embeddings": false, - "transformers_version": "5.14.1", - "video_token_id": 248057, - "vision_config": { - "deepstack_visual_indexes": [], - "depth": 27, - "dtype": "bfloat16", - "hidden_act": "gelu_pytorch_tanh", - "hidden_size": 1152, - "in_channels": 3, - "initializer_range": 0.02, - "intermediate_size": 4304, - "model_type": "qwen3_5_vision", - "num_heads": 16, - "num_position_embeddings": 2304, - "out_hidden_size": 4096, - "patch_size": 16, - "spatial_merge_size": 2, - "temporal_patch_size": 2 - }, - "vision_end_token_id": 248054, - "vision_start_token_id": 248053 -} diff --git a/models/9b_s3_1600h_gs6760/generation_config.json b/models/9b_s3_1600h_gs6760/generation_config.json deleted file mode 100644 index 0e6d59a5f5463e62e7dc45c7f40ff8604275c81a..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "eos_token_id": 248046, - "output_attentions": false, - "output_hidden_states": false, - "pad_token_id": 248044, - "transformers_version": "5.14.1", - "use_cache": true -} diff --git a/models/9b_s3_1600h_gs6760/model.safetensors b/models/9b_s3_1600h_gs6760/model.safetensors deleted file mode 100644 index b8499ee0ce9fe309af7e8fce96f80e262f93aaf9..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:18afe037afcf175abd061193ab98d0d46f90224ffc28c083fe2a12ed366d7d50 -size 18819722392 diff --git a/models/9b_s3_1600h_gs6760/preprocessor_config.json b/models/9b_s3_1600h_gs6760/preprocessor_config.json deleted file mode 100644 index 2ea84a437d448ff71b08df68fdd949d5cc4ebb64..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "image_processor_type": "Qwen2VLImageProcessorFast" -} \ No newline at end of file diff --git a/models/9b_s3_1600h_gs6760/processor_config.json b/models/9b_s3_1600h_gs6760/processor_config.json deleted file mode 100644 index 33818c7f9e991ad735fd240209f4fa73e6c28c50..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/processor_config.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "image_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_processor_type": "Qwen2VLImageProcessor", - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "merge_size": 2, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "size": { - "longest_edge": 16777216, - "shortest_edge": 65536 - }, - "temporal_patch_size": 2 - }, - "processor_class": "Qwen3VLProcessor", - "video_processor": { - "do_convert_rgb": true, - "do_normalize": true, - "do_rescale": true, - "do_resize": true, - "do_sample_frames": true, - "fps": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "max_frames": 768, - "merge_size": 2, - "min_frames": 4, - "patch_size": 16, - "resample": 3, - "rescale_factor": 0.00392156862745098, - "return_metadata": false, - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "temporal_patch_size": 2, - "video_processor_type": "Qwen3VLVideoProcessor" - } -} diff --git a/models/9b_s3_1600h_gs6760/tokenizer.json b/models/9b_s3_1600h_gs6760/tokenizer.json deleted file mode 100644 index 5520bfd2dd834ce386c1312c410fa71af56db5ad..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 -size 19989325 diff --git a/models/9b_s3_1600h_gs6760/tokenizer_config.json b/models/9b_s3_1600h_gs6760/tokenizer_config.json deleted file mode 100644 index 1d134cd298be1e3be25db393d93a1cefe80e3214..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/tokenizer_config.json +++ /dev/null @@ -1,33 +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+", - "processor_class": "Qwen3VLProcessor", - "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/models/9b_s3_1600h_gs6760/video_preprocessor_config.json b/models/9b_s3_1600h_gs6760/video_preprocessor_config.json deleted file mode 100644 index 3ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe..0000000000000000000000000000000000000000 --- a/models/9b_s3_1600h_gs6760/video_preprocessor_config.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "size": { - "longest_edge": 25165824, - "shortest_edge": 4096 - }, - "patch_size": 16, - "temporal_patch_size": 2, - "merge_size": 2, - "image_mean": [ - 0.5, - 0.5, - 0.5 - ], - "image_std": [ - 0.5, - 0.5, - 0.5 - ], - "processor_class": "Qwen3VLProcessor", - "video_processor_type": "Qwen3VLVideoProcessor" -} \ No newline at end of file