Move the eight checkpoints to their own repos (THUSI-Lab/GameScaling-<size>-<mix>)
Browse filesThe Hub counts model downloads on the root config.json only, so checkpoints in models/<name>/ never registered a download. Each checkpoint now lives at the root of its own repo; this repo keeps the client, prompts and scripts.
This view is limited to 50 files because it contains too many changes. See raw diff
- README.md +38 -42
- examples/run_example.py +1 -1
- models/0p8b_s1_1600h_gs6736/chat_template.jinja +0 -134
- models/0p8b_s1_1600h_gs6736/config.json +0 -104
- models/0p8b_s1_1600h_gs6736/generation_config.json +0 -9
- models/0p8b_s1_1600h_gs6736/model.safetensors +0 -3
- models/0p8b_s1_1600h_gs6736/preprocessor_config.json +0 -21
- models/0p8b_s1_1600h_gs6736/processor_config.json +0 -60
- models/0p8b_s1_1600h_gs6736/tokenizer.json +0 -3
- models/0p8b_s1_1600h_gs6736/tokenizer_config.json +0 -33
- models/0p8b_s1_1600h_gs6736/video_preprocessor_config.json +0 -21
- models/0p8b_s3_1600h_gs6760/chat_template.jinja +0 -134
- models/0p8b_s3_1600h_gs6760/config.json +0 -104
- models/0p8b_s3_1600h_gs6760/generation_config.json +0 -9
- models/0p8b_s3_1600h_gs6760/model.safetensors +0 -3
- models/0p8b_s3_1600h_gs6760/preprocessor_config.json +0 -21
- models/0p8b_s3_1600h_gs6760/processor_config.json +0 -60
- models/0p8b_s3_1600h_gs6760/tokenizer.json +0 -3
- models/0p8b_s3_1600h_gs6760/tokenizer_config.json +0 -33
- models/0p8b_s3_1600h_gs6760/video_preprocessor_config.json +0 -21
- models/27b_s1_1600h_gs6995/chat_template.jinja +0 -134
- models/27b_s1_1600h_gs6995/config.json +0 -144
- models/27b_s1_1600h_gs6995/generation_config.json +0 -13
- models/27b_s1_1600h_gs6995/model-00001-of-00002.safetensors +0 -3
- models/27b_s1_1600h_gs6995/model-00002-of-00002.safetensors +0 -3
- models/27b_s1_1600h_gs6995/model.safetensors.index.json +0 -0
- models/27b_s1_1600h_gs6995/preprocessor_config.json +0 -21
- models/27b_s1_1600h_gs6995/processor_config.json +0 -60
- models/27b_s1_1600h_gs6995/tokenizer.json +0 -3
- models/27b_s1_1600h_gs6995/tokenizer_config.json +0 -33
- models/27b_s1_1600h_gs6995/video_preprocessor_config.json +0 -21
- models/27b_s3_1600h_gs7020/chat_template.jinja +0 -134
- models/27b_s3_1600h_gs7020/config.json +0 -144
- models/27b_s3_1600h_gs7020/generation_config.json +0 -13
- models/27b_s3_1600h_gs7020/model-00001-of-00002.safetensors +0 -3
- models/27b_s3_1600h_gs7020/model-00002-of-00002.safetensors +0 -3
- models/27b_s3_1600h_gs7020/model.safetensors.index.json +0 -0
- models/27b_s3_1600h_gs7020/preprocessor_config.json +0 -21
- models/27b_s3_1600h_gs7020/processor_config.json +0 -60
- models/27b_s3_1600h_gs7020/tokenizer.json +0 -3
- models/27b_s3_1600h_gs7020/tokenizer_config.json +0 -33
- models/27b_s3_1600h_gs7020/video_preprocessor_config.json +0 -21
- models/2b_s1_1600h_gs6736/chat_template.jinja +0 -134
- models/2b_s1_1600h_gs6736/config.json +0 -104
- models/2b_s1_1600h_gs6736/generation_config.json +0 -9
- models/2b_s1_1600h_gs6736/model.safetensors +0 -3
- models/2b_s1_1600h_gs6736/preprocessor_config.json +0 -21
- models/2b_s1_1600h_gs6736/processor_config.json +0 -60
- models/2b_s1_1600h_gs6736/tokenizer.json +0 -3
- models/2b_s1_1600h_gs6736/tokenizer_config.json +0 -33
README.md
CHANGED
|
@@ -60,50 +60,42 @@ frames and actions) and returns the next **200 ms of keyboard and mouse actions*
|
|
| 60 |
33 ms each, plus one mouse movement and scroll for the whole chunk. The model may think before it
|
| 61 |
acts.
|
| 62 |
|
| 63 |
-
This repository contains
|
| 64 |
-
|
| 65 |
-
training code. Paper results and analysis are on the [project page](https://gamescaling.github.io).
|
| 66 |
|
| 67 |
## Checkpoints
|
| 68 |
|
| 69 |
-
| Model |
|
| 70 |
-
|---|---|---:|:---:|
|
| 71 |
-
| GameScaling-0.8B-S1 |
|
| 72 |
-
| GameScaling-0.8B-S3 |
|
| 73 |
-
| GameScaling-2B-S1 |
|
| 74 |
-
| GameScaling-2B-S3 |
|
| 75 |
-
| GameScaling-9B-S1 |
|
| 76 |
-
| GameScaling-9B-S3 |
|
| 77 |
-
| GameScaling-27B-S1 |
|
| 78 |
-
| GameScaling-27B-S3 |
|
| 79 |
|
| 80 |
- **S1** is trained on Minecraft gameplay only. **S3** is a balanced mixture: 27% Minecraft, the
|
| 81 |
rest from other games. All checkpoints use 1,600 h of gameplay.
|
| 82 |
-
-
|
| 83 |
-
Qwen3.5-0.8B / 2B / 9B / 27B backbones.
|
| 84 |
|
| 85 |
## File tree
|
| 86 |
|
| 87 |
```text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
THUSI-Lab/GameScaling
|
| 89 |
-
├── models/ eight checkpoints, one folder each
|
| 90 |
-
│ ├── 0p8b_s1_1600h_gs6736/
|
| 91 |
-
│ │ ├── config.json Qwen3.5 architecture, bfloat16
|
| 92 |
-
│ │ ├── model.safetensors weights (27B: 2 shards + index)
|
| 93 |
-
│ │ ├── chat_template.jinja required, renders history turns
|
| 94 |
-
│ │ ├── tokenizer.json
|
| 95 |
-
│ │ ├── tokenizer_config.json
|
| 96 |
-
│ │ ├── generation_config.json
|
| 97 |
-
│ │ ├── preprocessor_config.json
|
| 98 |
-
│ │ ├── processor_config.json
|
| 99 |
-
│ │ └── video_preprocessor_config.json
|
| 100 |
-
│ ├── 0p8b_s3_1600h_gs6760/
|
| 101 |
-
│ ├── 2b_s1_1600h_gs6736/
|
| 102 |
-
│ ├── 2b_s3_1600h_gs6760/
|
| 103 |
-
│ ├── 9b_s1_1600h_gs6736/
|
| 104 |
-
│ ├── 9b_s3_1600h_gs6760/
|
| 105 |
-
│ ├── 27b_s1_1600h_gs6995/
|
| 106 |
-
│ └── 27b_s3_1600h_gs7020/
|
| 107 |
├── prompts/
|
| 108 |
│ ├── system_prompt_template.txt standard prompt, 3 slots (§2)
|
| 109 |
│ └── example_doom_battle1.txt complete Doom prompt (§2)
|
|
@@ -125,23 +117,27 @@ THUSI-Lab/GameScaling
|
|
| 125 |
|
| 126 |
## 1. Download and serve
|
| 127 |
|
| 128 |
-
Download
|
| 129 |
|
| 130 |
```bash
|
| 131 |
pip install -U huggingface_hub
|
| 132 |
-
huggingface-cli download THUSI-Lab/GameScaling
|
| 133 |
-
--include "models/9b_s1_1600h_gs6736/*" "gamescaling/*" "prompts/*" "scripts/*" \
|
| 134 |
-
"examples/*" "tests/*" "requirements.txt" \
|
| 135 |
-
--local-dir ./GameScaling
|
| 136 |
cd GameScaling
|
| 137 |
```
|
| 138 |
|
| 139 |
-
Serve
|
| 140 |
|
| 141 |
```bash
|
| 142 |
pip install "vllm>=0.17"
|
| 143 |
-
bash scripts/serve_vllm.sh
|
| 144 |
-
bash scripts/serve_vllm.sh
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
```
|
| 146 |
|
| 147 |
`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
|
|
| 159 |
|
| 160 |
Things to keep as shipped:
|
| 161 |
|
| 162 |
-
- **Chat template.** Use the `chat_template.jinja` in the checkpoint
|
| 163 |
default). Do not replace it with the stock Qwen template: this one renders past turns without
|
| 164 |
reasoning as `<think>\n\n</think>\n\n<|action_start|>...`, token-for-token as in training.
|
| 165 |
- **Special tokens.** Requests must set `skip_special_tokens: false`, or the server strips the
|
|
|
|
| 60 |
33 ms each, plus one mouse movement and scroll for the whole chunk. The model may think before it
|
| 61 |
acts.
|
| 62 |
|
| 63 |
+
This repository contains the inference client and the standard system-prompt template; each of the
|
| 64 |
+
eight checkpoints is its own repository (below). Together they are everything needed to serve a
|
| 65 |
+
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).
|
| 66 |
|
| 67 |
## Checkpoints
|
| 68 |
|
| 69 |
+
| Model | Training steps | Weights | GPUs (bf16) |
|
| 70 |
+
|---|---:|---:|:---:|
|
| 71 |
+
| [GameScaling-0.8B-S1](https://huggingface.co/THUSI-Lab/GameScaling-0.8B-S1) | 6,736 | 2.2 GB | 1 |
|
| 72 |
+
| [GameScaling-0.8B-S3](https://huggingface.co/THUSI-Lab/GameScaling-0.8B-S3) | 6,760 | 2.2 GB | 1 |
|
| 73 |
+
| [GameScaling-2B-S1](https://huggingface.co/THUSI-Lab/GameScaling-2B-S1) | 6,736 | 5.4 GB | 1 |
|
| 74 |
+
| [GameScaling-2B-S3](https://huggingface.co/THUSI-Lab/GameScaling-2B-S3) | 6,760 | 5.4 GB | 1 |
|
| 75 |
+
| [GameScaling-9B-S1](https://huggingface.co/THUSI-Lab/GameScaling-9B-S1) | 6,736 | 18.8 GB | 1 |
|
| 76 |
+
| [GameScaling-9B-S3](https://huggingface.co/THUSI-Lab/GameScaling-9B-S3) | 6,760 | 18.8 GB | 1 |
|
| 77 |
+
| [GameScaling-27B-S1](https://huggingface.co/THUSI-Lab/GameScaling-27B-S1) | 6,995 | 54.7 GB | 2 (tensor parallel) |
|
| 78 |
+
| [GameScaling-27B-S3](https://huggingface.co/THUSI-Lab/GameScaling-27B-S3) | 7,020 | 54.7 GB | 2 (tensor parallel) |
|
| 79 |
|
| 80 |
- **S1** is trained on Minecraft gameplay only. **S3** is a balanced mixture: 27% Minecraft, the
|
| 81 |
rest from other games. All checkpoints use 1,600 h of gameplay.
|
| 82 |
+
- Weights are bfloat16, from the Qwen3.5-0.8B / 2B / 9B / 27B backbones.
|
|
|
|
| 83 |
|
| 84 |
## File tree
|
| 85 |
|
| 86 |
```text
|
| 87 |
+
THUSI-Lab/GameScaling-<size>-<mixture> one repository per checkpoint
|
| 88 |
+
├── config.json Qwen3.5 architecture, bfloat16
|
| 89 |
+
├── model.safetensors weights (27B: 2 shards + index)
|
| 90 |
+
├── chat_template.jinja required, renders history turns
|
| 91 |
+
├── tokenizer.json
|
| 92 |
+
├── tokenizer_config.json
|
| 93 |
+
├── generation_config.json
|
| 94 |
+
├── preprocessor_config.json
|
| 95 |
+
├── processor_config.json
|
| 96 |
+
└── video_preprocessor_config.json
|
| 97 |
+
|
| 98 |
THUSI-Lab/GameScaling
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
├── prompts/
|
| 100 |
│ ├── system_prompt_template.txt standard prompt, 3 slots (§2)
|
| 101 |
│ └── example_doom_battle1.txt complete Doom prompt (§2)
|
|
|
|
| 117 |
|
| 118 |
## 1. Download and serve
|
| 119 |
|
| 120 |
+
Download the client and scripts from this repository:
|
| 121 |
|
| 122 |
```bash
|
| 123 |
pip install -U huggingface_hub
|
| 124 |
+
huggingface-cli download THUSI-Lab/GameScaling --exclude "assets/*" --local-dir ./GameScaling
|
|
|
|
|
|
|
|
|
|
| 125 |
cd GameScaling
|
| 126 |
```
|
| 127 |
|
| 128 |
+
Serve a checkpoint with vLLM (tested with 0.17.0); vLLM fetches the weights from its repository:
|
| 129 |
|
| 130 |
```bash
|
| 131 |
pip install "vllm>=0.17"
|
| 132 |
+
bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-9B-S1 8000 # 0.8B-9B fit on one GPU
|
| 133 |
+
bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-27B-S1 8000 2 # 27B: tensor parallel 2
|
| 134 |
+
```
|
| 135 |
+
|
| 136 |
+
To keep the weights in a local folder instead, download the checkpoint repository and pass its path:
|
| 137 |
+
|
| 138 |
+
```bash
|
| 139 |
+
huggingface-cli download THUSI-Lab/GameScaling-9B-S1 --local-dir ./GameScaling-9B-S1
|
| 140 |
+
bash scripts/serve_vllm.sh ./GameScaling-9B-S1 8000
|
| 141 |
```
|
| 142 |
|
| 143 |
`serve_vllm.sh CKPT [PORT] [TP]` starts vLLM with `--served-model-name gamescaling`, bfloat16,
|
|
|
|
| 155 |
|
| 156 |
Things to keep as shipped:
|
| 157 |
|
| 158 |
+
- **Chat template.** Use the `chat_template.jinja` in the checkpoint repository (vLLM loads it by
|
| 159 |
default). Do not replace it with the stock Qwen template: this one renders past turns without
|
| 160 |
reasoning as `<think>\n\n</think>\n\n<|action_start|>...`, token-for-token as in training.
|
| 161 |
- **Special tokens.** Requests must set `skip_special_tokens: false`, or the server strips the
|
examples/run_example.py
CHANGED
|
@@ -5,7 +5,7 @@ GameScaling-9B-S3, and `examples/doom_battle1_action.txt` is the reply the model
|
|
| 5 |
gave on that frame (a monster just left of the crosshair: turn left and fire).
|
| 6 |
|
| 7 |
python examples/run_example.py --offline # parse the reference reply only
|
| 8 |
-
bash scripts/serve_vllm.sh
|
| 9 |
python examples/run_example.py # prefill <think>
|
| 10 |
python examples/run_example.py --no-reasoning # prefill <think>\\n\\n</think>
|
| 11 |
|
|
|
|
| 5 |
gave on that frame (a monster just left of the crosshair: turn left and fire).
|
| 6 |
|
| 7 |
python examples/run_example.py --offline # parse the reference reply only
|
| 8 |
+
bash scripts/serve_vllm.sh THUSI-Lab/GameScaling-9B-S3 8000
|
| 9 |
python examples/run_example.py # prefill <think>
|
| 10 |
python examples/run_example.py --no-reasoning # prefill <think>\\n\\n</think>
|
| 11 |
|
models/0p8b_s1_1600h_gs6736/chat_template.jinja
DELETED
|
@@ -1,134 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{#- ICLR27-GameScaling CPT permissive template:
|
| 43 |
-
- 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)。
|
| 44 |
-
- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
|
| 45 |
-
"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
|
| 46 |
-
- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
|
| 47 |
-
传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
|
| 48 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 49 |
-
{{- '<|im_start|>system\n' }}
|
| 50 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 51 |
-
{%- for tool in tools %}
|
| 52 |
-
{{- "\n" }}
|
| 53 |
-
{{- tool | tojson }}
|
| 54 |
-
{%- endfor %}
|
| 55 |
-
{{- "\n</tools>" }}
|
| 56 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
|
| 57 |
-
{%- if messages[0].role == 'system' %}
|
| 58 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 59 |
-
{%- if content %}
|
| 60 |
-
{{- '\n\n' + content }}
|
| 61 |
-
{%- endif %}
|
| 62 |
-
{%- endif %}
|
| 63 |
-
{{- '<|im_end|>\n' }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- if messages[0].role == 'system' %}
|
| 66 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 67 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endif %}
|
| 70 |
-
{%- for message in messages %}
|
| 71 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 72 |
-
{%- if message.role == "system" %}
|
| 73 |
-
{%- if not loop.first %}
|
| 74 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- elif message.role == "user" %}
|
| 77 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 78 |
-
{%- elif message.role == "assistant" %}
|
| 79 |
-
{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
|
| 80 |
-
- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
|
| 81 |
-
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)。
|
| 82 |
-
- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
|
| 83 |
-
训练无 think GT 只保结构, ���模型仍会输出 <think>...</think>, 不破坏原生思考通路;
|
| 84 |
-
inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
|
| 85 |
-
{%- if '<think>' in content or '</think>' in content %}
|
| 86 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 87 |
-
{%- else %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 91 |
-
{%- for tool_call in message.tool_calls %}
|
| 92 |
-
{%- if tool_call.function is defined %}
|
| 93 |
-
{%- set tool_call = tool_call.function %}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{%- if loop.first %}
|
| 96 |
-
{%- if content|trim %}
|
| 97 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 100 |
-
{%- endif %}
|
| 101 |
-
{%- else %}
|
| 102 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 103 |
-
{%- endif %}
|
| 104 |
-
{%- if tool_call.arguments is defined %}
|
| 105 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 106 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 107 |
-
{%- 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 %}
|
| 108 |
-
{{- args_value }}
|
| 109 |
-
{{- '\n</parameter>\n' }}
|
| 110 |
-
{%- endfor %}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{{- '</function>\n</tool_call>' }}
|
| 113 |
-
{%- endfor %}
|
| 114 |
-
{%- endif %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- elif message.role == "tool" %}
|
| 117 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 118 |
-
{{- '<|im_start|>user' }}
|
| 119 |
-
{%- endif %}
|
| 120 |
-
{{- '\n<tool_response>\n' }}
|
| 121 |
-
{{- content }}
|
| 122 |
-
{{- '\n</tool_response>' }}
|
| 123 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 124 |
-
{{- '<|im_end|>\n' }}
|
| 125 |
-
{%- elif loop.last %}
|
| 126 |
-
{{- '<|im_end|>\n' }}
|
| 127 |
-
{%- endif %}
|
| 128 |
-
{%- else %}
|
| 129 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 130 |
-
{%- endif %}
|
| 131 |
-
{%- endfor %}
|
| 132 |
-
{%- if add_generation_prompt %}
|
| 133 |
-
{{- '<|im_start|>assistant\n' }}
|
| 134 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "bfloat16",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 1024,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 3584,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention"
|
| 49 |
-
],
|
| 50 |
-
"linear_conv_kernel_dim": 4,
|
| 51 |
-
"linear_key_head_dim": 128,
|
| 52 |
-
"linear_num_key_heads": 16,
|
| 53 |
-
"linear_num_value_heads": 16,
|
| 54 |
-
"linear_value_head_dim": 128,
|
| 55 |
-
"mamba_ssm_dtype": "float32",
|
| 56 |
-
"max_position_embeddings": 262144,
|
| 57 |
-
"mlp_only_layers": [],
|
| 58 |
-
"model_type": "qwen3_5_text",
|
| 59 |
-
"mtp_num_hidden_layers": 1,
|
| 60 |
-
"mtp_use_dedicated_embeddings": false,
|
| 61 |
-
"num_attention_heads": 8,
|
| 62 |
-
"num_hidden_layers": 24,
|
| 63 |
-
"num_key_value_heads": 2,
|
| 64 |
-
"pad_token_id": null,
|
| 65 |
-
"partial_rotary_factor": 0.25,
|
| 66 |
-
"rms_norm_eps": 1e-06,
|
| 67 |
-
"rope_parameters": {
|
| 68 |
-
"mrope_interleaved": true,
|
| 69 |
-
"mrope_section": [
|
| 70 |
-
11,
|
| 71 |
-
11,
|
| 72 |
-
10
|
| 73 |
-
],
|
| 74 |
-
"partial_rotary_factor": 0.25,
|
| 75 |
-
"rope_theta": 10000000,
|
| 76 |
-
"rope_type": "default"
|
| 77 |
-
},
|
| 78 |
-
"tie_word_embeddings": true,
|
| 79 |
-
"use_cache": true,
|
| 80 |
-
"vocab_size": 248320
|
| 81 |
-
},
|
| 82 |
-
"tie_word_embeddings": true,
|
| 83 |
-
"transformers_version": "5.14.1",
|
| 84 |
-
"video_token_id": 248057,
|
| 85 |
-
"vision_config": {
|
| 86 |
-
"deepstack_visual_indexes": [],
|
| 87 |
-
"depth": 12,
|
| 88 |
-
"dtype": "bfloat16",
|
| 89 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 90 |
-
"hidden_size": 768,
|
| 91 |
-
"in_channels": 3,
|
| 92 |
-
"initializer_range": 0.02,
|
| 93 |
-
"intermediate_size": 3072,
|
| 94 |
-
"model_type": "qwen3_5_vision",
|
| 95 |
-
"num_heads": 12,
|
| 96 |
-
"num_position_embeddings": 2304,
|
| 97 |
-
"out_hidden_size": 1024,
|
| 98 |
-
"patch_size": 16,
|
| 99 |
-
"spatial_merge_size": 2,
|
| 100 |
-
"temporal_patch_size": 2
|
| 101 |
-
},
|
| 102 |
-
"vision_end_token_id": 248054,
|
| 103 |
-
"vision_start_token_id": 248053
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 248046,
|
| 4 |
-
"output_attentions": false,
|
| 5 |
-
"output_hidden_states": false,
|
| 6 |
-
"pad_token_id": 248044,
|
| 7 |
-
"transformers_version": "5.14.1",
|
| 8 |
-
"use_cache": true
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b2986b2a0deec5dd76c8c72946e7f65daf4b695c76c9b01c4f5fff9433dbeb67
|
| 3 |
-
size 2214590296
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 16777216,
|
| 4 |
-
"shortest_edge": 65536
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
-
size 19989325
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
-
"backend": "tokenizers",
|
| 7 |
-
"bos_token": null,
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<|im_end|>",
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local": true,
|
| 13 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"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+",
|
| 26 |
-
"processor_class": "Qwen3VLProcessor",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null,
|
| 30 |
-
"video_token": "<|video_pad|>",
|
| 31 |
-
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s1_1600h_gs6736/video_preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 25165824,
|
| 4 |
-
"shortest_edge": 4096
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/chat_template.jinja
DELETED
|
@@ -1,134 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{#- ICLR27-GameScaling CPT permissive template:
|
| 43 |
-
- 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)。
|
| 44 |
-
- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
|
| 45 |
-
"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
|
| 46 |
-
- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
|
| 47 |
-
传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
|
| 48 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 49 |
-
{{- '<|im_start|>system\n' }}
|
| 50 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 51 |
-
{%- for tool in tools %}
|
| 52 |
-
{{- "\n" }}
|
| 53 |
-
{{- tool | tojson }}
|
| 54 |
-
{%- endfor %}
|
| 55 |
-
{{- "\n</tools>" }}
|
| 56 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
|
| 57 |
-
{%- if messages[0].role == 'system' %}
|
| 58 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 59 |
-
{%- if content %}
|
| 60 |
-
{{- '\n\n' + content }}
|
| 61 |
-
{%- endif %}
|
| 62 |
-
{%- endif %}
|
| 63 |
-
{{- '<|im_end|>\n' }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- if messages[0].role == 'system' %}
|
| 66 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 67 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endif %}
|
| 70 |
-
{%- for message in messages %}
|
| 71 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 72 |
-
{%- if message.role == "system" %}
|
| 73 |
-
{%- if not loop.first %}
|
| 74 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- elif message.role == "user" %}
|
| 77 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 78 |
-
{%- elif message.role == "assistant" %}
|
| 79 |
-
{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
|
| 80 |
-
- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
|
| 81 |
-
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)。
|
| 82 |
-
- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
|
| 83 |
-
训练无 think GT 只保结构, ���模型仍会输出 <think>...</think>, 不破坏原生思考通路;
|
| 84 |
-
inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
|
| 85 |
-
{%- if '<think>' in content or '</think>' in content %}
|
| 86 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 87 |
-
{%- else %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 91 |
-
{%- for tool_call in message.tool_calls %}
|
| 92 |
-
{%- if tool_call.function is defined %}
|
| 93 |
-
{%- set tool_call = tool_call.function %}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{%- if loop.first %}
|
| 96 |
-
{%- if content|trim %}
|
| 97 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 100 |
-
{%- endif %}
|
| 101 |
-
{%- else %}
|
| 102 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 103 |
-
{%- endif %}
|
| 104 |
-
{%- if tool_call.arguments is defined %}
|
| 105 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 106 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 107 |
-
{%- 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 %}
|
| 108 |
-
{{- args_value }}
|
| 109 |
-
{{- '\n</parameter>\n' }}
|
| 110 |
-
{%- endfor %}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{{- '</function>\n</tool_call>' }}
|
| 113 |
-
{%- endfor %}
|
| 114 |
-
{%- endif %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- elif message.role == "tool" %}
|
| 117 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 118 |
-
{{- '<|im_start|>user' }}
|
| 119 |
-
{%- endif %}
|
| 120 |
-
{{- '\n<tool_response>\n' }}
|
| 121 |
-
{{- content }}
|
| 122 |
-
{{- '\n</tool_response>' }}
|
| 123 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 124 |
-
{{- '<|im_end|>\n' }}
|
| 125 |
-
{%- elif loop.last %}
|
| 126 |
-
{{- '<|im_end|>\n' }}
|
| 127 |
-
{%- endif %}
|
| 128 |
-
{%- else %}
|
| 129 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 130 |
-
{%- endif %}
|
| 131 |
-
{%- endfor %}
|
| 132 |
-
{%- if add_generation_prompt %}
|
| 133 |
-
{{- '<|im_start|>assistant\n' }}
|
| 134 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "bfloat16",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 1024,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 3584,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention"
|
| 49 |
-
],
|
| 50 |
-
"linear_conv_kernel_dim": 4,
|
| 51 |
-
"linear_key_head_dim": 128,
|
| 52 |
-
"linear_num_key_heads": 16,
|
| 53 |
-
"linear_num_value_heads": 16,
|
| 54 |
-
"linear_value_head_dim": 128,
|
| 55 |
-
"mamba_ssm_dtype": "float32",
|
| 56 |
-
"max_position_embeddings": 262144,
|
| 57 |
-
"mlp_only_layers": [],
|
| 58 |
-
"model_type": "qwen3_5_text",
|
| 59 |
-
"mtp_num_hidden_layers": 1,
|
| 60 |
-
"mtp_use_dedicated_embeddings": false,
|
| 61 |
-
"num_attention_heads": 8,
|
| 62 |
-
"num_hidden_layers": 24,
|
| 63 |
-
"num_key_value_heads": 2,
|
| 64 |
-
"pad_token_id": null,
|
| 65 |
-
"partial_rotary_factor": 0.25,
|
| 66 |
-
"rms_norm_eps": 1e-06,
|
| 67 |
-
"rope_parameters": {
|
| 68 |
-
"mrope_interleaved": true,
|
| 69 |
-
"mrope_section": [
|
| 70 |
-
11,
|
| 71 |
-
11,
|
| 72 |
-
10
|
| 73 |
-
],
|
| 74 |
-
"partial_rotary_factor": 0.25,
|
| 75 |
-
"rope_theta": 10000000,
|
| 76 |
-
"rope_type": "default"
|
| 77 |
-
},
|
| 78 |
-
"tie_word_embeddings": true,
|
| 79 |
-
"use_cache": true,
|
| 80 |
-
"vocab_size": 248320
|
| 81 |
-
},
|
| 82 |
-
"tie_word_embeddings": true,
|
| 83 |
-
"transformers_version": "5.14.1",
|
| 84 |
-
"video_token_id": 248057,
|
| 85 |
-
"vision_config": {
|
| 86 |
-
"deepstack_visual_indexes": [],
|
| 87 |
-
"depth": 12,
|
| 88 |
-
"dtype": "bfloat16",
|
| 89 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 90 |
-
"hidden_size": 768,
|
| 91 |
-
"in_channels": 3,
|
| 92 |
-
"initializer_range": 0.02,
|
| 93 |
-
"intermediate_size": 3072,
|
| 94 |
-
"model_type": "qwen3_5_vision",
|
| 95 |
-
"num_heads": 12,
|
| 96 |
-
"num_position_embeddings": 2304,
|
| 97 |
-
"out_hidden_size": 1024,
|
| 98 |
-
"patch_size": 16,
|
| 99 |
-
"spatial_merge_size": 2,
|
| 100 |
-
"temporal_patch_size": 2
|
| 101 |
-
},
|
| 102 |
-
"vision_end_token_id": 248054,
|
| 103 |
-
"vision_start_token_id": 248053
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 248046,
|
| 4 |
-
"output_attentions": false,
|
| 5 |
-
"output_hidden_states": false,
|
| 6 |
-
"pad_token_id": 248044,
|
| 7 |
-
"transformers_version": "5.14.1",
|
| 8 |
-
"use_cache": true
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d553c0796833691e32277a937db649eaac39bae9a0028a63c964c12a261c2dfa
|
| 3 |
-
size 2214590296
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 16777216,
|
| 4 |
-
"shortest_edge": 65536
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
-
size 19989325
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
-
"backend": "tokenizers",
|
| 7 |
-
"bos_token": null,
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<|im_end|>",
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local": true,
|
| 13 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"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+",
|
| 26 |
-
"processor_class": "Qwen3VLProcessor",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null,
|
| 30 |
-
"video_token": "<|video_pad|>",
|
| 31 |
-
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/0p8b_s3_1600h_gs6760/video_preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 25165824,
|
| 4 |
-
"shortest_edge": 4096
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/chat_template.jinja
DELETED
|
@@ -1,134 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{#- ICLR27-GameScaling CPT permissive template:
|
| 43 |
-
- 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)。
|
| 44 |
-
- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
|
| 45 |
-
"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
|
| 46 |
-
- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
|
| 47 |
-
传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
|
| 48 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 49 |
-
{{- '<|im_start|>system\n' }}
|
| 50 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 51 |
-
{%- for tool in tools %}
|
| 52 |
-
{{- "\n" }}
|
| 53 |
-
{{- tool | tojson }}
|
| 54 |
-
{%- endfor %}
|
| 55 |
-
{{- "\n</tools>" }}
|
| 56 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
|
| 57 |
-
{%- if messages[0].role == 'system' %}
|
| 58 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 59 |
-
{%- if content %}
|
| 60 |
-
{{- '\n\n' + content }}
|
| 61 |
-
{%- endif %}
|
| 62 |
-
{%- endif %}
|
| 63 |
-
{{- '<|im_end|>\n' }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- if messages[0].role == 'system' %}
|
| 66 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 67 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endif %}
|
| 70 |
-
{%- for message in messages %}
|
| 71 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 72 |
-
{%- if message.role == "system" %}
|
| 73 |
-
{%- if not loop.first %}
|
| 74 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- elif message.role == "user" %}
|
| 77 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 78 |
-
{%- elif message.role == "assistant" %}
|
| 79 |
-
{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
|
| 80 |
-
- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
|
| 81 |
-
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)。
|
| 82 |
-
- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
|
| 83 |
-
训练无 think GT 只保结构, ���模型仍会输出 <think>...</think>, 不破坏原生思考通路;
|
| 84 |
-
inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
|
| 85 |
-
{%- if '<think>' in content or '</think>' in content %}
|
| 86 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 87 |
-
{%- else %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 91 |
-
{%- for tool_call in message.tool_calls %}
|
| 92 |
-
{%- if tool_call.function is defined %}
|
| 93 |
-
{%- set tool_call = tool_call.function %}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{%- if loop.first %}
|
| 96 |
-
{%- if content|trim %}
|
| 97 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 100 |
-
{%- endif %}
|
| 101 |
-
{%- else %}
|
| 102 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 103 |
-
{%- endif %}
|
| 104 |
-
{%- if tool_call.arguments is defined %}
|
| 105 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 106 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 107 |
-
{%- 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 %}
|
| 108 |
-
{{- args_value }}
|
| 109 |
-
{{- '\n</parameter>\n' }}
|
| 110 |
-
{%- endfor %}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{{- '</function>\n</tool_call>' }}
|
| 113 |
-
{%- endfor %}
|
| 114 |
-
{%- endif %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- elif message.role == "tool" %}
|
| 117 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 118 |
-
{{- '<|im_start|>user' }}
|
| 119 |
-
{%- endif %}
|
| 120 |
-
{{- '\n<tool_response>\n' }}
|
| 121 |
-
{{- content }}
|
| 122 |
-
{{- '\n</tool_response>' }}
|
| 123 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 124 |
-
{{- '<|im_end|>\n' }}
|
| 125 |
-
{%- elif loop.last %}
|
| 126 |
-
{{- '<|im_end|>\n' }}
|
| 127 |
-
{%- endif %}
|
| 128 |
-
{%- else %}
|
| 129 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 130 |
-
{%- endif %}
|
| 131 |
-
{%- endfor %}
|
| 132 |
-
{%- if add_generation_prompt %}
|
| 133 |
-
{{- '<|im_start|>assistant\n' }}
|
| 134 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "bfloat16",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 5120,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 17408,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"linear_attention",
|
| 50 |
-
"linear_attention",
|
| 51 |
-
"linear_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"linear_attention",
|
| 54 |
-
"linear_attention",
|
| 55 |
-
"linear_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"linear_attention",
|
| 58 |
-
"linear_attention",
|
| 59 |
-
"linear_attention",
|
| 60 |
-
"full_attention",
|
| 61 |
-
"linear_attention",
|
| 62 |
-
"linear_attention",
|
| 63 |
-
"linear_attention",
|
| 64 |
-
"full_attention",
|
| 65 |
-
"linear_attention",
|
| 66 |
-
"linear_attention",
|
| 67 |
-
"linear_attention",
|
| 68 |
-
"full_attention",
|
| 69 |
-
"linear_attention",
|
| 70 |
-
"linear_attention",
|
| 71 |
-
"linear_attention",
|
| 72 |
-
"full_attention",
|
| 73 |
-
"linear_attention",
|
| 74 |
-
"linear_attention",
|
| 75 |
-
"linear_attention",
|
| 76 |
-
"full_attention",
|
| 77 |
-
"linear_attention",
|
| 78 |
-
"linear_attention",
|
| 79 |
-
"linear_attention",
|
| 80 |
-
"full_attention",
|
| 81 |
-
"linear_attention",
|
| 82 |
-
"linear_attention",
|
| 83 |
-
"linear_attention",
|
| 84 |
-
"full_attention",
|
| 85 |
-
"linear_attention",
|
| 86 |
-
"linear_attention",
|
| 87 |
-
"linear_attention",
|
| 88 |
-
"full_attention"
|
| 89 |
-
],
|
| 90 |
-
"linear_conv_kernel_dim": 4,
|
| 91 |
-
"linear_key_head_dim": 128,
|
| 92 |
-
"linear_num_key_heads": 16,
|
| 93 |
-
"linear_num_value_heads": 48,
|
| 94 |
-
"linear_value_head_dim": 128,
|
| 95 |
-
"mamba_ssm_dtype": "float32",
|
| 96 |
-
"max_position_embeddings": 262144,
|
| 97 |
-
"mlp_only_layers": [],
|
| 98 |
-
"model_type": "qwen3_5_text",
|
| 99 |
-
"mtp_num_hidden_layers": 1,
|
| 100 |
-
"mtp_use_dedicated_embeddings": false,
|
| 101 |
-
"num_attention_heads": 24,
|
| 102 |
-
"num_hidden_layers": 64,
|
| 103 |
-
"num_key_value_heads": 4,
|
| 104 |
-
"pad_token_id": null,
|
| 105 |
-
"partial_rotary_factor": 0.25,
|
| 106 |
-
"rms_norm_eps": 1e-06,
|
| 107 |
-
"rope_parameters": {
|
| 108 |
-
"mrope_interleaved": true,
|
| 109 |
-
"mrope_section": [
|
| 110 |
-
11,
|
| 111 |
-
11,
|
| 112 |
-
10
|
| 113 |
-
],
|
| 114 |
-
"partial_rotary_factor": 0.25,
|
| 115 |
-
"rope_theta": 10000000,
|
| 116 |
-
"rope_type": "default"
|
| 117 |
-
},
|
| 118 |
-
"tie_word_embeddings": false,
|
| 119 |
-
"use_cache": true,
|
| 120 |
-
"vocab_size": 248320
|
| 121 |
-
},
|
| 122 |
-
"tie_word_embeddings": false,
|
| 123 |
-
"transformers_version": "5.14.1",
|
| 124 |
-
"video_token_id": 248057,
|
| 125 |
-
"vision_config": {
|
| 126 |
-
"deepstack_visual_indexes": [],
|
| 127 |
-
"depth": 27,
|
| 128 |
-
"dtype": "bfloat16",
|
| 129 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 130 |
-
"hidden_size": 1152,
|
| 131 |
-
"in_channels": 3,
|
| 132 |
-
"initializer_range": 0.02,
|
| 133 |
-
"intermediate_size": 4304,
|
| 134 |
-
"model_type": "qwen3_5_vision",
|
| 135 |
-
"num_heads": 16,
|
| 136 |
-
"num_position_embeddings": 2304,
|
| 137 |
-
"out_hidden_size": 5120,
|
| 138 |
-
"patch_size": 16,
|
| 139 |
-
"spatial_merge_size": 2,
|
| 140 |
-
"temporal_patch_size": 2
|
| 141 |
-
},
|
| 142 |
-
"vision_end_token_id": 248054,
|
| 143 |
-
"vision_start_token_id": 248053
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 248044,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
248046,
|
| 6 |
-
248044
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 248044,
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_k": 20,
|
| 11 |
-
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "5.14.1"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:170b268eccf87f9c19d81bae8b78672aba2d996a159192dc7c83ac6a2a5c6d0d
|
| 3 |
-
size 49935066216
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:753c79c6f45331d98f0be24b72df6defbfd8daa5d583b3edf203fc417b83a222
|
| 3 |
-
size 4778542568
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/model.safetensors.index.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/27b_s1_1600h_gs6995/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 16777216,
|
| 4 |
-
"shortest_edge": 65536
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
-
size 19989325
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
-
"backend": "tokenizers",
|
| 7 |
-
"bos_token": null,
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<|im_end|>",
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local": true,
|
| 13 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"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+",
|
| 26 |
-
"processor_class": "Qwen3VLProcessor",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null,
|
| 30 |
-
"video_token": "<|video_pad|>",
|
| 31 |
-
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s1_1600h_gs6995/video_preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 25165824,
|
| 4 |
-
"shortest_edge": 4096
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/chat_template.jinja
DELETED
|
@@ -1,134 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{#- ICLR27-GameScaling CPT permissive template:
|
| 43 |
-
- 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)。
|
| 44 |
-
- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
|
| 45 |
-
"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
|
| 46 |
-
- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
|
| 47 |
-
传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
|
| 48 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 49 |
-
{{- '<|im_start|>system\n' }}
|
| 50 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 51 |
-
{%- for tool in tools %}
|
| 52 |
-
{{- "\n" }}
|
| 53 |
-
{{- tool | tojson }}
|
| 54 |
-
{%- endfor %}
|
| 55 |
-
{{- "\n</tools>" }}
|
| 56 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
|
| 57 |
-
{%- if messages[0].role == 'system' %}
|
| 58 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 59 |
-
{%- if content %}
|
| 60 |
-
{{- '\n\n' + content }}
|
| 61 |
-
{%- endif %}
|
| 62 |
-
{%- endif %}
|
| 63 |
-
{{- '<|im_end|>\n' }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- if messages[0].role == 'system' %}
|
| 66 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 67 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endif %}
|
| 70 |
-
{%- for message in messages %}
|
| 71 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 72 |
-
{%- if message.role == "system" %}
|
| 73 |
-
{%- if not loop.first %}
|
| 74 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- elif message.role == "user" %}
|
| 77 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 78 |
-
{%- elif message.role == "assistant" %}
|
| 79 |
-
{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
|
| 80 |
-
- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
|
| 81 |
-
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)。
|
| 82 |
-
- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
|
| 83 |
-
训练无 think GT 只保结构, ���模型仍会输出 <think>...</think>, 不破坏原生思考通路;
|
| 84 |
-
inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
|
| 85 |
-
{%- if '<think>' in content or '</think>' in content %}
|
| 86 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 87 |
-
{%- else %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 91 |
-
{%- for tool_call in message.tool_calls %}
|
| 92 |
-
{%- if tool_call.function is defined %}
|
| 93 |
-
{%- set tool_call = tool_call.function %}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{%- if loop.first %}
|
| 96 |
-
{%- if content|trim %}
|
| 97 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 100 |
-
{%- endif %}
|
| 101 |
-
{%- else %}
|
| 102 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 103 |
-
{%- endif %}
|
| 104 |
-
{%- if tool_call.arguments is defined %}
|
| 105 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 106 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 107 |
-
{%- 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 %}
|
| 108 |
-
{{- args_value }}
|
| 109 |
-
{{- '\n</parameter>\n' }}
|
| 110 |
-
{%- endfor %}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{{- '</function>\n</tool_call>' }}
|
| 113 |
-
{%- endfor %}
|
| 114 |
-
{%- endif %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- elif message.role == "tool" %}
|
| 117 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 118 |
-
{{- '<|im_start|>user' }}
|
| 119 |
-
{%- endif %}
|
| 120 |
-
{{- '\n<tool_response>\n' }}
|
| 121 |
-
{{- content }}
|
| 122 |
-
{{- '\n</tool_response>' }}
|
| 123 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 124 |
-
{{- '<|im_end|>\n' }}
|
| 125 |
-
{%- elif loop.last %}
|
| 126 |
-
{{- '<|im_end|>\n' }}
|
| 127 |
-
{%- endif %}
|
| 128 |
-
{%- else %}
|
| 129 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 130 |
-
{%- endif %}
|
| 131 |
-
{%- endfor %}
|
| 132 |
-
{%- if add_generation_prompt %}
|
| 133 |
-
{{- '<|im_start|>assistant\n' }}
|
| 134 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "bfloat16",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 5120,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 17408,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"linear_attention",
|
| 50 |
-
"linear_attention",
|
| 51 |
-
"linear_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"linear_attention",
|
| 54 |
-
"linear_attention",
|
| 55 |
-
"linear_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"linear_attention",
|
| 58 |
-
"linear_attention",
|
| 59 |
-
"linear_attention",
|
| 60 |
-
"full_attention",
|
| 61 |
-
"linear_attention",
|
| 62 |
-
"linear_attention",
|
| 63 |
-
"linear_attention",
|
| 64 |
-
"full_attention",
|
| 65 |
-
"linear_attention",
|
| 66 |
-
"linear_attention",
|
| 67 |
-
"linear_attention",
|
| 68 |
-
"full_attention",
|
| 69 |
-
"linear_attention",
|
| 70 |
-
"linear_attention",
|
| 71 |
-
"linear_attention",
|
| 72 |
-
"full_attention",
|
| 73 |
-
"linear_attention",
|
| 74 |
-
"linear_attention",
|
| 75 |
-
"linear_attention",
|
| 76 |
-
"full_attention",
|
| 77 |
-
"linear_attention",
|
| 78 |
-
"linear_attention",
|
| 79 |
-
"linear_attention",
|
| 80 |
-
"full_attention",
|
| 81 |
-
"linear_attention",
|
| 82 |
-
"linear_attention",
|
| 83 |
-
"linear_attention",
|
| 84 |
-
"full_attention",
|
| 85 |
-
"linear_attention",
|
| 86 |
-
"linear_attention",
|
| 87 |
-
"linear_attention",
|
| 88 |
-
"full_attention"
|
| 89 |
-
],
|
| 90 |
-
"linear_conv_kernel_dim": 4,
|
| 91 |
-
"linear_key_head_dim": 128,
|
| 92 |
-
"linear_num_key_heads": 16,
|
| 93 |
-
"linear_num_value_heads": 48,
|
| 94 |
-
"linear_value_head_dim": 128,
|
| 95 |
-
"mamba_ssm_dtype": "float32",
|
| 96 |
-
"max_position_embeddings": 262144,
|
| 97 |
-
"mlp_only_layers": [],
|
| 98 |
-
"model_type": "qwen3_5_text",
|
| 99 |
-
"mtp_num_hidden_layers": 1,
|
| 100 |
-
"mtp_use_dedicated_embeddings": false,
|
| 101 |
-
"num_attention_heads": 24,
|
| 102 |
-
"num_hidden_layers": 64,
|
| 103 |
-
"num_key_value_heads": 4,
|
| 104 |
-
"pad_token_id": null,
|
| 105 |
-
"partial_rotary_factor": 0.25,
|
| 106 |
-
"rms_norm_eps": 1e-06,
|
| 107 |
-
"rope_parameters": {
|
| 108 |
-
"mrope_interleaved": true,
|
| 109 |
-
"mrope_section": [
|
| 110 |
-
11,
|
| 111 |
-
11,
|
| 112 |
-
10
|
| 113 |
-
],
|
| 114 |
-
"partial_rotary_factor": 0.25,
|
| 115 |
-
"rope_theta": 10000000,
|
| 116 |
-
"rope_type": "default"
|
| 117 |
-
},
|
| 118 |
-
"tie_word_embeddings": false,
|
| 119 |
-
"use_cache": true,
|
| 120 |
-
"vocab_size": 248320
|
| 121 |
-
},
|
| 122 |
-
"tie_word_embeddings": false,
|
| 123 |
-
"transformers_version": "5.14.1",
|
| 124 |
-
"video_token_id": 248057,
|
| 125 |
-
"vision_config": {
|
| 126 |
-
"deepstack_visual_indexes": [],
|
| 127 |
-
"depth": 27,
|
| 128 |
-
"dtype": "bfloat16",
|
| 129 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 130 |
-
"hidden_size": 1152,
|
| 131 |
-
"in_channels": 3,
|
| 132 |
-
"initializer_range": 0.02,
|
| 133 |
-
"intermediate_size": 4304,
|
| 134 |
-
"model_type": "qwen3_5_vision",
|
| 135 |
-
"num_heads": 16,
|
| 136 |
-
"num_position_embeddings": 2304,
|
| 137 |
-
"out_hidden_size": 5120,
|
| 138 |
-
"patch_size": 16,
|
| 139 |
-
"spatial_merge_size": 2,
|
| 140 |
-
"temporal_patch_size": 2
|
| 141 |
-
},
|
| 142 |
-
"vision_end_token_id": 248054,
|
| 143 |
-
"vision_start_token_id": 248053
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 248044,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
248046,
|
| 6 |
-
248044
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 248044,
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_k": 20,
|
| 11 |
-
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "5.14.1"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9138f232014c26a45fd8f8a519180eb9a986fdfc4ac2c8649635552dfc352f6e
|
| 3 |
-
size 29848868595
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f008fc3ec5f8a24ff6b2b9607030858a7ce24cec84dea98f5675e562e285187a
|
| 3 |
-
size 24864740005
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/model.safetensors.index.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/27b_s3_1600h_gs7020/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 16777216,
|
| 4 |
-
"shortest_edge": 65536
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
-
size 19989325
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
-
"backend": "tokenizers",
|
| 7 |
-
"bos_token": null,
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<|im_end|>",
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local": true,
|
| 13 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"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+",
|
| 26 |
-
"processor_class": "Qwen3VLProcessor",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null,
|
| 30 |
-
"video_token": "<|video_pad|>",
|
| 31 |
-
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/27b_s3_1600h_gs7020/video_preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 25165824,
|
| 4 |
-
"shortest_edge": 4096
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/chat_template.jinja
DELETED
|
@@ -1,134 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{#- ICLR27-GameScaling CPT permissive template:
|
| 43 |
-
- 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)。
|
| 44 |
-
- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
|
| 45 |
-
"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
|
| 46 |
-
- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
|
| 47 |
-
传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
|
| 48 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 49 |
-
{{- '<|im_start|>system\n' }}
|
| 50 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 51 |
-
{%- for tool in tools %}
|
| 52 |
-
{{- "\n" }}
|
| 53 |
-
{{- tool | tojson }}
|
| 54 |
-
{%- endfor %}
|
| 55 |
-
{{- "\n</tools>" }}
|
| 56 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
|
| 57 |
-
{%- if messages[0].role == 'system' %}
|
| 58 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 59 |
-
{%- if content %}
|
| 60 |
-
{{- '\n\n' + content }}
|
| 61 |
-
{%- endif %}
|
| 62 |
-
{%- endif %}
|
| 63 |
-
{{- '<|im_end|>\n' }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- if messages[0].role == 'system' %}
|
| 66 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 67 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endif %}
|
| 70 |
-
{%- for message in messages %}
|
| 71 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 72 |
-
{%- if message.role == "system" %}
|
| 73 |
-
{%- if not loop.first %}
|
| 74 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- elif message.role == "user" %}
|
| 77 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 78 |
-
{%- elif message.role == "assistant" %}
|
| 79 |
-
{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
|
| 80 |
-
- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
|
| 81 |
-
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)。
|
| 82 |
-
- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
|
| 83 |
-
训练无 think GT 只保结构, ���模型仍会输出 <think>...</think>, 不破坏原生思考通路;
|
| 84 |
-
inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
|
| 85 |
-
{%- if '<think>' in content or '</think>' in content %}
|
| 86 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 87 |
-
{%- else %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 91 |
-
{%- for tool_call in message.tool_calls %}
|
| 92 |
-
{%- if tool_call.function is defined %}
|
| 93 |
-
{%- set tool_call = tool_call.function %}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{%- if loop.first %}
|
| 96 |
-
{%- if content|trim %}
|
| 97 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 100 |
-
{%- endif %}
|
| 101 |
-
{%- else %}
|
| 102 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 103 |
-
{%- endif %}
|
| 104 |
-
{%- if tool_call.arguments is defined %}
|
| 105 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 106 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 107 |
-
{%- 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 %}
|
| 108 |
-
{{- args_value }}
|
| 109 |
-
{{- '\n</parameter>\n' }}
|
| 110 |
-
{%- endfor %}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{{- '</function>\n</tool_call>' }}
|
| 113 |
-
{%- endfor %}
|
| 114 |
-
{%- endif %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- elif message.role == "tool" %}
|
| 117 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 118 |
-
{{- '<|im_start|>user' }}
|
| 119 |
-
{%- endif %}
|
| 120 |
-
{{- '\n<tool_response>\n' }}
|
| 121 |
-
{{- content }}
|
| 122 |
-
{{- '\n</tool_response>' }}
|
| 123 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 124 |
-
{{- '<|im_end|>\n' }}
|
| 125 |
-
{%- elif loop.last %}
|
| 126 |
-
{{- '<|im_end|>\n' }}
|
| 127 |
-
{%- endif %}
|
| 128 |
-
{%- else %}
|
| 129 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 130 |
-
{%- endif %}
|
| 131 |
-
{%- endfor %}
|
| 132 |
-
{%- if add_generation_prompt %}
|
| 133 |
-
{{- '<|im_start|>assistant\n' }}
|
| 134 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "bfloat16",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 2048,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 6144,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention"
|
| 49 |
-
],
|
| 50 |
-
"linear_conv_kernel_dim": 4,
|
| 51 |
-
"linear_key_head_dim": 128,
|
| 52 |
-
"linear_num_key_heads": 16,
|
| 53 |
-
"linear_num_value_heads": 16,
|
| 54 |
-
"linear_value_head_dim": 128,
|
| 55 |
-
"mamba_ssm_dtype": "float32",
|
| 56 |
-
"max_position_embeddings": 262144,
|
| 57 |
-
"mlp_only_layers": [],
|
| 58 |
-
"model_type": "qwen3_5_text",
|
| 59 |
-
"mtp_num_hidden_layers": 1,
|
| 60 |
-
"mtp_use_dedicated_embeddings": false,
|
| 61 |
-
"num_attention_heads": 8,
|
| 62 |
-
"num_hidden_layers": 24,
|
| 63 |
-
"num_key_value_heads": 2,
|
| 64 |
-
"pad_token_id": null,
|
| 65 |
-
"partial_rotary_factor": 0.25,
|
| 66 |
-
"rms_norm_eps": 1e-06,
|
| 67 |
-
"rope_parameters": {
|
| 68 |
-
"mrope_interleaved": true,
|
| 69 |
-
"mrope_section": [
|
| 70 |
-
11,
|
| 71 |
-
11,
|
| 72 |
-
10
|
| 73 |
-
],
|
| 74 |
-
"partial_rotary_factor": 0.25,
|
| 75 |
-
"rope_theta": 10000000,
|
| 76 |
-
"rope_type": "default"
|
| 77 |
-
},
|
| 78 |
-
"tie_word_embeddings": true,
|
| 79 |
-
"use_cache": true,
|
| 80 |
-
"vocab_size": 248320
|
| 81 |
-
},
|
| 82 |
-
"tie_word_embeddings": true,
|
| 83 |
-
"transformers_version": "5.14.1",
|
| 84 |
-
"video_token_id": 248057,
|
| 85 |
-
"vision_config": {
|
| 86 |
-
"deepstack_visual_indexes": [],
|
| 87 |
-
"depth": 24,
|
| 88 |
-
"dtype": "bfloat16",
|
| 89 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 90 |
-
"hidden_size": 1024,
|
| 91 |
-
"in_channels": 3,
|
| 92 |
-
"initializer_range": 0.02,
|
| 93 |
-
"intermediate_size": 4096,
|
| 94 |
-
"model_type": "qwen3_5_vision",
|
| 95 |
-
"num_heads": 16,
|
| 96 |
-
"num_position_embeddings": 2304,
|
| 97 |
-
"out_hidden_size": 2048,
|
| 98 |
-
"patch_size": 16,
|
| 99 |
-
"spatial_merge_size": 2,
|
| 100 |
-
"temporal_patch_size": 2
|
| 101 |
-
},
|
| 102 |
-
"vision_end_token_id": 248054,
|
| 103 |
-
"vision_start_token_id": 248053
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 248046,
|
| 4 |
-
"output_attentions": false,
|
| 5 |
-
"output_hidden_states": false,
|
| 6 |
-
"pad_token_id": 248044,
|
| 7 |
-
"transformers_version": "5.14.1",
|
| 8 |
-
"use_cache": true
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:320dd2f7e1804faceae76fbfd6bfb83f17c9294a369bebf07cf1f3278dec3351
|
| 3 |
-
size 5443677680
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"size": {
|
| 3 |
-
"longest_edge": 16777216,
|
| 4 |
-
"shortest_edge": 65536
|
| 5 |
-
},
|
| 6 |
-
"patch_size": 16,
|
| 7 |
-
"temporal_patch_size": 2,
|
| 8 |
-
"merge_size": 2,
|
| 9 |
-
"image_mean": [
|
| 10 |
-
0.5,
|
| 11 |
-
0.5,
|
| 12 |
-
0.5
|
| 13 |
-
],
|
| 14 |
-
"image_std": [
|
| 15 |
-
0.5,
|
| 16 |
-
0.5,
|
| 17 |
-
0.5
|
| 18 |
-
],
|
| 19 |
-
"processor_class": "Qwen3VLProcessor",
|
| 20 |
-
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
-
size 19989325
|
|
|
|
|
|
|
|
|
|
|
|
models/2b_s1_1600h_gs6736/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
-
"backend": "tokenizers",
|
| 7 |
-
"bos_token": null,
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<|im_end|>",
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local": true,
|
| 13 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"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+",
|
| 26 |
-
"processor_class": "Qwen3VLProcessor",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null,
|
| 30 |
-
"video_token": "<|video_pad|>",
|
| 31 |
-
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|