初始化项目，由ModelHub XC社区提供模型
Model: unsloth/Qwen3-VL-8B-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
55
.gitattributes
vendored
Normal file
55
.gitattributes
vendored
Normal file
@@ -0,0 +1,55 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
217
README.md
Normal file
217
README.md
Normal file
@@ -0,0 +1,217 @@
|
||||
---
|
||||
tags:
|
||||
- unsloth
|
||||
base_model:
|
||||
- Qwen/Qwen3-VL-8B-Instruct
|
||||
license: apache-2.0
|
||||
pipeline_tag: image-text-to-text
|
||||
library_name: transformers
|
||||
---
|
||||
> [!NOTE]
|
||||
> Includes Unsloth **chat template fixes**! <br> For `llama.cpp`, use `--jinja`
|
||||
>
|
||||
|
||||
<div>
|
||||
<p style="margin-top: 0;margin-bottom: 0;">
|
||||
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
||||
</p>
|
||||
<div style="display: flex; gap: 5px; align-items: center; ">
|
||||
<a href="https://github.com/unslothai/unsloth/">
|
||||
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
||||
</a>
|
||||
<a href="https://discord.gg/unsloth">
|
||||
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
||||
</a>
|
||||
<a href="https://docs.unsloth.ai/">
|
||||
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
||||
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
|
||||
|
||||
# Qwen3-VL-8B-Instruct
|
||||
|
||||
|
||||
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
|
||||
|
||||
This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.
|
||||
|
||||
Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.
|
||||
|
||||
|
||||
#### Key Enhancements:
|
||||
|
||||
* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.
|
||||
|
||||
* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos.
|
||||
|
||||
* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.
|
||||
|
||||
* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.
|
||||
|
||||
* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers.
|
||||
|
||||
* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.
|
||||
|
||||
* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.
|
||||
|
||||
* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension.
|
||||
|
||||
|
||||
#### Model Architecture Updates:
|
||||
|
||||
<p align="center">
|
||||
<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_arc.jpg" width="80%"/>
|
||||
<p>
|
||||
|
||||
|
||||
1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
|
||||
|
||||
2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
|
||||
|
||||
3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.
|
||||
|
||||
This is the weight repository for Qwen3-VL-8B-Instruct.
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Model Performance
|
||||
|
||||
**Multimodal performance**
|
||||
|
||||
|
||||
|
||||
**Pure text performance**
|
||||
|
||||
|
||||
## Quickstart
|
||||
|
||||
Below, we provide simple examples to show how to use Qwen3-VL with 🤖 ModelScope and 🤗 Transformers.
|
||||
|
||||
The code of Qwen3-VL has been in the latest Hugging Face transformers and we advise you to build from source with command:
|
||||
```
|
||||
pip install git+https://github.com/huggingface/transformers
|
||||
# pip install transformers==4.57.0 # currently, V4.57.0 is not released
|
||||
```
|
||||
|
||||
### Using 🤗 Transformers to Chat
|
||||
|
||||
Here we show a code snippet to show how to use the chat model with `transformers`:
|
||||
|
||||
```python
|
||||
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
|
||||
|
||||
# default: Load the model on the available device(s)
|
||||
model = Qwen3VLForConditionalGeneration.from_pretrained(
|
||||
"Qwen/Qwen3-VL-8B-Instruct", dtype="auto", device_map="auto"
|
||||
)
|
||||
|
||||
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
||||
# model = Qwen3VLForConditionalGeneration.from_pretrained(
|
||||
# "Qwen/Qwen3-VL-8B-Instruct",
|
||||
# dtype=torch.bfloat16,
|
||||
# attn_implementation="flash_attention_2",
|
||||
# device_map="auto",
|
||||
# )
|
||||
|
||||
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-8B-Instruct")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "image",
|
||||
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
||||
},
|
||||
{"type": "text", "text": "Describe this image."},
|
||||
],
|
||||
}
|
||||
]
|
||||
|
||||
# Preparation for inference
|
||||
inputs = processor.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_dict=True,
|
||||
return_tensors="pt"
|
||||
)
|
||||
inputs = inputs.to(model.device)
|
||||
|
||||
# Inference: Generation of the output
|
||||
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
||||
generated_ids_trimmed = [
|
||||
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
||||
]
|
||||
output_text = processor.batch_decode(
|
||||
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
)
|
||||
print(output_text)
|
||||
```
|
||||
|
||||
### Generation Hyperparameters
|
||||
#### VL
|
||||
```bash
|
||||
export greedy='false'
|
||||
export top_p=0.8
|
||||
export top_k=20
|
||||
export temperature=0.7
|
||||
export repetition_penalty=1.0
|
||||
export presence_penalty=1.5
|
||||
export out_seq_length=16384
|
||||
```
|
||||
|
||||
#### Text
|
||||
```bash
|
||||
export greedy='false'
|
||||
export top_p=1.0
|
||||
export top_k=40
|
||||
export repetition_penalty=1.0
|
||||
export presence_penalty=2.0
|
||||
export temperature=1.0
|
||||
export out_seq_length=32768
|
||||
```
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
If you find our work helpful, feel free to give us a cite.
|
||||
|
||||
```
|
||||
@misc{qwen3technicalreport,
|
||||
title={Qwen3 Technical Report},
|
||||
author={Qwen Team},
|
||||
year={2025},
|
||||
eprint={2505.09388},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2505.09388},
|
||||
}
|
||||
|
||||
@article{Qwen2.5-VL,
|
||||
title={Qwen2.5-VL Technical Report},
|
||||
author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
|
||||
journal={arXiv preprint arXiv:2502.13923},
|
||||
year={2025}
|
||||
}
|
||||
|
||||
@article{Qwen2VL,
|
||||
title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
|
||||
author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
|
||||
journal={arXiv preprint arXiv:2409.12191},
|
||||
year={2024}
|
||||
}
|
||||
|
||||
@article{Qwen-VL,
|
||||
title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
|
||||
author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
|
||||
journal={arXiv preprint arXiv:2308.12966},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
120
chat_template.jinja
Normal file
120
chat_template.jinja
Normal file
@@ -0,0 +1,120 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set image_count = namespace(value=0) %}
|
||||
{%- set video_count = namespace(value=0) %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.role == "user" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content_item in message.content %}
|
||||
{%- if 'text' in content_item %}
|
||||
{{- content_item.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and message.content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
File diff suppressed because one or more lines are too long
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3VLForConditionalGeneration"
|
||||
],
|
||||
"image_token_id": 151655,
|
||||
"model_type": "qwen3_vl",
|
||||
"pad_token_id": 151654,
|
||||
"text_config": {
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 262144,
|
||||
"model_type": "qwen3_vl_text",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_interleaved": true,
|
||||
"mrope_section": [
|
||||
24,
|
||||
20,
|
||||
20
|
||||
],
|
||||
"rope_type": "default"
|
||||
},
|
||||
"rope_theta": 5000000,
|
||||
"use_cache": true,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"unsloth_fixed": true,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"deepstack_visual_indexes": [
|
||||
8,
|
||||
16,
|
||||
24
|
||||
],
|
||||
"depth": 27,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"in_channels": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4304,
|
||||
"model_type": "qwen3_vl",
|
||||
"num_heads": 16,
|
||||
"num_position_embeddings": 2304,
|
||||
"out_hidden_size": 4096,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"pad_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"repetition_penalty": 1.0,
|
||||
"temperature": 0.7,
|
||||
"transformers_version": "4.56.0"
|
||||
}
|
||||
3
merges.txt
Normal file
3
merges.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
|
||||
size 1671853
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5d0aef0eb170fc7453a296c43c0849a56f510555d3588e4fd662bb35490aefa
|
||||
size 4902275944
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8be88fb5501e4d5719a6d4cc212e6a13480330e74f3e8c77daa1a68f199106b5
|
||||
size 4915962496
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:83de00eafe6e0d57ccd009dbcf71c9974d74df2f016c27afb7e95aafd16b2192
|
||||
size 4999831048
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a88b98e9f96270973f567e6a2c103ede6ccdf915ca3075e21c755604d0377a5
|
||||
size 2716270024
|
||||
757
model.safetensors.index.json
Normal file
757
model.safetensors.index.json
Normal file
@@ -0,0 +1,757 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 17534247392
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
39
preprocessor_config.json
Normal file
39
preprocessor_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": null,
|
||||
"merge_size": 2,
|
||||
"min_pixels": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 16,
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
242
tokenizer_config.json
Normal file
242
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
41
video_preprocessor_config.json
Normal file
41
video_preprocessor_config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": true,
|
||||
"fps": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_frames": 768,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"num_frames": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 16,
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user