Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +262 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- config.json +106 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +736 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +210 -0
- video_preprocessor_config.json +86 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: nvidia-open-model-license
|
| 4 |
+
license_link: >-
|
| 5 |
+
https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license
|
| 6 |
+
datasets:
|
| 7 |
+
- nvidia/Cosmos-Reason1-SFT-Dataset
|
| 8 |
+
- nvidia/Cosmos-Reason1-RL-Dataset
|
| 9 |
+
- nvidia/Cosmos-Reason1-Benchmark
|
| 10 |
+
library_name: transformers
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
base_model:
|
| 14 |
+
- nvidia/Cosmos-Reason1-7B
|
| 15 |
+
tags:
|
| 16 |
+
- nvidia
|
| 17 |
+
- unsloth
|
| 18 |
+
- cosmos
|
| 19 |
+
---
|
| 20 |
+
<div>
|
| 21 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 22 |
+
<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>
|
| 23 |
+
</p>
|
| 24 |
+
<div style="display: flex; gap: 5px; align-items: center; ">
|
| 25 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 26 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 27 |
+
</a>
|
| 28 |
+
<a href="https://discord.gg/unsloth">
|
| 29 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 30 |
+
</a>
|
| 31 |
+
<a href="https://docs.unsloth.ai/basics/qwen3-how-to-run-and-fine-tune">
|
| 32 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 33 |
+
</a>
|
| 34 |
+
</div>
|
| 35 |
+
</div>
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
# **Cosmos-Reason1: Physical AI Common Sense and Embodied Reasoning Models**
|
| 40 |
+
|
| 41 |
+
[**Cosmos**](https://huggingface.co/collections/nvidia/cosmos-reason1-67c9e926206426008f1da1b7) | [**Code**](https://github.com/nvidia-cosmos/cosmos-reason1) | [**Paper**](https://arxiv.org/abs/2503.15558) | [**Paper Website**](https://research.nvidia.com/labs/dir/cosmos-reason1)
|
| 42 |
+
|
| 43 |
+
# Model Overview
|
| 44 |
+
|
| 45 |
+
## Description:
|
| 46 |
+
|
| 47 |
+
**Cosmos-Reason1 Models**: Physical AI models understand physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
|
| 48 |
+
|
| 49 |
+
The Cosmos-Reason1 models are post-trained with physical common sense and embodied reasoning data with supervised fine-tuning and reinforcement learning. These are Physical AI models that can understand space, time, and fundamental physics, and can serve as planning models to reason about the next steps of an embodied agent.
|
| 50 |
+
|
| 51 |
+
The models are ready for commercial use.
|
| 52 |
+
|
| 53 |
+
**Model Developer**: NVIDIA
|
| 54 |
+
|
| 55 |
+
## Model Versions
|
| 56 |
+
|
| 57 |
+
The Cosmos-Reason1 includes the following model:
|
| 58 |
+
|
| 59 |
+
- [Cosmos-Reason1-7B](https://huggingface.co/nvidia/Cosmos-Reason1-7B): Given a text prompt and an input video, think and generate the answer with respect to the input text prompt and video.
|
| 60 |
+
|
| 61 |
+
### License:
|
| 62 |
+
|
| 63 |
+
This model is released under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). For a custom license, please contact [[email protected]](mailto:[email protected]).
|
| 64 |
+
|
| 65 |
+
Under the NVIDIA Open Model License, NVIDIA confirms:
|
| 66 |
+
|
| 67 |
+
* Models are commercially usable.
|
| 68 |
+
* You are free to create and distribute Derivative Models.
|
| 69 |
+
* NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
|
| 70 |
+
|
| 71 |
+
**Important Note**: If You bypass, disable, reduce the efficacy of, or circumvent any technical limitation, safety guardrail or associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism (collectively “Guardrail”) contained in the Model without a substantially similar Guardrail appropriate for your use case, your rights under this Agreement [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate.
|
| 72 |
+
|
| 73 |
+
### Deployment Geography:
|
| 74 |
+
|
| 75 |
+
Global
|
| 76 |
+
|
| 77 |
+
### Use Case:
|
| 78 |
+
|
| 79 |
+
Physical AI: Space, time, fundamental physics understanding and embodied reasoning, encompassing robotics, and autonomous vehicles (AV).
|
| 80 |
+
|
| 81 |
+
### Release Date:
|
| 82 |
+
|
| 83 |
+
* Github: [05/17/2025](https://github.com/nvidia-cosmos/cosmos-reason1)
|
| 84 |
+
* Huggingface: [05/17/2025](https://huggingface.co/collections/nvidia/cosmos-reason1-67c9e926206426008f1da1b7)
|
| 85 |
+
|
| 86 |
+
## Model Architecture:
|
| 87 |
+
|
| 88 |
+
Architecture Type: A Multi-modal LLM consists of a Vision Transformer (ViT) for vision encoder and a Dense Transformer model for LLM.
|
| 89 |
+
Network Architecture: Qwen2.5-VL-7B-Instruct.
|
| 90 |
+
|
| 91 |
+
Cosmos-Reason-7B is post-trained based on [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) and follows the same model architecture.
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
## Input
|
| 95 |
+
|
| 96 |
+
**Input Type(s)**: Text+Video/Image
|
| 97 |
+
|
| 98 |
+
**Input Format(s)**:
|
| 99 |
+
* Text: String
|
| 100 |
+
* Video: mp4
|
| 101 |
+
* Image: jpg
|
| 102 |
+
|
| 103 |
+
**Input Parameters**:
|
| 104 |
+
* Text: One-dimensional (1D)
|
| 105 |
+
* Video: Three-dimensional (3D)
|
| 106 |
+
* Image: Two-dimensional (2D)
|
| 107 |
+
|
| 108 |
+
**Other Properties Related to Input**:
|
| 109 |
+
* Use `FPS=4` for input video to match the training setup.
|
| 110 |
+
* Append `Answer the question in the following format: <think>\nyour reasoning\n</think>\n\n<answer>\nyour answer\n</answer>.` in the system prompt to encourage long chain-of-thought reasoning response.
|
| 111 |
+
|
| 112 |
+
## Output
|
| 113 |
+
|
| 114 |
+
**Output Type(s)**: Text
|
| 115 |
+
|
| 116 |
+
**Output Format**: String
|
| 117 |
+
|
| 118 |
+
**Output Parameters**: Text: One-dimensional (1D)
|
| 119 |
+
|
| 120 |
+
**Other Properties Related to Output**:
|
| 121 |
+
* Recommend using 4096 or more output max tokens to avoid truncation of long chain-of-thought response.
|
| 122 |
+
* Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
|
| 123 |
+
|
| 124 |
+
|
| 125 |
+
## Software Integration
|
| 126 |
+
|
| 127 |
+
**Runtime Engine(s):**
|
| 128 |
+
|
| 129 |
+
* [vLLM](https://github.com/vllm-project/vllm)
|
| 130 |
+
|
| 131 |
+
**Supported Hardware Microarchitecture Compatibility:**
|
| 132 |
+
|
| 133 |
+
* NVIDIA Blackwell
|
| 134 |
+
* NVIDIA Hopper
|
| 135 |
+
|
| 136 |
+
**Note**: We have only tested doing inference with BF16 precision.
|
| 137 |
+
|
| 138 |
+
**Operating System(s):**
|
| 139 |
+
|
| 140 |
+
* Linux (We have not tested on other operating systems.)
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
# Usage
|
| 144 |
+
|
| 145 |
+
See [Cosmos-Reason1](https://github.com/nvidia-cosmos/cosmos-reason1) for details.
|
| 146 |
+
* Post Training: [Cosmos-Reason1](https://github.com/nvidia-cosmos/cosmos-reason1) provides examples of supervised fine-tuning and reinforcement learning on embodied reasoning datasets.
|
| 147 |
+
|
| 148 |
+
# Evaluation
|
| 149 |
+
|
| 150 |
+
Please see our [technical paper](https://arxiv.org/pdf/2503.15558) for detailed evaluations on physical common sense and embodied reasoning. Part of the evaluation datasets are released under [Cosmos-Reason1-Benchmark](https://huggingface.co/datasets/nvidia/Cosmos-Reason1-Benchmark). The embodied reasoning datasets and benchmarks focus on the following areas: robotics (RoboVQA, BridgeDataV2, Agibot, RobFail), ego-centric human demonstration (HoloAssist), and Autonomous Vehicle (AV) driving video data. The AV dataset is collected and annotated by NVIDIA.
|
| 151 |
+
All datasets go through the data annotation process described in the technical paper to prepare training and evaluation data and annotations.
|
| 152 |
+
|
| 153 |
+
**Data Collection Method**:
|
| 154 |
+
* RoboVQA: Hybrid: Automatic/Sensors
|
| 155 |
+
* BridgeDataV2: Automatic/Sensors
|
| 156 |
+
* AgiBot: Automatic/Sensors
|
| 157 |
+
* RoboFail: Automatic/Sensors
|
| 158 |
+
* HoloAssist: Human
|
| 159 |
+
* AV: Automatic/Sensors
|
| 160 |
+
|
| 161 |
+
**Labeling Method**:
|
| 162 |
+
* RoboVQA: Hybrid: Human,Automated
|
| 163 |
+
* BridgeDataV2: Hybrid: Human,Automated
|
| 164 |
+
* AgiBot: Hybrid: Human,Automated
|
| 165 |
+
* RoboFail: Hybrid: Human,Automated
|
| 166 |
+
* HoloAssist: Hybrid: Human,Automated
|
| 167 |
+
* AV: Hybrid: Human,Automated
|
| 168 |
+
|
| 169 |
+
**Metrics**:
|
| 170 |
+
We report the model accuracy on the embodied reasoning benchmark introduced in [Cosmos-Reason1](https://arxiv.org/abs/2503.15558). The results differ from those presented in Table 9 due to additional training aimed at supporting a broader range of Physical AI tasks beyond the benchmark.
|
| 171 |
+
| | [RoboVQA](https://robovqa.github.io/) | AV | [BridgeDataV2](https://rail-berkeley.github.io/bridgedata/)| [Agibot](https://github.com/OpenDriveLab/AgiBot-World)| [HoloAssist](https://holoassist.github.io/) | [RoboFail](https://robot-reflect.github.io/) | Average |
|
| 172 |
+
|--------------------|---------------------------------------------|----------|------------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|
|
| 173 |
+
| **Accuracy** | 87.3 | 70.8 | 63.7 | 48.9 | 62.7 | 57.2 | 65.1 |
|
| 174 |
+
|
| 175 |
+
## Dataset Format
|
| 176 |
+
Modality: Video (mp4) and Text
|
| 177 |
+
|
| 178 |
+
## Dataset Quantification
|
| 179 |
+
We release the embodied reasoning data and benchmarks. Each data sample is a pair of video and text. The text annotations include understanding and reasoning annotations described in the Cosmos-Reason1 paper. Each video may have multiple text annotations. The quantity of the video and text pairs is described in the table below.
|
| 180 |
+
**The AV data is currently unavailable and will be uploaded soon!**
|
| 181 |
+
|
| 182 |
+
| | [RoboVQA](https://robovqa.github.io/) | AV | [BridgeDataV2](https://rail-berkeley.github.io/bridgedata/)| [Agibot](https://github.com/OpenDriveLab/AgiBot-World)| [HoloAssist](https://holoassist.github.io/) | [RoboFail](https://robot-reflect.github.io/) | Total Storage Size |
|
| 183 |
+
|--------------------|---------------------------------------------|----------|------------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|--------------------|
|
| 184 |
+
| **SFT Data** | 1.14m | 24.7k | 258k | 38.9k | 273k | N/A | **300.6GB** |
|
| 185 |
+
| **RL Data** | 252 | 200 | 240 | 200 | 200 | N/A | **2.6GB** |
|
| 186 |
+
| **Benchmark Data** | 110 | 100 | 100 | 100 | 100 | 100 | **1.5GB** |
|
| 187 |
+
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
We release text annotations for all embodied reasoning datasets and videos for RoboVQA and AV datasets. For other datasets, users may download the source videos from the original data source and find corresponding video sources via the video names. The held-out RoboFail benchmark is released for measuring the generalization capability.
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
## Inference:
|
| 194 |
+
**Acceleration Engine:** PyTorch, flash attention <br>
|
| 195 |
+
**Test Hardware:** H100, A100, GB200 <br>
|
| 196 |
+
* Minimum 2 GPU cards, multi nodes require Infiniband / ROCE connection <br>
|
| 197 |
+
|
| 198 |
+
## Ethical Considerations
|
| 199 |
+
|
| 200 |
+
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
|
| 201 |
+
|
| 202 |
+
Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.
|
| 203 |
+
|
| 204 |
+
For more detailed information on ethical considerations for this model, please see the subcards of Explainability, Bias, Safety & Security, and Privacy below.
|
| 205 |
+
|
| 206 |
+
Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
|
| 207 |
+
|
| 208 |
+
### Plus Plus (++) Promise
|
| 209 |
+
|
| 210 |
+
We value you, the datasets, the diversity they represent, and what we have been entrusted with. This model and its associated data have been:
|
| 211 |
+
|
| 212 |
+
* Verified to comply with current applicable disclosure laws, regulations, and industry standards.
|
| 213 |
+
* Verified to comply with applicable privacy labeling requirements.
|
| 214 |
+
* Annotated to describe the collector/source (NVIDIA or a third-party).
|
| 215 |
+
* Characterized for technical limitations.
|
| 216 |
+
* Reviewed to ensure proper disclosure is accessible to, maintained for, and in compliance with NVIDIA data subjects and their requests.
|
| 217 |
+
* Reviewed before release.
|
| 218 |
+
* Tagged for known restrictions and potential safety implications.
|
| 219 |
+
|
| 220 |
+
### Bias
|
| 221 |
+
|
| 222 |
+
| Field | Response |
|
| 223 |
+
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
|
| 224 |
+
| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None |
|
| 225 |
+
| Measures taken to mitigate against unwanted bias: | The training video sources contain multiple physical embodiments and environments including human, car, single arm robot, bimanual robot in indoor and outdoor environments. By training on numerous and various physical interactions and curated datasets, we strive to provide a model that does not possess biases towards certain embodiments or environments. |
|
| 226 |
+
|
| 227 |
+
### Explainability
|
| 228 |
+
|
| 229 |
+
| Field | Response |
|
| 230 |
+
| :-------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------- |
|
| 231 |
+
| Intended Application & Domain: | Physical AI Reasoning |
|
| 232 |
+
| Model Type: | Transformer |
|
| 233 |
+
| Intended Users: | Physical AI developers |
|
| 234 |
+
| Output: | Text |
|
| 235 |
+
| Describe how the model works: | Generates text answers based on input text prompt and video |
|
| 236 |
+
| Technical Limitations: | The model may not follow the video or text input accurately in challenging cases, where the input video shows complex scene composition and temporal dynamics. Examples of challenging scenes include: fast camera movements, overlapping human-object interactions, low lighting with high motion blur, and multiple people performing different actions simultaneously. |
|
| 237 |
+
| Verified to have met prescribed NVIDIA quality standards: | Yes |
|
| 238 |
+
| Performance Metrics: | Quantitative and Qualitative Evaluation. Cosmos-Reason1 proposes the embodied reasoning benchmark and physical common sense benchmark to evaluate accuracy with visual question answering. |
|
| 239 |
+
| Potential Known Risks: | The model's output can generate all forms of texts, including what may be considered toxic, offensive, or indecent. |
|
| 240 |
+
| Licensing: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) |
|
| 241 |
+
|
| 242 |
+
### Privacy
|
| 243 |
+
|
| 244 |
+
| Field | Response |
|
| 245 |
+
| :------------------------------------------------------------------ | :------------- |
|
| 246 |
+
| Generatable or reverse engineerable personal information? | None Known |
|
| 247 |
+
| Protected class data used to create this model? | None Known |
|
| 248 |
+
| Was consent obtained for any personal data used? | None Known |
|
| 249 |
+
| How often is dataset reviewed? | Before Release |
|
| 250 |
+
| Is there provenance for all datasets used in training? | Yes |
|
| 251 |
+
| Does data labeling (annotation, metadata) comply with privacy laws? | Yes |
|
| 252 |
+
| Applicable Privacy Policy | [NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy) |
|
| 253 |
+
|
| 254 |
+
|
| 255 |
+
### Safety
|
| 256 |
+
|
| 257 |
+
| Field | Response |
|
| 258 |
+
| :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| 259 |
+
| Model Application(s): | Physical AI common sense understanding and embodied reasoning |
|
| 260 |
+
| Describe the life critical impact (if present). | None Known |
|
| 261 |
+
| Use Case Restrictions: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) |
|
| 262 |
+
| Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face, and may become available on cloud providers' model catalog. |
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% 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 %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 3584,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 18944,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 28,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 28,
|
| 16 |
+
"num_hidden_layers": 28,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"pad_token_id": 151654,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"text_config": {
|
| 32 |
+
"architectures": [
|
| 33 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 34 |
+
],
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"bos_token_id": 151643,
|
| 37 |
+
"eos_token_id": 151645,
|
| 38 |
+
"hidden_act": "silu",
|
| 39 |
+
"hidden_size": 3584,
|
| 40 |
+
"image_token_id": null,
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 18944,
|
| 43 |
+
"max_position_embeddings": 128000,
|
| 44 |
+
"max_window_layers": 28,
|
| 45 |
+
"model_type": "qwen2_5_vl_text",
|
| 46 |
+
"num_attention_heads": 28,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 4,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": {
|
| 51 |
+
"mrope_section": [
|
| 52 |
+
16,
|
| 53 |
+
24,
|
| 54 |
+
24
|
| 55 |
+
],
|
| 56 |
+
"rope_type": "default",
|
| 57 |
+
"type": "default"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": 32768,
|
| 61 |
+
"torch_dtype": "bfloat16",
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"use_sliding_window": false,
|
| 64 |
+
"video_token_id": null,
|
| 65 |
+
"vision_end_token_id": 151653,
|
| 66 |
+
"vision_start_token_id": 151652,
|
| 67 |
+
"vision_token_id": 151654,
|
| 68 |
+
"vocab_size": 152064
|
| 69 |
+
},
|
| 70 |
+
"tie_word_embeddings": false,
|
| 71 |
+
"torch_dtype": "bfloat16",
|
| 72 |
+
"transformers_version": "4.52.3",
|
| 73 |
+
"unsloth_fixed": true,
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"use_sliding_window": false,
|
| 76 |
+
"video_token_id": 151656,
|
| 77 |
+
"vision_config": {
|
| 78 |
+
"depth": 32,
|
| 79 |
+
"fullatt_block_indexes": [
|
| 80 |
+
7,
|
| 81 |
+
15,
|
| 82 |
+
23,
|
| 83 |
+
31
|
| 84 |
+
],
|
| 85 |
+
"hidden_act": "silu",
|
| 86 |
+
"hidden_size": 1280,
|
| 87 |
+
"in_channels": 3,
|
| 88 |
+
"in_chans": 3,
|
| 89 |
+
"initializer_range": 0.02,
|
| 90 |
+
"intermediate_size": 3420,
|
| 91 |
+
"model_type": "qwen2_5_vl",
|
| 92 |
+
"num_heads": 16,
|
| 93 |
+
"out_hidden_size": 3584,
|
| 94 |
+
"patch_size": 14,
|
| 95 |
+
"spatial_merge_size": 2,
|
| 96 |
+
"spatial_patch_size": 14,
|
| 97 |
+
"temporal_patch_size": 2,
|
| 98 |
+
"tokens_per_second": 2,
|
| 99 |
+
"torch_dtype": "bfloat16",
|
| 100 |
+
"window_size": 112
|
| 101 |
+
},
|
| 102 |
+
"vision_end_token_id": 151653,
|
| 103 |
+
"vision_start_token_id": 151652,
|
| 104 |
+
"vision_token_id": 151654,
|
| 105 |
+
"vocab_size": 152064
|
| 106 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 128000,
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"temperature": 1e-06,
|
| 12 |
+
"transformers_version": "4.52.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e2251aa8f91e15bd345ad7cada85f83e4fe087d41f43d968f0c566a04696073
|
| 3 |
+
size 4968243304
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:503b87e7e15d34830d47bca272f734b08bfc6af3a36d489e500261807fb1e13e
|
| 3 |
+
size 4991495816
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a1d8b031246eee79a6a0a6fc99f526bad78f69e16a9555633fae0d0dc3fa999
|
| 3 |
+
size 4932751040
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc041a7ce8ead8b9a4e218e484d94164ce945dcb68799814737dd0f57d969f21
|
| 3 |
+
size 1691924384
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,736 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16584333312
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 7 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 11 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 23 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 25 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 35 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 37 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 39 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 41 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 43 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 45 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 47 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 49 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 50 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 51 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 52 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 53 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 55 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 56 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 57 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 58 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 59 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 60 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 61 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 62 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 63 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 64 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 65 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 66 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 67 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 68 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 69 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 70 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 71 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 72 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 73 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 74 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 75 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 76 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 77 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 78 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 79 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 80 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 81 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 82 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 83 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 84 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 85 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 86 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 87 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 88 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 89 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 90 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 91 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 92 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 93 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 94 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 95 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 96 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 97 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 98 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 99 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 100 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 101 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 102 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 103 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 104 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 105 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 106 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 107 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 109 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 110 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 111 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 112 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 113 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 114 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 115 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 116 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 119 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 121 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 123 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 125 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 126 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 127 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 128 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 129 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 130 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 131 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 132 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 133 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 134 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 135 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 136 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 137 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 138 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 139 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 140 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 143 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 145 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 147 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 149 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 151 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 155 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 157 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 161 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 163 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 164 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 166 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 167 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 168 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 169 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 170 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 171 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 172 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 173 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 175 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 176 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 177 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 178 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 179 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 180 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 181 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 182 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 183 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 184 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 185 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 186 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 187 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 188 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 189 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 190 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 191 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 192 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 193 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 194 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 195 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 196 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 197 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 198 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 199 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 200 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 201 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 202 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 203 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 204 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 205 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 206 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 207 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 208 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 209 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 210 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 211 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 212 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 213 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 214 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 215 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 217 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 219 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 221 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 223 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 225 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 226 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 227 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 228 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 229 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 230 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 231 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 232 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 233 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 234 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 235 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 236 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 237 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 238 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 239 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 240 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 241 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 242 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 243 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 245 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 247 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 251 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 253 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 255 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 257 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 259 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 263 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 265 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 269 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 271 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 275 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 277 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 281 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 283 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 287 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 289 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 293 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 295 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 296 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 299 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 301 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 305 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 306 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 307 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 308 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 311 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 313 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 317 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 318 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 319 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 320 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 322 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 323 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 324 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 325 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 326 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 329 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 330 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 331 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
| 332 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 334 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 335 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 336 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 337 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 338 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 339 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 341 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 343 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 347 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 349 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 351 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 353 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 355 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 359 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 361 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 363 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 365 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 367 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 371 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 373 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 375 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 377 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 379 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 383 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 385 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 387 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 389 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 391 |
+
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 394 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 406 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 466 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 467 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 468 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 469 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 470 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 471 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 472 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 473 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 474 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 475 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 476 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 477 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 478 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 479 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 480 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 481 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 482 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 483 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 484 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 485 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 486 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 487 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 488 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 489 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 490 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 491 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 492 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 493 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 494 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 495 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 496 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 497 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 498 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 499 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 500 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 501 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 502 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 503 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 504 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 505 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 506 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 507 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 508 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 509 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 510 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 511 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 512 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 513 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 514 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 515 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 516 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 517 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 518 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 519 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 520 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 521 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 522 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 523 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 524 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 525 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 526 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 527 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 528 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 529 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 530 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 531 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 532 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 533 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 534 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 535 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 536 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 537 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 538 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 539 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 540 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 541 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 542 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 543 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 544 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 545 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 546 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 547 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 548 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 549 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 550 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 551 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 552 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 553 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 554 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 555 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 556 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 557 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 558 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 559 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 560 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 561 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 562 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 563 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 564 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 565 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 566 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 567 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 568 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 569 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 570 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 571 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 572 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 573 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 574 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 575 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 576 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 577 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 578 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 579 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 580 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 581 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 582 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 583 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 584 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 585 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 586 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 587 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 588 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 589 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 590 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 591 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 592 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 593 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 594 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 595 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 596 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 597 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 598 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 599 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 600 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 601 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 602 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 603 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 604 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 605 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 606 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 607 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 608 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 609 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 610 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 611 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 612 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 613 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 614 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 615 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 616 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 617 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 618 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 619 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 620 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 621 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 622 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 623 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 624 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 625 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 626 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 627 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 628 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 629 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 630 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 631 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 632 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 633 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 634 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 635 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 636 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 637 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 638 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 639 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 640 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 641 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 642 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 643 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 644 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 645 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 646 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 647 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 648 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 649 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 650 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 651 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 652 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 653 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 654 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 655 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 656 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 657 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 658 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 659 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 660 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 662 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 734 |
+
"lm_head.weight": "model-00004-of-00004.safetensors"
|
| 735 |
+
}
|
| 736 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 128000,
|
| 203 |
+
"pad_token": "<|vision_pad|>",
|
| 204 |
+
"padding_side": "left",
|
| 205 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null,
|
| 209 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 210 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_kwargs_names": [
|
| 3 |
+
"do_convert_rgb",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"size_divisor",
|
| 7 |
+
"default_to_square",
|
| 8 |
+
"resample",
|
| 9 |
+
"do_rescale",
|
| 10 |
+
"rescale_factor",
|
| 11 |
+
"do_normalize",
|
| 12 |
+
"image_mean",
|
| 13 |
+
"image_std",
|
| 14 |
+
"do_pad",
|
| 15 |
+
"do_center_crop",
|
| 16 |
+
"crop_size",
|
| 17 |
+
"data_format",
|
| 18 |
+
"input_data_format",
|
| 19 |
+
"device",
|
| 20 |
+
"min_pixels",
|
| 21 |
+
"max_pixels",
|
| 22 |
+
"patch_size",
|
| 23 |
+
"temporal_patch_size",
|
| 24 |
+
"merge_size"
|
| 25 |
+
],
|
| 26 |
+
"crop_size": null,
|
| 27 |
+
"data_format": "channels_first",
|
| 28 |
+
"default_to_square": true,
|
| 29 |
+
"device": null,
|
| 30 |
+
"do_center_crop": null,
|
| 31 |
+
"do_convert_rgb": true,
|
| 32 |
+
"do_normalize": true,
|
| 33 |
+
"do_pad": null,
|
| 34 |
+
"do_rescale": true,
|
| 35 |
+
"do_resize": true,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.48145466,
|
| 38 |
+
0.4578275,
|
| 39 |
+
0.40821073
|
| 40 |
+
],
|
| 41 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 42 |
+
"image_std": [
|
| 43 |
+
0.26862954,
|
| 44 |
+
0.26130258,
|
| 45 |
+
0.27577711
|
| 46 |
+
],
|
| 47 |
+
"input_data_format": null,
|
| 48 |
+
"max_pixels": 12845056,
|
| 49 |
+
"merge_size": 2,
|
| 50 |
+
"min_pixels": 3136,
|
| 51 |
+
"model_valid_processing_keys": [
|
| 52 |
+
"do_convert_rgb",
|
| 53 |
+
"do_resize",
|
| 54 |
+
"size",
|
| 55 |
+
"size_divisor",
|
| 56 |
+
"default_to_square",
|
| 57 |
+
"resample",
|
| 58 |
+
"do_rescale",
|
| 59 |
+
"rescale_factor",
|
| 60 |
+
"do_normalize",
|
| 61 |
+
"image_mean",
|
| 62 |
+
"image_std",
|
| 63 |
+
"do_pad",
|
| 64 |
+
"do_center_crop",
|
| 65 |
+
"crop_size",
|
| 66 |
+
"data_format",
|
| 67 |
+
"input_data_format",
|
| 68 |
+
"device",
|
| 69 |
+
"min_pixels",
|
| 70 |
+
"max_pixels",
|
| 71 |
+
"patch_size",
|
| 72 |
+
"temporal_patch_size",
|
| 73 |
+
"merge_size"
|
| 74 |
+
],
|
| 75 |
+
"patch_size": 14,
|
| 76 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 77 |
+
"resample": 3,
|
| 78 |
+
"rescale_factor": 0.00392156862745098,
|
| 79 |
+
"size": {
|
| 80 |
+
"longest_edge": 12845056,
|
| 81 |
+
"shortest_edge": 3136
|
| 82 |
+
},
|
| 83 |
+
"size_divisor": null,
|
| 84 |
+
"temporal_patch_size": 2,
|
| 85 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 86 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|