Flatten checkpoints layout: vlm/, grounding_dino/, refinenet/ hold core files directly
Browse files- checkpoints/grounding_dino/.gitkeep +0 -0
- checkpoints/refinenet/.gitkeep +0 -0
- checkpoints/refinenet/run_iter132_submission/checkpoints/proposal_adapter_full.pt +0 -3
- checkpoints/refinenet/run_iter132_submission/deployment_manifest.json +0 -17
- checkpoints/vlm/.gitkeep +0 -0
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/.gitattributes +0 -36
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/README.md +0 -178
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/added_tokens.json +0 -24
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/chat_template.jinja +0 -7
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/config.json +0 -132
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/generation_config.json +0 -13
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/merges.txt +0 -0
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00001-of-00004.safetensors +0 -3
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00002-of-00004.safetensors +0 -3
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00003-of-00004.safetensors +0 -3
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00004-of-00004.safetensors +0 -3
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model.safetensors.index.json +0 -737
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/preprocessor_config.json +0 -39
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/special_tokens_map.json +0 -31
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/tokenizer.json +0 -3
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/tokenizer_config.json +0 -210
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/video_preprocessor_config.json +0 -43
- checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/vocab.json +0 -0
checkpoints/grounding_dino/.gitkeep
DELETED
|
File without changes
|
checkpoints/refinenet/.gitkeep
DELETED
|
File without changes
|
checkpoints/refinenet/run_iter132_submission/checkpoints/proposal_adapter_full.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:932e479b854c3d5fbafee25a3fcf9e6481e864fe98a6867502d6ebff39463d9b
|
| 3 |
-
size 5013971
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/refinenet/run_iter132_submission/deployment_manifest.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"schema_version": 1,
|
| 3 |
-
"decision": "PROPOSAL_REPAIR_FULL_FIT_COMPLETE",
|
| 4 |
-
"model_kind": "proposal_repair_quality",
|
| 5 |
-
"selector_kind": "repair_quality",
|
| 6 |
-
"repair_variant": "full",
|
| 7 |
-
"query_mode": "q_last",
|
| 8 |
-
"decoder_mode": "fixed_current",
|
| 9 |
-
"operator_authorized": true,
|
| 10 |
-
"fit_protocol": "fixed_fold_selected_then_all_train_groups_full_fit",
|
| 11 |
-
"feature_contract_hash": "7fd672157bfa0174e802e66d1c37b5dd7996214edb191f9fba0c926f73d38748",
|
| 12 |
-
"proposal_checkpoint": "checkpoints/proposal_adapter_full.pt",
|
| 13 |
-
"proposal_checkpoint_sha256": "932e479b854c3d5fbafee25a3fcf9e6481e864fe98a6867502d6ebff39463d9b",
|
| 14 |
-
"frozen_inputs_unchanged": true,
|
| 15 |
-
"official_leaderboard_claim": false,
|
| 16 |
-
"release_note": "Camera-ready release manifest reconstructed from the checkpoint metadata (adapter_config, train_config, standardizer, source_feature_contract_hash). Original training run: runs/kept_wf10_final/iter132_submission in the SurgST-VLM research workspace."
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/.gitkeep
DELETED
|
File without changes
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/.gitattributes
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/README.md
DELETED
|
@@ -1,178 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
-
license: apache-2.0
|
| 5 |
-
base_model: Qwen/Qwen2.5-VL-7B-Instruct
|
| 6 |
-
tags:
|
| 7 |
-
- medical
|
| 8 |
-
- video understanding
|
| 9 |
-
- vision-language
|
| 10 |
-
- temporal action localization
|
| 11 |
-
- GRPO
|
| 12 |
-
- reinforcement learning
|
| 13 |
-
pipeline_tag: visual-question-answering
|
| 14 |
-
---
|
| 15 |
-
|
| 16 |
-
# uAI-NEXUS-MedVLM-1.0a-7B-RL
|
| 17 |
-
|
| 18 |
-
> **Accepted at CVPR 2026** 🎉
|
| 19 |
-
|
| 20 |
-
**Base Model**: [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
|
| 21 |
-
|
| 22 |
-
`uAI-NEXUS-MedVLM-1.0a-7B-RL` is a medical-video understanding model fine-tuned from Qwen2.5-VL-7B-Instruct. It is the 7B-RL member of the **uAI-NEXUS-MedVLM 1.0** family (variant **a** = Qwen2.5-VL base; variants **b** / **c** use Qwen3-VL-4B and Qwen3.5-4B respectively). Training uses a two-stage pipeline:
|
| 23 |
-
|
| 24 |
-
1. **Supervised Fine-Tuning (SFT)** on medical video QA data.
|
| 25 |
-
2. **Group Relative Policy Optimization (GRPO)** with task-specific rewards for temporal precision and clinical semantics.
|
| 26 |
-
|
| 27 |
-
It achieves state-of-the-art performance on medical video understanding across temporal action localization, spatiotemporal grounding, video summarization, region captioning, and surgical skill/CVS assessment.
|
| 28 |
-
|
| 29 |
-
- **📄 Paper**: [arXiv:2512.06581](https://arxiv.org/abs/2512.06581)
|
| 30 |
-
- **🌐 Project Page**: [uii-ai.github.io/MedGRPO](https://uii-ai.github.io/MedGRPO/)
|
| 31 |
-
- **💻 Code**: [github.com/UII-AI/MedGRPO-Code](https://github.com/UII-AI/MedGRPO-Code)
|
| 32 |
-
- **🤗 Dataset**: [UII-AI/MedVidBench](https://huggingface.co/datasets/UII-AI/MedVidBench)
|
| 33 |
-
- **📊 Leaderboard**: [UII-AI/MedVidBench-Leaderboard](https://huggingface.co/spaces/UII-AI/MedVidBench-Leaderboard)
|
| 34 |
-
|
| 35 |
-
## Model Details
|
| 36 |
-
|
| 37 |
-
- **Architecture**: Qwen2.5-VL (7B parameters) — video + text
|
| 38 |
-
- **Base Model**: [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
|
| 39 |
-
- **Training**: SFT → GRPO
|
| 40 |
-
- **Domain**: Medical and surgical video understanding
|
| 41 |
-
- **License**: Apache 2.0
|
| 42 |
-
|
| 43 |
-
## Supported Tasks
|
| 44 |
-
|
| 45 |
-
The model handles 8 medical video understanding tasks (11 variants):
|
| 46 |
-
|
| 47 |
-
| Task Category | Tasks |
|
| 48 |
-
|---|---|
|
| 49 |
-
| **Temporal Understanding** | Temporal Action Localization (TAL), Spatiotemporal Grounding (STG), Next Action Prediction |
|
| 50 |
-
| **Captioning** | Dense Captioning (GPT / Gemini), Video Summary (GPT / Gemini), Region Caption (GPT / Gemini) |
|
| 51 |
-
| **Assessment** | Skill Assessment, CVS (Critical View of Safety) |
|
| 52 |
-
|
| 53 |
-
## Training Data
|
| 54 |
-
|
| 55 |
-
Trained on 51,505 balanced video-instruction pairs (the MedVidBench Standard split), spanning 8 source datasets: AVOS, CholecT50, CholecTrack20, Cholec80-CVS, CoPESD, EgoSurgery, JIGSAWS, NurViD.
|
| 56 |
-
|
| 57 |
-
Stage 2 (GRPO) uses task-balanced subsets of the Standard split (detailed in the paper).
|
| 58 |
-
|
| 59 |
-
## Training Details
|
| 60 |
-
|
| 61 |
-
### Stage 1 — Supervised Fine-Tuning
|
| 62 |
-
|
| 63 |
-
- **Objective**: Learn medical video understanding from human-annotated QA pairs.
|
| 64 |
-
- **Optimizer**: AdamW with linear learning-rate schedule.
|
| 65 |
-
|
| 66 |
-
### Stage 2 — Group Relative Policy Optimization (GRPO)
|
| 67 |
-
|
| 68 |
-
- **Objective**: Improve temporal precision and clinical semantic quality with RL.
|
| 69 |
-
- **Reward functions**:
|
| 70 |
-
- **TAL / STG**: Logistic-normalized IoU (dataset-fair, IQR-based).
|
| 71 |
-
- **Video Summary / Region Caption**: Semantic similarity (SentenceBERT).
|
| 72 |
-
- **Next Action**: Exact-match reward.
|
| 73 |
-
- **Skill / CVS Assessment**: Score-based reward.
|
| 74 |
-
- **Framework**: [EasyR1](https://github.com/hiyouga/EasyR1) (built on [verl](https://github.com/volcengine/verl) by ByteDance).
|
| 75 |
-
|
| 76 |
-
## Usage
|
| 77 |
-
|
| 78 |
-
### Install
|
| 79 |
-
|
| 80 |
-
```bash
|
| 81 |
-
pip install transformers accelerate torch pillow qwen-vl-utils
|
| 82 |
-
```
|
| 83 |
-
|
| 84 |
-
### Inference with Transformers
|
| 85 |
-
|
| 86 |
-
```python
|
| 87 |
-
import torch
|
| 88 |
-
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
|
| 89 |
-
from qwen_vl_utils import process_vision_info
|
| 90 |
-
|
| 91 |
-
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
| 92 |
-
"UII-AI/uAI-NEXUS-MedVLM-1.0a-7B-RL",
|
| 93 |
-
torch_dtype=torch.bfloat16,
|
| 94 |
-
device_map="auto",
|
| 95 |
-
)
|
| 96 |
-
processor = AutoProcessor.from_pretrained("UII-AI/uAI-NEXUS-MedVLM-1.0a-7B-RL")
|
| 97 |
-
|
| 98 |
-
video_frames = ["frame_0001.jpg", "frame_0002.jpg", "frame_0003.jpg"] # list of frame paths
|
| 99 |
-
|
| 100 |
-
messages = [{
|
| 101 |
-
"role": "user",
|
| 102 |
-
"content": [
|
| 103 |
-
{"type": "video", "video": video_frames},
|
| 104 |
-
{"type": "text", "text": "When does the surgeon grasp the gallbladder? Provide start and end times in seconds."},
|
| 105 |
-
],
|
| 106 |
-
}]
|
| 107 |
-
|
| 108 |
-
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 109 |
-
image_inputs, video_inputs = process_vision_info(messages)
|
| 110 |
-
inputs = processor(
|
| 111 |
-
text=[text], images=image_inputs, videos=video_inputs,
|
| 112 |
-
padding=True, return_tensors="pt",
|
| 113 |
-
).to(model.device)
|
| 114 |
-
|
| 115 |
-
with torch.no_grad():
|
| 116 |
-
output_ids = model.generate(**inputs, max_new_tokens=256)
|
| 117 |
-
generated_ids = [out[len(inp):] for inp, out in zip(inputs.input_ids, output_ids)]
|
| 118 |
-
response = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 119 |
-
|
| 120 |
-
print(response)
|
| 121 |
-
# Example: "The surgeon grasps the gallbladder from 45.2 to 58.7 seconds."
|
| 122 |
-
```
|
| 123 |
-
|
| 124 |
-
### Batch Inference with VLLM
|
| 125 |
-
|
| 126 |
-
For full batch inference with correct video frame handling, use the reference pipeline at [UII-AI/MedGRPO-Code](https://github.com/UII-AI/MedGRPO-Code):
|
| 127 |
-
|
| 128 |
-
```bash
|
| 129 |
-
git clone https://github.com/UII-AI/MedGRPO-Code
|
| 130 |
-
cd MedGRPO-Code
|
| 131 |
-
pip install -r requirements.txt
|
| 132 |
-
bash run_inference.sh
|
| 133 |
-
```
|
| 134 |
-
|
| 135 |
-
## Performance
|
| 136 |
-
|
| 137 |
-
Evaluated on [MedVidBench](https://huggingface.co/datasets/UII-AI/MedVidBench) (6,245 test samples across 8 tasks). GRPO consistently improves the SFT baseline on:
|
| 138 |
-
|
| 139 |
-
- Temporal precision for TAL / STG (higher IoU).
|
| 140 |
-
- Semantic quality for video summaries and region captions.
|
| 141 |
-
- Alignment with expert annotations for skill / CVS assessment.
|
| 142 |
-
|
| 143 |
-
Submit predictions to the [MedVidBench Leaderboard](https://huggingface.co/spaces/UII-AI/MedVidBench-Leaderboard) to benchmark your own models.
|
| 144 |
-
|
| 145 |
-
## Limitations
|
| 146 |
-
|
| 147 |
-
- **Domain**: Optimized for medical / surgical videos; may not generalize to other domains.
|
| 148 |
-
- **Temporal Resolution**: Best on videos sampled at 0.1–1.0 FPS.
|
| 149 |
-
- **Language**: Trained primarily on English medical terminology.
|
| 150 |
-
- **Video Length**: Optimal for videos of a few minutes; longer videos rely on frame sub-sampling.
|
| 151 |
-
|
| 152 |
-
## License
|
| 153 |
-
|
| 154 |
-
Released under the Apache 2.0 License.
|
| 155 |
-
|
| 156 |
-
## Citation
|
| 157 |
-
|
| 158 |
-
If you use this model or the MedVidBench benchmark, please cite:
|
| 159 |
-
|
| 160 |
-
```bibtex
|
| 161 |
-
@inproceedings{su2026medgrpo,
|
| 162 |
-
title = {{MedGRPO}: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding},
|
| 163 |
-
author = {Su, Yuhao and Choudhuri, Anwesa and Gao, Zhongpai and Planche, Benjamin and
|
| 164 |
-
Nguyen, Van Nguyen and Zheng, Meng and Shen, Yuhan and Innanje, Arun and
|
| 165 |
-
Chen, Terrence and Elhamifar, Ehsan and Wu, Ziyan},
|
| 166 |
-
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
|
| 167 |
-
year = {2026}
|
| 168 |
-
}
|
| 169 |
-
```
|
| 170 |
-
|
| 171 |
-
## Acknowledgments
|
| 172 |
-
|
| 173 |
-
- Base model: [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) by Alibaba Cloud.
|
| 174 |
-
- Training framework: [EasyR1](https://github.com/hiyouga/EasyR1) (built on [verl](https://github.com/volcengine/verl)).
|
| 175 |
-
|
| 176 |
-
## Contact
|
| 177 |
-
|
| 178 |
-
Open an issue on the [GitHub repository](https://github.com/UII-AI/MedGRPO-Code).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/added_tokens.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/chat_template.jinja
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/config.json
DELETED
|
@@ -1,132 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"attention_dropout": 0.0,
|
| 6 |
-
"bos_token_id": 151643,
|
| 7 |
-
"dtype": "float32",
|
| 8 |
-
"eos_token_id": 151645,
|
| 9 |
-
"hidden_act": "silu",
|
| 10 |
-
"hidden_size": 3584,
|
| 11 |
-
"image_token_id": 151655,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 18944,
|
| 14 |
-
"max_position_embeddings": 128000,
|
| 15 |
-
"max_window_layers": 28,
|
| 16 |
-
"model_type": "qwen2_5_vl",
|
| 17 |
-
"num_attention_heads": 28,
|
| 18 |
-
"num_hidden_layers": 28,
|
| 19 |
-
"num_key_value_heads": 4,
|
| 20 |
-
"rms_norm_eps": 1e-06,
|
| 21 |
-
"rope_scaling": {
|
| 22 |
-
"mrope_section": [
|
| 23 |
-
16,
|
| 24 |
-
24,
|
| 25 |
-
24
|
| 26 |
-
],
|
| 27 |
-
"rope_type": "default",
|
| 28 |
-
"type": "default"
|
| 29 |
-
},
|
| 30 |
-
"rope_theta": 1000000.0,
|
| 31 |
-
"sliding_window": 32768,
|
| 32 |
-
"text_config": {
|
| 33 |
-
"_name_or_path": "/root/code/Qwen2.5-VL/qwen-vl-finetune/fine_tuned_models/qwen2.5vl-7b-medvideo_08_18_baseline",
|
| 34 |
-
"architectures": [
|
| 35 |
-
"Qwen2_5_VLForConditionalGeneration"
|
| 36 |
-
],
|
| 37 |
-
"attention_dropout": 0.0,
|
| 38 |
-
"dtype": "float32",
|
| 39 |
-
"eos_token_id": 151645,
|
| 40 |
-
"hidden_act": "silu",
|
| 41 |
-
"hidden_size": 3584,
|
| 42 |
-
"initializer_range": 0.02,
|
| 43 |
-
"intermediate_size": 18944,
|
| 44 |
-
"layer_types": [
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"full_attention",
|
| 54 |
-
"full_attention",
|
| 55 |
-
"full_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"full_attention",
|
| 58 |
-
"full_attention",
|
| 59 |
-
"full_attention",
|
| 60 |
-
"full_attention",
|
| 61 |
-
"full_attention",
|
| 62 |
-
"full_attention",
|
| 63 |
-
"full_attention",
|
| 64 |
-
"full_attention",
|
| 65 |
-
"full_attention",
|
| 66 |
-
"full_attention",
|
| 67 |
-
"full_attention",
|
| 68 |
-
"full_attention",
|
| 69 |
-
"full_attention",
|
| 70 |
-
"full_attention",
|
| 71 |
-
"full_attention",
|
| 72 |
-
"full_attention"
|
| 73 |
-
],
|
| 74 |
-
"max_position_embeddings": 128000,
|
| 75 |
-
"max_window_layers": 28,
|
| 76 |
-
"model_type": "qwen2_5_vl_text",
|
| 77 |
-
"num_attention_heads": 28,
|
| 78 |
-
"num_hidden_layers": 28,
|
| 79 |
-
"num_key_value_heads": 4,
|
| 80 |
-
"pad_token_id": 151643,
|
| 81 |
-
"rms_norm_eps": 1e-06,
|
| 82 |
-
"rope_scaling": {
|
| 83 |
-
"mrope_section": [
|
| 84 |
-
16,
|
| 85 |
-
24,
|
| 86 |
-
24
|
| 87 |
-
],
|
| 88 |
-
"rope_type": "default",
|
| 89 |
-
"type": "default"
|
| 90 |
-
},
|
| 91 |
-
"rope_theta": 1000000.0,
|
| 92 |
-
"sliding_window": null,
|
| 93 |
-
"use_cache": true,
|
| 94 |
-
"use_sliding_window": false,
|
| 95 |
-
"vision_token_id": 151654,
|
| 96 |
-
"vocab_size": 152064
|
| 97 |
-
},
|
| 98 |
-
"tie_word_embeddings": false,
|
| 99 |
-
"transformers_version": "4.57.0",
|
| 100 |
-
"use_cache": true,
|
| 101 |
-
"use_sliding_window": false,
|
| 102 |
-
"video_token_id": 151656,
|
| 103 |
-
"vision_config": {
|
| 104 |
-
"depth": 32,
|
| 105 |
-
"dtype": "float32",
|
| 106 |
-
"fullatt_block_indexes": [
|
| 107 |
-
7,
|
| 108 |
-
15,
|
| 109 |
-
23,
|
| 110 |
-
31
|
| 111 |
-
],
|
| 112 |
-
"hidden_act": "silu",
|
| 113 |
-
"hidden_size": 1280,
|
| 114 |
-
"in_channels": 3,
|
| 115 |
-
"in_chans": 3,
|
| 116 |
-
"initializer_range": 0.02,
|
| 117 |
-
"intermediate_size": 3420,
|
| 118 |
-
"model_type": "qwen2_5_vl",
|
| 119 |
-
"num_heads": 16,
|
| 120 |
-
"out_hidden_size": 3584,
|
| 121 |
-
"patch_size": 14,
|
| 122 |
-
"spatial_merge_size": 2,
|
| 123 |
-
"spatial_patch_size": 14,
|
| 124 |
-
"temporal_patch_size": 2,
|
| 125 |
-
"tokens_per_second": 2,
|
| 126 |
-
"window_size": 112
|
| 127 |
-
},
|
| 128 |
-
"vision_end_token_id": 151653,
|
| 129 |
-
"vision_start_token_id": 151652,
|
| 130 |
-
"vision_token_id": 151654,
|
| 131 |
-
"vocab_size": 152064
|
| 132 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"attn_implementation": "flash_attention_2",
|
| 3 |
-
"bos_token_id": 151643,
|
| 4 |
-
"do_sample": true,
|
| 5 |
-
"eos_token_id": [
|
| 6 |
-
151645,
|
| 7 |
-
151643
|
| 8 |
-
],
|
| 9 |
-
"pad_token_id": 151643,
|
| 10 |
-
"repetition_penalty": 1.05,
|
| 11 |
-
"temperature": 1e-06,
|
| 12 |
-
"transformers_version": "4.57.0"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00001-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1bbbadebc6da0e2d0a3c3100592264beb90a52b2e79d5baad828519f9933fede
|
| 3 |
-
size 4939896344
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00002-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f0274ce542fd2ebd3aaaf7e9f620ce82778872000f31a60fe65af520fef8391e
|
| 3 |
-
size 4942327032
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00003-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4142b79d0531d9c96383001fd1cd896a7ce43578df830a6d808250eae40036c2
|
| 3 |
-
size 4891783496
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model-00004-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7b648c3c60eb7be0a3897ba5037aacd4a9aacf794ccac61f4be682d489e87dda
|
| 3 |
-
size 1810407680
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/model.safetensors.index.json
DELETED
|
@@ -1,737 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_parameters": 8292166656,
|
| 4 |
-
"total_size": 16584333312
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"lm_head.weight": "model-00002-of-00004.safetensors",
|
| 8 |
-
"model.embed_tokens.weight": "model-00003-of-00004.safetensors",
|
| 9 |
-
"model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 10 |
-
"model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 11 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 12 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 14 |
-
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 15 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 17 |
-
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 18 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 19 |
-
"model.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 20 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 21 |
-
"model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 22 |
-
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 23 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
-
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 25 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 26 |
-
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 27 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
-
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 30 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
-
"model.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 32 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 33 |
-
"model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 34 |
-
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
-
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 37 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 38 |
-
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 39 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 41 |
-
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 42 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 43 |
-
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
-
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 46 |
-
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 47 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 48 |
-
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 49 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 50 |
-
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 52 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 53 |
-
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 54 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 55 |
-
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 57 |
-
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 58 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 60 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 62 |
-
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 63 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 64 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
-
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 67 |
-
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 68 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 69 |
-
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 70 |
-
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 71 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 72 |
-
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 73 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 74 |
-
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 75 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 76 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 77 |
-
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 79 |
-
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 80 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 81 |
-
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 82 |
-
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 83 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 84 |
-
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 85 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 86 |
-
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 87 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 88 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 89 |
-
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 90 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 91 |
-
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 93 |
-
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 94 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 98 |
-
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 99 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 101 |
-
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 102 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 103 |
-
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 104 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 105 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
-
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
-
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 109 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 110 |
-
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 111 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 113 |
-
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 115 |
-
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 116 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 117 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
-
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
-
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 121 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 122 |
-
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 123 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
-
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 126 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 127 |
-
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 128 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 129 |
-
"model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 130 |
-
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 131 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
-
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 133 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
-
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 135 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
-
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
-
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 140 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
-
"model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 142 |
-
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 145 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
-
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 147 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 149 |
-
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
-
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 152 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
-
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
-
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 157 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
-
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 161 |
-
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 162 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
-
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 164 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
-
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
-
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 167 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
-
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 170 |
-
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
-
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 174 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 175 |
-
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 177 |
-
"model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 178 |
-
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 180 |
-
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 181 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
-
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 183 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
-
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 186 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 187 |
-
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 188 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 189 |
-
"model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 190 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 192 |
-
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 193 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 194 |
-
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 195 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 196 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 197 |
-
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 199 |
-
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 200 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 201 |
-
"model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 202 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 203 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 204 |
-
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 205 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 206 |
-
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 208 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 209 |
-
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 210 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 211 |
-
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 212 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 213 |
-
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
-
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 215 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 216 |
-
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 217 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
-
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 219 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 220 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
-
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 222 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
-
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 224 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 225 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 226 |
-
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 228 |
-
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 229 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 230 |
-
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 232 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 233 |
-
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 235 |
-
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 237 |
-
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
-
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
-
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 241 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 242 |
-
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 243 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 244 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
-
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 246 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 247 |
-
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 248 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 249 |
-
"model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 250 |
-
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
-
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 253 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
-
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 255 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
-
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 258 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
-
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 260 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
-
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 262 |
-
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 263 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 264 |
-
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 265 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
-
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 268 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 269 |
-
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 270 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 271 |
-
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 272 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
-
"model.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 274 |
-
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 275 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
-
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 279 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 281 |
-
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 282 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
-
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
-
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 286 |
-
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 287 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
-
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 290 |
-
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 291 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 292 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
-
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 294 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
-
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
-
"model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 298 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 300 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
-
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 303 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 304 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
-
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 306 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
-
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 308 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 309 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
-
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
-
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 314 |
-
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 315 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 317 |
-
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 318 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
-
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 320 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
-
"model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
-
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 323 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 324 |
-
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
-
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 329 |
-
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 330 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
-
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 332 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 333 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 334 |
-
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 337 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 338 |
-
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 339 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
-
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 342 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
-
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 344 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 345 |
-
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 346 |
-
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 347 |
-
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
-
"visual.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 349 |
-
"visual.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 350 |
-
"visual.blocks.0.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 351 |
-
"visual.blocks.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 352 |
-
"visual.blocks.0.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 353 |
-
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
-
"visual.blocks.0.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 355 |
-
"visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 356 |
-
"visual.blocks.0.norm1.weight": "model-00002-of-00004.safetensors",
|
| 357 |
-
"visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 358 |
-
"visual.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 359 |
-
"visual.blocks.1.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 360 |
-
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 361 |
-
"visual.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 362 |
-
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 363 |
-
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
-
"visual.blocks.1.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 365 |
-
"visual.blocks.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 366 |
-
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 367 |
-
"visual.blocks.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 368 |
-
"visual.blocks.1.norm1.weight": "model-00002-of-00004.safetensors",
|
| 369 |
-
"visual.blocks.1.norm2.weight": "model-00002-of-00004.safetensors",
|
| 370 |
-
"visual.blocks.10.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 371 |
-
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
-
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 373 |
-
"visual.blocks.10.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 374 |
-
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 375 |
-
"visual.blocks.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
-
"visual.blocks.10.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 377 |
-
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
-
"visual.blocks.10.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 379 |
-
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
-
"visual.blocks.10.norm1.weight": "model-00002-of-00004.safetensors",
|
| 381 |
-
"visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 382 |
-
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 383 |
-
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
-
"visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 385 |
-
"visual.blocks.11.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 386 |
-
"visual.blocks.11.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 387 |
-
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 388 |
-
"visual.blocks.11.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 389 |
-
"visual.blocks.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 390 |
-
"visual.blocks.11.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 391 |
-
"visual.blocks.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 392 |
-
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 393 |
-
"visual.blocks.11.norm2.weight": "model-00002-of-00004.safetensors",
|
| 394 |
-
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 395 |
-
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
-
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 397 |
-
"visual.blocks.12.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 398 |
-
"visual.blocks.12.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 399 |
-
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
-
"visual.blocks.12.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 401 |
-
"visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 402 |
-
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 403 |
-
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
-
"visual.blocks.12.norm1.weight": "model-00003-of-00004.safetensors",
|
| 405 |
-
"visual.blocks.12.norm2.weight": "model-00003-of-00004.safetensors",
|
| 406 |
-
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
-
"visual.blocks.13.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 408 |
-
"visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 409 |
-
"visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 410 |
-
"visual.blocks.13.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 411 |
-
"visual.blocks.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 412 |
-
"visual.blocks.13.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 413 |
-
"visual.blocks.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 414 |
-
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 415 |
-
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 416 |
-
"visual.blocks.13.norm1.weight": "model-00003-of-00004.safetensors",
|
| 417 |
-
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
-
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 419 |
-
"visual.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 420 |
-
"visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 421 |
-
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 422 |
-
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 423 |
-
"visual.blocks.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 424 |
-
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 425 |
-
"visual.blocks.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 426 |
-
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 427 |
-
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 428 |
-
"visual.blocks.14.norm1.weight": "model-00002-of-00004.safetensors",
|
| 429 |
-
"visual.blocks.14.norm2.weight": "model-00003-of-00004.safetensors",
|
| 430 |
-
"visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 431 |
-
"visual.blocks.15.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
-
"visual.blocks.15.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 433 |
-
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 434 |
-
"visual.blocks.15.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 435 |
-
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 436 |
-
"visual.blocks.15.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 437 |
-
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 438 |
-
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 439 |
-
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 440 |
-
"visual.blocks.15.norm1.weight": "model-00003-of-00004.safetensors",
|
| 441 |
-
"visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
-
"visual.blocks.16.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 443 |
-
"visual.blocks.16.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 444 |
-
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 445 |
-
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 446 |
-
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 447 |
-
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 448 |
-
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 449 |
-
"visual.blocks.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 450 |
-
"visual.blocks.16.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 451 |
-
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 452 |
-
"visual.blocks.16.norm1.weight": "model-00002-of-00004.safetensors",
|
| 453 |
-
"visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
-
"visual.blocks.17.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 455 |
-
"visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 456 |
-
"visual.blocks.17.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 457 |
-
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 458 |
-
"visual.blocks.17.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 459 |
-
"visual.blocks.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 460 |
-
"visual.blocks.17.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 461 |
-
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
-
"visual.blocks.17.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 463 |
-
"visual.blocks.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 464 |
-
"visual.blocks.17.norm1.weight": "model-00002-of-00004.safetensors",
|
| 465 |
-
"visual.blocks.17.norm2.weight": "model-00002-of-00004.safetensors",
|
| 466 |
-
"visual.blocks.18.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 467 |
-
"visual.blocks.18.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 468 |
-
"visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 469 |
-
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 470 |
-
"visual.blocks.18.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 471 |
-
"visual.blocks.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 472 |
-
"visual.blocks.18.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 473 |
-
"visual.blocks.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 474 |
-
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 475 |
-
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 476 |
-
"visual.blocks.18.norm1.weight": "model-00002-of-00004.safetensors",
|
| 477 |
-
"visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
-
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 479 |
-
"visual.blocks.19.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 480 |
-
"visual.blocks.19.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 481 |
-
"visual.blocks.19.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 482 |
-
"visual.blocks.19.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 483 |
-
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 484 |
-
"visual.blocks.19.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 485 |
-
"visual.blocks.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 486 |
-
"visual.blocks.19.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 487 |
-
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 488 |
-
"visual.blocks.19.norm1.weight": "model-00002-of-00004.safetensors",
|
| 489 |
-
"visual.blocks.19.norm2.weight": "model-00002-of-00004.safetensors",
|
| 490 |
-
"visual.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 491 |
-
"visual.blocks.2.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 492 |
-
"visual.blocks.2.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 493 |
-
"visual.blocks.2.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 494 |
-
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 495 |
-
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 496 |
-
"visual.blocks.2.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 497 |
-
"visual.blocks.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 498 |
-
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 499 |
-
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 500 |
-
"visual.blocks.2.norm1.weight": "model-00002-of-00004.safetensors",
|
| 501 |
-
"visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
-
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
-
"visual.blocks.20.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 504 |
-
"visual.blocks.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 505 |
-
"visual.blocks.20.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 506 |
-
"visual.blocks.20.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 507 |
-
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 508 |
-
"visual.blocks.20.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 509 |
-
"visual.blocks.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 510 |
-
"visual.blocks.20.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 511 |
-
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 512 |
-
"visual.blocks.20.norm1.weight": "model-00003-of-00004.safetensors",
|
| 513 |
-
"visual.blocks.20.norm2.weight": "model-00002-of-00004.safetensors",
|
| 514 |
-
"visual.blocks.21.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 515 |
-
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
-
"visual.blocks.21.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 517 |
-
"visual.blocks.21.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 518 |
-
"visual.blocks.21.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 519 |
-
"visual.blocks.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 520 |
-
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 521 |
-
"visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 522 |
-
"visual.blocks.21.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 523 |
-
"visual.blocks.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 524 |
-
"visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 525 |
-
"visual.blocks.21.norm2.weight": "model-00002-of-00004.safetensors",
|
| 526 |
-
"visual.blocks.22.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 527 |
-
"visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 528 |
-
"visual.blocks.22.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 529 |
-
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 530 |
-
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 531 |
-
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 532 |
-
"visual.blocks.22.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 533 |
-
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 534 |
-
"visual.blocks.22.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 535 |
-
"visual.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 536 |
-
"visual.blocks.22.norm1.weight": "model-00003-of-00004.safetensors",
|
| 537 |
-
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
-
"visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 539 |
-
"visual.blocks.23.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 540 |
-
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
-
"visual.blocks.23.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 542 |
-
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 543 |
-
"visual.blocks.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 544 |
-
"visual.blocks.23.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 545 |
-
"visual.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 546 |
-
"visual.blocks.23.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 547 |
-
"visual.blocks.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 548 |
-
"visual.blocks.23.norm1.weight": "model-00002-of-00004.safetensors",
|
| 549 |
-
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
-
"visual.blocks.24.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 551 |
-
"visual.blocks.24.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 552 |
-
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 553 |
-
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 554 |
-
"visual.blocks.24.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 555 |
-
"visual.blocks.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 556 |
-
"visual.blocks.24.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 557 |
-
"visual.blocks.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 558 |
-
"visual.blocks.24.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 559 |
-
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 560 |
-
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 561 |
-
"visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
-
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 563 |
-
"visual.blocks.25.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 564 |
-
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 565 |
-
"visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 566 |
-
"visual.blocks.25.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 567 |
-
"visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 568 |
-
"visual.blocks.25.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 569 |
-
"visual.blocks.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 570 |
-
"visual.blocks.25.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 571 |
-
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 572 |
-
"visual.blocks.25.norm1.weight": "model-00003-of-00004.safetensors",
|
| 573 |
-
"visual.blocks.25.norm2.weight": "model-00003-of-00004.safetensors",
|
| 574 |
-
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 575 |
-
"visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 576 |
-
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 577 |
-
"visual.blocks.26.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 578 |
-
"visual.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 579 |
-
"visual.blocks.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 580 |
-
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 581 |
-
"visual.blocks.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 582 |
-
"visual.blocks.26.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 583 |
-
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 584 |
-
"visual.blocks.26.norm1.weight": "model-00002-of-00004.safetensors",
|
| 585 |
-
"visual.blocks.26.norm2.weight": "model-00003-of-00004.safetensors",
|
| 586 |
-
"visual.blocks.27.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 587 |
-
"visual.blocks.27.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 588 |
-
"visual.blocks.27.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 589 |
-
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 590 |
-
"visual.blocks.27.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 591 |
-
"visual.blocks.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 592 |
-
"visual.blocks.27.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 593 |
-
"visual.blocks.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 594 |
-
"visual.blocks.27.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 595 |
-
"visual.blocks.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 596 |
-
"visual.blocks.27.norm1.weight": "model-00004-of-00004.safetensors",
|
| 597 |
-
"visual.blocks.27.norm2.weight": "model-00002-of-00004.safetensors",
|
| 598 |
-
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
-
"visual.blocks.28.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 600 |
-
"visual.blocks.28.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 601 |
-
"visual.blocks.28.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 602 |
-
"visual.blocks.28.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 603 |
-
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 604 |
-
"visual.blocks.28.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 605 |
-
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 606 |
-
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 607 |
-
"visual.blocks.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 608 |
-
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 609 |
-
"visual.blocks.28.norm2.weight": "model-00003-of-00004.safetensors",
|
| 610 |
-
"visual.blocks.29.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 611 |
-
"visual.blocks.29.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 612 |
-
"visual.blocks.29.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 613 |
-
"visual.blocks.29.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 614 |
-
"visual.blocks.29.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 615 |
-
"visual.blocks.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 616 |
-
"visual.blocks.29.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 617 |
-
"visual.blocks.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 618 |
-
"visual.blocks.29.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 619 |
-
"visual.blocks.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 620 |
-
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 621 |
-
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 622 |
-
"visual.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 623 |
-
"visual.blocks.3.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 624 |
-
"visual.blocks.3.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 625 |
-
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 626 |
-
"visual.blocks.3.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 627 |
-
"visual.blocks.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 628 |
-
"visual.blocks.3.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 629 |
-
"visual.blocks.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 630 |
-
"visual.blocks.3.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 631 |
-
"visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 632 |
-
"visual.blocks.3.norm1.weight": "model-00003-of-00004.safetensors",
|
| 633 |
-
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 634 |
-
"visual.blocks.30.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 635 |
-
"visual.blocks.30.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 636 |
-
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
-
"visual.blocks.30.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 638 |
-
"visual.blocks.30.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 639 |
-
"visual.blocks.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 640 |
-
"visual.blocks.30.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 641 |
-
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 642 |
-
"visual.blocks.30.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 643 |
-
"visual.blocks.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 644 |
-
"visual.blocks.30.norm1.weight": "model-00002-of-00004.safetensors",
|
| 645 |
-
"visual.blocks.30.norm2.weight": "model-00002-of-00004.safetensors",
|
| 646 |
-
"visual.blocks.31.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 647 |
-
"visual.blocks.31.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 648 |
-
"visual.blocks.31.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 649 |
-
"visual.blocks.31.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 650 |
-
"visual.blocks.31.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 651 |
-
"visual.blocks.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 652 |
-
"visual.blocks.31.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 653 |
-
"visual.blocks.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 654 |
-
"visual.blocks.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 655 |
-
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 656 |
-
"visual.blocks.31.norm1.weight": "model-00004-of-00004.safetensors",
|
| 657 |
-
"visual.blocks.31.norm2.weight": "model-00003-of-00004.safetensors",
|
| 658 |
-
"visual.blocks.4.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 659 |
-
"visual.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 660 |
-
"visual.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 661 |
-
"visual.blocks.4.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 662 |
-
"visual.blocks.4.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 663 |
-
"visual.blocks.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 664 |
-
"visual.blocks.4.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 665 |
-
"visual.blocks.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 666 |
-
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 667 |
-
"visual.blocks.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 668 |
-
"visual.blocks.4.norm1.weight": "model-00003-of-00004.safetensors",
|
| 669 |
-
"visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
-
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 671 |
-
"visual.blocks.5.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 672 |
-
"visual.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 673 |
-
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 674 |
-
"visual.blocks.5.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 675 |
-
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 676 |
-
"visual.blocks.5.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 677 |
-
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 678 |
-
"visual.blocks.5.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 679 |
-
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 680 |
-
"visual.blocks.5.norm1.weight": "model-00003-of-00004.safetensors",
|
| 681 |
-
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 682 |
-
"visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 683 |
-
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
-
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
-
"visual.blocks.6.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 686 |
-
"visual.blocks.6.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 687 |
-
"visual.blocks.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 688 |
-
"visual.blocks.6.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 689 |
-
"visual.blocks.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 690 |
-
"visual.blocks.6.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 691 |
-
"visual.blocks.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 692 |
-
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 693 |
-
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
-
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
-
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
-
"visual.blocks.7.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 697 |
-
"visual.blocks.7.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 698 |
-
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 699 |
-
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 700 |
-
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 701 |
-
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
-
"visual.blocks.7.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
| 703 |
-
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 704 |
-
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 705 |
-
"visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
-
"visual.blocks.8.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 707 |
-
"visual.blocks.8.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 708 |
-
"visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 709 |
-
"visual.blocks.8.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 710 |
-
"visual.blocks.8.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 711 |
-
"visual.blocks.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 712 |
-
"visual.blocks.8.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
| 713 |
-
"visual.blocks.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 714 |
-
"visual.blocks.8.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 715 |
-
"visual.blocks.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 716 |
-
"visual.blocks.8.norm1.weight": "model-00003-of-00004.safetensors",
|
| 717 |
-
"visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
-
"visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 719 |
-
"visual.blocks.9.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 720 |
-
"visual.blocks.9.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 721 |
-
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 722 |
-
"visual.blocks.9.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
| 723 |
-
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 724 |
-
"visual.blocks.9.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 725 |
-
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 726 |
-
"visual.blocks.9.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 727 |
-
"visual.blocks.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 728 |
-
"visual.blocks.9.norm1.weight": "model-00003-of-00004.safetensors",
|
| 729 |
-
"visual.blocks.9.norm2.weight": "model-00002-of-00004.safetensors",
|
| 730 |
-
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 731 |
-
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 732 |
-
"visual.merger.mlp.0.weight": "model-00002-of-00004.safetensors",
|
| 733 |
-
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 734 |
-
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 735 |
-
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
| 736 |
-
}
|
| 737 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/preprocessor_config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"crop_size": null,
|
| 3 |
-
"data_format": "channels_first",
|
| 4 |
-
"default_to_square": true,
|
| 5 |
-
"device": null,
|
| 6 |
-
"disable_grouping": null,
|
| 7 |
-
"do_center_crop": null,
|
| 8 |
-
"do_convert_rgb": true,
|
| 9 |
-
"do_normalize": true,
|
| 10 |
-
"do_pad": null,
|
| 11 |
-
"do_rescale": true,
|
| 12 |
-
"do_resize": true,
|
| 13 |
-
"image_mean": [
|
| 14 |
-
0.48145466,
|
| 15 |
-
0.4578275,
|
| 16 |
-
0.40821073
|
| 17 |
-
],
|
| 18 |
-
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
-
"image_std": [
|
| 20 |
-
0.26862954,
|
| 21 |
-
0.26130258,
|
| 22 |
-
0.27577711
|
| 23 |
-
],
|
| 24 |
-
"input_data_format": null,
|
| 25 |
-
"max_pixels": 37632,
|
| 26 |
-
"merge_size": 2,
|
| 27 |
-
"min_pixels": 6272,
|
| 28 |
-
"pad_size": null,
|
| 29 |
-
"patch_size": 14,
|
| 30 |
-
"processor_class": "Qwen2_5_VLProcessor",
|
| 31 |
-
"resample": 3,
|
| 32 |
-
"rescale_factor": 0.00392156862745098,
|
| 33 |
-
"return_tensors": null,
|
| 34 |
-
"size": {
|
| 35 |
-
"longest_edge": 37632,
|
| 36 |
-
"shortest_edge": 6272
|
| 37 |
-
},
|
| 38 |
-
"temporal_patch_size": 2
|
| 39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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": "<|endoftext|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6ae8594f633daa21dc0e04606279856d0ccb8abb64bb7a5a93e72531fb12b9d9
|
| 3 |
-
size 11421890
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/tokenizer_config.json
DELETED
|
@@ -1,210 +0,0 @@
|
|
| 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": 16384,
|
| 203 |
-
"pad_token": "<|endoftext|>",
|
| 204 |
-
"padding_side": "right",
|
| 205 |
-
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
-
"split_special_tokens": false,
|
| 207 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
-
"unk_token": null,
|
| 209 |
-
"use_fast": true
|
| 210 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/video_preprocessor_config.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"crop_size": null,
|
| 3 |
-
"data_format": "channels_first",
|
| 4 |
-
"default_to_square": true,
|
| 5 |
-
"device": null,
|
| 6 |
-
"do_center_crop": null,
|
| 7 |
-
"do_convert_rgb": true,
|
| 8 |
-
"do_normalize": true,
|
| 9 |
-
"do_rescale": true,
|
| 10 |
-
"do_resize": true,
|
| 11 |
-
"do_sample_frames": false,
|
| 12 |
-
"fps": null,
|
| 13 |
-
"image_mean": [
|
| 14 |
-
0.48145466,
|
| 15 |
-
0.4578275,
|
| 16 |
-
0.40821073
|
| 17 |
-
],
|
| 18 |
-
"image_std": [
|
| 19 |
-
0.26862954,
|
| 20 |
-
0.26130258,
|
| 21 |
-
0.27577711
|
| 22 |
-
],
|
| 23 |
-
"input_data_format": null,
|
| 24 |
-
"max_frames": 768,
|
| 25 |
-
"max_pixels": 37632,
|
| 26 |
-
"merge_size": 2,
|
| 27 |
-
"min_frames": 4,
|
| 28 |
-
"min_pixels": 6272,
|
| 29 |
-
"num_frames": null,
|
| 30 |
-
"pad_size": null,
|
| 31 |
-
"patch_size": 14,
|
| 32 |
-
"processor_class": "Qwen2_5_VLProcessor",
|
| 33 |
-
"resample": 3,
|
| 34 |
-
"rescale_factor": 0.00392156862745098,
|
| 35 |
-
"return_metadata": false,
|
| 36 |
-
"size": {
|
| 37 |
-
"longest_edge": 37632,
|
| 38 |
-
"shortest_edge": 6272
|
| 39 |
-
},
|
| 40 |
-
"temporal_patch_size": 2,
|
| 41 |
-
"video_metadata": null,
|
| 42 |
-
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 43 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/vlm/uAI-NEXUS-MedVLM-1.0a-7B-RL/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|