VisualQuality-R1-7B 是基于 Qwen2.5-VL-7B-Instruct 微调的视觉质量评估模型,来自论文 VisualQuality-R1,已被 NeurIPS 2025 接收为 spotlight。
该模型是首个基于 RL2R (Reinforcement Learning to Reason) 增强的 NR-IQA 模型,能够通过推理生成质量描述和评分。
| 属性 | 值 |
|---|---|
| 模型类型 | Qwen2_5_VLForConditionalGeneration |
| 参数量 | 8.29 B |
| Hidden Size | 3584 |
| Transformer 层数 | 28 |
| Attention Heads | 28 (GQA, 4 KV heads) |
| Vision Hidden Size | 1280 |
| Vocab Size | 152064 |
| 基础模型 | Qwen2.5-VL-7B-Instruct |
| 依赖项 | 版本要求 | 说明 |
|---|---|---|
| 操作系统 | CentOS 7.6+ / Ubuntu 18.04+ | 支持主流 Linux 发行版 |
| CANN | 5.0.RC2+ | 华为昇腾计算架构 |
| Python | 3.10+ | 推荐 3.10+ |
| PyTorch | 2.0.0+ | 推荐 2.12 |
| torch_npu | 与 PyTorch 版本匹配 | 昇腾 PyTorch 扩展 |
| transformers | >=4.49.0 | Qwen2.5-VL 模型加载 |
| qwen-vl-utils | 最新版 | 视觉信息处理工具 |
# 1) 激活已预装 torch / torch_npu 的 conda 环境
conda activate pt2100
# 2) 安装依赖(使用华为云源)
pip install transformers qwen-vl-utils -i https://repo.huaweicloud.com/repository/pypi/simple
# 3) 验证环境
python -c "
import torch, torch_npu
print('torch:', torch.__version__)
print('torch_npu:', torch_npu.__version__)
print('NPU 可用:', torch.npu.is_available())
"cd /workspace/agent4/VisualQuality-R1-7B-ascend
ls -la /workspace/agent3/TianheWu/VisualQuality-R1-7B/npu-smi info
python -c "import torch; import torch_npu; print('NPU 可用:', torch.npu.is_available())"python inference.py --device npu:0
python inference.py --device npu:0 --max_new_tokens 512conda activate pt2100
cd /workspace/agent4/VisualQuality-R1-7B-ascend
python inference.py --device npu:0实际输出:
============================================================
VisualQuality-R1-7B 昇腾 NPU 推理
============================================================
[Device] npu:0
[Model Path] /workspace/agent3/TianheWu/VisualQuality-R1-7B
[Config]
model_type: qwen2_5_vl
architectures: ['Qwen2_5_VLForConditionalGeneration']
hidden_size: 3584
num_hidden_layers: 28
num_attention_heads: 28
vocab_size: 152064
vision_hidden_size: 1280
[Memory Before Model Load] Allocated: 0.00 GB, Reserved: 0.00 GB
[npu-smi info]
+------------------------------------------------------------------------------------------------+
| npu-smi 25.5.2 Version: 25.5.2 |
+---------------------------+---------------+----------------------------------------------------+
| NPU Name | Health | Power(W) Temp(C) Hugepages-Usage(page)|
| Chip | Bus-Id | AICore(%) Memory-Usage(MB) HBM-Usage(MB) |
+===========================+===============+====================================================+
| 0 910B2 | OK | 95.1 41 0 / 0 |
| 0 | 0000:C1:00.0 | 0 0 / 0 3424 / 65536 |
+===========================+===============+====================================================+
[Loading] VisualQuality-R1-7B model...
[Loading] VisualQuality-R1-7B model from /workspace/agent3/TianheWu/VisualQuality-R1-7B
Tokenizer loaded: vocab_size=151643
Loading weights: 100%|██████████| 729/729 [00:09<00:00, 76.42it/s]
Model loaded: 8.29 B parameters
[Model Loaded] Allocated: 15.45 GB, Reserved: 15.45 GB
[npu-smi info]
+------------------------------------------------------------------------------------------------+
| NPU Name | Health | Power(W) Temp(C) Hugepages-Usage(page)|
| Chip | Bus-Id | AICore(%) Memory-Usage(MB) HBM-Usage(MB) |
+===========================+===============+====================================================+
| 0 910B2 | OK | 95.1 41 0 / 0 |
| 0 | 0000:C1:00.0 | 0 0 / 0 19306/ 65536 |
+========================---+---------------+----------------------------------------------------+
| NPU Chip | Process id | Process name | Process memory(MB) |
+===========================+===============+====================================================+
| 0 0 | 1708858 | python | 15936 |
+===========================+===============+====================================================+
[Running] VisualQuality-R1-7B inference...
[npu-smi info]
+------------------------------------------------------------------------------------------------+
| NPU Name | Health | Power(W) Temp(C) Hugepages-Usage(page)|
| Chip | Bus-Id | AICore(%) Memory-Usage(MB) HBM-Usage(MB) |
+===========================+===============+====================================================+
| 0 910B2 | OK | 113.1 41 0 / 0 |
| 0 | 0000:C1:00.0 | 0 0 / 0 19634/ 65536 |
+===========================+===============+====================================================+
| NPU Chip | Process id | Process name | Process memory(MB) |
+===========================+===============+===============+==========================================|
| 0 0 | 1708858 | python | 16269 |
+===========================+===============+====================================================+
[Results]
Generated text length: 21
Output preview: <answer>0.00</answer>...
[Memory After Inference] Allocated: 15.45 GB, Reserved: 15.64 GB
[Done]| 指标 | 值 |
|---|---|
| 模型参数量 | 8.29 B |
| 推理显存峰值 | ~16 GB |
| 输出长度 | 21 tokens |