Instructions to use BELLE-2/BELLE-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BELLE-2/BELLE-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BELLE-2/BELLE-VL", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BELLE-2/BELLE-VL", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BELLE-2/BELLE-VL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BELLE-2/BELLE-VL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BELLE-2/BELLE-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BELLE-2/BELLE-VL
- SGLang
How to use BELLE-2/BELLE-VL with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "BELLE-2/BELLE-VL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BELLE-2/BELLE-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "BELLE-2/BELLE-VL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BELLE-2/BELLE-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BELLE-2/BELLE-VL with Docker Model Runner:
docker model run hf.co/BELLE-2/BELLE-VL
Commit ·
0edc963
1
Parent(s): c49982b
Update README.md
Browse files
README.md
CHANGED
|
@@ -75,6 +75,11 @@ print(response)
|
|
| 75 |
| --Code Reasoning | 57.00 |
|
| 76 |
|
| 77 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
## Citation
|
| 79 |
|
| 80 |
Please cite our paper and github when using our code, data or model.
|
|
|
|
| 75 |
| --Code Reasoning | 57.00 |
|
| 76 |
|
| 77 |
|
| 78 |
+
### 模型不足
|
| 79 |
+
当前模型仅基于开源数据训练,仍存在不足,用户可基于自身需要继续微调强化
|
| 80 |
+
* 目前模型仅支持单张图片的交互
|
| 81 |
+
* 目前在中文ocr场景能力较弱
|
| 82 |
+
|
| 83 |
## Citation
|
| 84 |
|
| 85 |
Please cite our paper and github when using our code, data or model.
|