Instructions to use SDUIRLab/fuzi-mingcha-v1_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SDUIRLab/fuzi-mingcha-v1_0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SDUIRLab/fuzi-mingcha-v1_0", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SDUIRLab/fuzi-mingcha-v1_0", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SDUIRLab/fuzi-mingcha-v1_0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SDUIRLab/fuzi-mingcha-v1_0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SDUIRLab/fuzi-mingcha-v1_0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SDUIRLab/fuzi-mingcha-v1_0
- SGLang
How to use SDUIRLab/fuzi-mingcha-v1_0 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 "SDUIRLab/fuzi-mingcha-v1_0" \ --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": "SDUIRLab/fuzi-mingcha-v1_0", "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 "SDUIRLab/fuzi-mingcha-v1_0" \ --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": "SDUIRLab/fuzi-mingcha-v1_0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SDUIRLab/fuzi-mingcha-v1_0 with Docker Model Runner:
docker model run hf.co/SDUIRLab/fuzi-mingcha-v1_0
ModuleNotFoundError: No module named 'transformers_modules.SDUIRLab.fuzi'
#1
by Leymore - opened
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("SDUIRLab/fuzi.mingcha-v1.0", trust_remote_code=True)
model = AutoModel.from_pretrained("SDUIRLab/fuzi.mingcha-v1.0", trust_remote_code=True).half().cuda()
有如下报错:
ModuleNotFoundError: No module named 'transformers_modules.SDUIRLab.fuzi'
您好,感谢您指出这个报错。
README.md 里路径名有误,改为模型权重具体的路径即可。因为我们是基于 ChatGLM-6B 做了司法增量训练,所以调用方式与 ChatGLM-6B 相同。README.md 里已经做了修改,您可以再尝试一下。