Instructions to use BelleGroup/BELLE-7B-2M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BelleGroup/BELLE-7B-2M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BelleGroup/BELLE-7B-2M")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("BelleGroup/BELLE-7B-2M") model = AutoModel.from_pretrained("BelleGroup/BELLE-7B-2M") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BelleGroup/BELLE-7B-2M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BelleGroup/BELLE-7B-2M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BelleGroup/BELLE-7B-2M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BelleGroup/BELLE-7B-2M
- SGLang
How to use BelleGroup/BELLE-7B-2M 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 "BelleGroup/BELLE-7B-2M" \ --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": "BelleGroup/BELLE-7B-2M", "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 "BelleGroup/BELLE-7B-2M" \ --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": "BelleGroup/BELLE-7B-2M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BelleGroup/BELLE-7B-2M with Docker Model Runner:
docker model run hf.co/BelleGroup/BELLE-7B-2M
在生成数据时出现超出token问题 请问该怎么解决
WARNING:root:Reducing target length to 224, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 3078 tokens (2854 in your prompt; 224 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 179, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 3033 tokens (2854 in your prompt; 179 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 143, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2997 tokens (2854 in your prompt; 143 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 114, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2968 tokens (2854 in your prompt; 114 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 91, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2945 tokens (2854 in your prompt; 91 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 72, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2926 tokens (2854 in your prompt; 72 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 57, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2911 tokens (2854 in your prompt; 57 for the completion). Please reduce your prompt; or completion length..
WARNING:root:Reducing target length to 45, Retrying...
WARNING:root:OpenAIError: This model's maximum context length is 2049 tokens, however you requested 2899 tokens (2854 in your prompt; 45 for the completion). Please reduce your prompt; or