Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

openbmb
/
cpm-bee-10b

Text Generation
Transformers
PyTorch
English
Chinese
cpmbee
feature-extraction
custom_code
Model card Files Files and versions
xet
Community
9

Instructions to use openbmb/cpm-bee-10b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use openbmb/cpm-bee-10b with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="openbmb/cpm-bee-10b", trust_remote_code=True)
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("openbmb/cpm-bee-10b", trust_remote_code=True, dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use openbmb/cpm-bee-10b with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "openbmb/cpm-bee-10b"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "openbmb/cpm-bee-10b",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/openbmb/cpm-bee-10b
  • SGLang

    How to use openbmb/cpm-bee-10b 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 "openbmb/cpm-bee-10b" \
        --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": "openbmb/cpm-bee-10b",
    		"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 "openbmb/cpm-bee-10b" \
            --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": "openbmb/cpm-bee-10b",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use openbmb/cpm-bee-10b with Docker Model Runner:

    docker model run hf.co/openbmb/cpm-bee-10b
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Adding `safetensors` variant of this model

#9 opened over 1 year ago by
SFconvertbot

Error loading model or tokenizer: 'CpmBeeTokenizer' object has no attribute 'encoder'

#8 opened over 1 year ago by
fragrantly

how does the function ```prepare_for_finetune``` work?

2
#7 opened over 2 years ago by
timaos

Compatible with ooba?

#6 opened almost 3 years ago by
BBLL3456

'<' has been replaced with '<<', but the tokenizer still reported an error

1
#5 opened almost 3 years ago by
qizhao

Add support for return_dict_in_generate

#4 opened almost 3 years ago by
Lockee

Error while running it with huggingface transformers

1
#3 opened almost 3 years ago by
zcpp

No such file or directory: 'path/to/checkpoint.pt'

1
#2 opened almost 3 years ago by
mycat

Unrecognized model in openbmb/cpm-bee-10b. Should have a `model_type` key in its config.json

4
#1 opened almost 3 years ago by
hendrydong
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs