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

  • Log In
  • Sign Up

bigcode
/
santacoder-ldf

Text Generation
Transformers
PyTorch
gpt2
custom_code
text-generation-inference
Model card Files Files and versions
xet
Community

Instructions to use bigcode/santacoder-ldf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use bigcode/santacoder-ldf with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="bigcode/santacoder-ldf", trust_remote_code=True)
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForCausalLM
    
    tokenizer = AutoTokenizer.from_pretrained("bigcode/santacoder-ldf", trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained("bigcode/santacoder-ldf", trust_remote_code=True)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use bigcode/santacoder-ldf with vLLM:

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

    How to use bigcode/santacoder-ldf 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 "bigcode/santacoder-ldf" \
        --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": "bigcode/santacoder-ldf",
    		"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 "bigcode/santacoder-ldf" \
            --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": "bigcode/santacoder-ldf",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use bigcode/santacoder-ldf with Docker Model Runner:

    docker model run hf.co/bigcode/santacoder-ldf
santacoder-ldf
2.35 GB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 3 commits
Muennighoff's picture
Muennighoff
Update README.md
32d4a3a over 2 years ago
  • .gitattributes
    1.52 kB
    initial commit over 2 years ago
  • README.md
    136 Bytes
    Update README.md over 2 years ago
  • config.json
    948 Bytes
    update models over 2 years ago
  • configuration_gpt2_mq.py
    9.47 kB
    update models over 2 years ago
  • modeling_gpt2_mq.py
    15.1 kB
    update models over 2 years ago
  • pytorch_model.bin

    Detected Pickle imports (4)

    • "torch.ByteStorage",
    • "torch._utils._rebuild_tensor_v2",
    • "collections.OrderedDict",
    • "torch.BFloat16Storage"

    What is a pickle import?

    2.35 GB
    xet
    update models over 2 years ago
  • special_tokens_map.json
    298 Bytes
    update models over 2 years ago
  • tokenizer.json
    2.08 MB
    update models over 2 years ago
  • tokenizer_config.json
    159 Bytes
    update models over 2 years ago