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

  • Log In
  • Sign Up

RUCAIBox
/
mvp-multi-task

Text Generation
Transformers
PyTorch
English
mvp
text2text-generation
summarization
conversational
Model card Files Files and versions
xet
Community
1

Instructions to use RUCAIBox/mvp-multi-task with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use RUCAIBox/mvp-multi-task with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="RUCAIBox/mvp-multi-task")
    messages = [
        {"role": "user", "content": "Who are you?"},
    ]
    pipe(messages)
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("RUCAIBox/mvp-multi-task", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use RUCAIBox/mvp-multi-task with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "RUCAIBox/mvp-multi-task"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "RUCAIBox/mvp-multi-task",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
    Use Docker
    docker model run hf.co/RUCAIBox/mvp-multi-task
  • SGLang

    How to use RUCAIBox/mvp-multi-task 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 "RUCAIBox/mvp-multi-task" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "RUCAIBox/mvp-multi-task",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
    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 "RUCAIBox/mvp-multi-task" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "RUCAIBox/mvp-multi-task",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
  • Docker Model Runner

    How to use RUCAIBox/mvp-multi-task with Docker Model Runner:

    docker model run hf.co/RUCAIBox/mvp-multi-task
mvp-multi-task
1.88 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 6 commits
StevenTang's picture
StevenTang
Update README
2462b3c almost 4 years ago
  • .gitattributes
    1.17 kB
    initial commit almost 4 years ago
  • README.md
    5.82 kB
    Update README almost 4 years ago
  • added_tokens.json
    41 Bytes
    Update vocab almost 4 years ago
  • config.json
    956 Bytes
    initial commit almost 4 years ago
  • merges.txt
    456 kB
    initial commit almost 4 years ago
  • pytorch_model.bin

    Detected Pickle imports (3)

    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage",
    • "collections.OrderedDict"

    What is a pickle import?

    1.87 GB
    xet
    initial commit almost 4 years ago
  • tokenizer.json
    2.11 MB
    Update vocab almost 4 years ago
  • tokenizer_config.json
    27 Bytes
    initial commit almost 4 years ago
  • vocab.json
    899 kB
    Update vocab almost 4 years ago