Instructions to use deepcs233/VisCoT-13b-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepcs233/VisCoT-13b-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepcs233/VisCoT-13b-224")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("deepcs233/VisCoT-13b-224") model = AutoModelForCausalLM.from_pretrained("deepcs233/VisCoT-13b-224") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use deepcs233/VisCoT-13b-224 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepcs233/VisCoT-13b-224" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepcs233/VisCoT-13b-224", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepcs233/VisCoT-13b-224
- SGLang
How to use deepcs233/VisCoT-13b-224 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 "deepcs233/VisCoT-13b-224" \ --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": "deepcs233/VisCoT-13b-224", "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 "deepcs233/VisCoT-13b-224" \ --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": "deepcs233/VisCoT-13b-224", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepcs233/VisCoT-13b-224 with Docker Model Runner:
docker model run hf.co/deepcs233/VisCoT-13b-224
- Xet hash:
- 837053fbbc749be568c2ba9ee591385736feaaf3dfb3e29abf8c287a5350442a
- Size of remote file:
- 6.14 kB
- SHA256:
- 4b64ac023a67b2e09a9b359e0e4fb7c9fcc22bf1bb6c9d73ac4997fadce804f9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.