Instructions to use tiny-random/voxtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiny-random/voxtral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tiny-random/voxtral")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("tiny-random/voxtral") model = AutoModelForSpeechSeq2Seq.from_pretrained("tiny-random/voxtral") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tiny-random/voxtral with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tiny-random/voxtral" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tiny-random/voxtral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tiny-random/voxtral
- SGLang
How to use tiny-random/voxtral 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 "tiny-random/voxtral" \ --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": "tiny-random/voxtral", "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 "tiny-random/voxtral" \ --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": "tiny-random/voxtral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tiny-random/voxtral with Docker Model Runner:
docker model run hf.co/tiny-random/voxtral
- Xet hash:
- 42901e5ebea33b91fdfe4e6fe1c6c23e80ff8e061e478aa04bba10addfa8e9a4
- Size of remote file:
- 14.9 MB
- SHA256:
- 4aaf3836c2a5332f029ce85a7a62255c966f47b6797ef81dedd0ade9c862e4a8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.