Instructions to use epfl-llm/meditron-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use epfl-llm/meditron-70b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="epfl-llm/meditron-70b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("epfl-llm/meditron-70b") model = AutoModelForCausalLM.from_pretrained("epfl-llm/meditron-70b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use epfl-llm/meditron-70b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "epfl-llm/meditron-70b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "epfl-llm/meditron-70b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/epfl-llm/meditron-70b
- SGLang
How to use epfl-llm/meditron-70b 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 "epfl-llm/meditron-70b" \ --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": "epfl-llm/meditron-70b", "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 "epfl-llm/meditron-70b" \ --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": "epfl-llm/meditron-70b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use epfl-llm/meditron-70b with Docker Model Runner:
docker model run hf.co/epfl-llm/meditron-70b
Inquiry on MEDITRON LLaMA 3 Version Release
significant work in developing large language models for the medical field!
However, I have a small query. I noticed that the MEDITRON version based on LLaMA 3 models, which also supports image processing (according the news), is not available on Hugging Face. While there are news articles about this version (https://the-decoder.com/med-gemini-and-meditron-google-and-meta-present-new-llms-for-medicine/), the model itself does not seem to be accessible for download.
Could you please let us know if this version will be released soon and where it might be available?
Thanks for the work and dedication to improving global access to medical knowledge.