Instructions to use microsoft/biogpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/biogpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/biogpt")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt") model = AutoModelForCausalLM.from_pretrained("microsoft/biogpt") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/biogpt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/biogpt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/biogpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/biogpt
- SGLang
How to use microsoft/biogpt 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 "microsoft/biogpt" \ --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": "microsoft/biogpt", "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 "microsoft/biogpt" \ --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": "microsoft/biogpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/biogpt with Docker Model Runner:
docker model run hf.co/microsoft/biogpt
Embeddings
Would there be a way to release the embedding model?
Could you clarify? You can get embeddings from this model directly using the AutoModel API.
Hello , are we able take a model trained for text generation(BioGPT) and use it to produce embeddings that make sense, without further training? Are these generated embeddings can be used and have a meaning?
I tried to use biogpt to generate embeddings and perform similarity to find matches but its accuracy is very low as compare to models trained on self-alignment task for biomedical entities. I used this model to generate embeddings like any model using sentence transform code. Can we use this model for embedding at all? Can someone shed light if they managed to use it?