|
# BioLLM2Vec |
|
|
|
This repository contains the model weights for the sentence-to-vector embedding model used in BioLitGPT. The main github repository is at https://github.com/jeffreyzhang92/BioLitGPT. |
|
|
|
Basic usage: |
|
|
|
``` |
|
import torch |
|
from llm2vec import LLM2Vec |
|
model = LLM2Vec.from_pretrained("McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp", |
|
peft_model_name_or_path="YBXL/BioLLM2Vec", |
|
device_map="cuda" if torch.cuda.is_available() else "cpu", |
|
torch_dtype=torch.bfloat16, |
|
revision="main" |
|
) |
|
embedding = model.encode("This is a sentence") |
|
``` |
|
|
|
You will also require access to the Meta LLaMA repository to load the model: https://huggingface.co/meta-llama |
|
``` |
|
from huggingface_hub import login |
|
login("insert_hf_access_token_here") |
|
``` |