How to use PeytonT/1m-paper-embedding-model with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("allenai/scibert_scivocab_uncased") model = PeftModel.from_pretrained(base_model, "PeytonT/1m-paper-embedding-model")
How to use PeytonT/1m-paper-embedding-model with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("PeytonT/1m-paper-embedding-model") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]
https://huggingface.co/PeytonT/1m-paper-embedding-model/resolve/main/tokenizer.json
hf download hf://PeytonT/1m-paper-embedding-model/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/PeytonT/1m-paper-embedding-model/resolve/main/tokenizer.json
