How to use Muennighoff/SGPT-125M-lasttoken-msmarco-specb with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Muennighoff/SGPT-125M-lasttoken-msmarco-specb") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
https://huggingface.co/Muennighoff/SGPT-125M-lasttoken-msmarco-specb/resolve/f39083140f54e7888046df7e37657f649f40f8e0/tokenizer.json
hf download hf://Muennighoff/SGPT-125M-lasttoken-msmarco-specb@f39083140f54e7888046df7e37657f649f40f8e0/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/Muennighoff/SGPT-125M-lasttoken-msmarco-specb/resolve/f39083140f54e7888046df7e37657f649f40f8e0/tokenizer.json
