How to use PyxiLab/Pyx-embeds with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("PyxiLab/Pyx-embeds") sentences = [ "search_query: i love autotrain", "search_query: huggingface auto train", "search_query: hugging face auto train", "search_query: i love autotrain" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
https://huggingface.co/PyxiLab/Pyx-embeds/resolve/d0d74c9ac661527bd1c798f792f57bd9e93397d0/tokenizer.json
hf download hf://PyxiLab/Pyx-embeds@d0d74c9ac661527bd1c798f792f57bd9e93397d0/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/PyxiLab/Pyx-embeds/resolve/d0d74c9ac661527bd1c798f792f57bd9e93397d0/tokenizer.json
