How to use kiel2/Kiel-2-Vector with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("kiel2/Kiel-2-Vector") sentences = [ "Name a style of hot yoga.", "Bikram.", "Tallahassee is the capital of Florida", "I want a redhead woman with tattoos and big boobs and a big ass" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
https://huggingface.co/kiel2/Kiel-2-Vector/resolve/main/tokenizer.json
hf download hf://kiel2/Kiel-2-Vector/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/kiel2/Kiel-2-Vector/resolve/main/tokenizer.json
