How to use ukung/semantic-lite-2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import SemanticLiteEmbedder model = SemanticLiteEmbedder.from_pretrained("ukung/semantic-lite-2", device_map="auto")
How to use ukung/semantic-lite-2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ukung/semantic-lite-2") 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/ukung/semantic-lite-2/resolve/main/tokenizer.json
hf download hf://ukung/semantic-lite-2/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/ukung/semantic-lite-2/resolve/main/tokenizer.json
