How to use BorisTM/bge-m3-unsupervised_en_ru with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BorisTM/bge-m3-unsupervised_en_ru") sentences = [ "Это счастливый человек", "Это счастливая собака", "Это очень счастливый человек", "Сегодня солнечный день" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
How to use BorisTM/bge-m3-unsupervised_en_ru with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("BorisTM/bge-m3-unsupervised_en_ru") model = AutoModel.from_pretrained("BorisTM/bge-m3-unsupervised_en_ru", device_map="auto")
https://huggingface.co/BorisTM/bge-m3-unsupervised_en_ru/resolve/main/tokenizer.json
hf download hf://BorisTM/bge-m3-unsupervised_en_ru/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/BorisTM/bge-m3-unsupervised_en_ru/resolve/main/tokenizer.json
