How to use sayed0am/gte-multilingual-base-m2v-768 with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("sayed0am/gte-multilingual-base-m2v-768") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape)
How to use sayed0am/gte-multilingual-base-m2v-768 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sayed0am/gte-multilingual-base-m2v-768") 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/sayed0am/gte-multilingual-base-m2v-768/resolve/main/tokenizer.json
hf download hf://sayed0am/gte-multilingual-base-m2v-768/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/sayed0am/gte-multilingual-base-m2v-768/resolve/main/tokenizer.json
