How to use Salesforce/SFR-Embedding-Mistral with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Salesforce/SFR-Embedding-Mistral") 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]
How to use Salesforce/SFR-Embedding-Mistral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Salesforce/SFR-Embedding-Mistral")
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Salesforce/SFR-Embedding-Mistral") model = AutoModel.from_pretrained("Salesforce/SFR-Embedding-Mistral")
Hi,
Could you simply add
with torch.no_grad():
in the example code? Otherwise it takes too much GPU memory as a normal user who simply need these embedings.
· Sign up or log in to comment
