Feature Extraction
sentence-transformers
Safetensors
Transformers
English
mistral
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use Salesforce/SFR-Embedding-2_R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Salesforce/SFR-Embedding-2_R with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Salesforce/SFR-Embedding-2_R") 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] - Transformers
How to use Salesforce/SFR-Embedding-2_R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Salesforce/SFR-Embedding-2_R")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Salesforce/SFR-Embedding-2_R") model = AutoModel.from_pretrained("Salesforce/SFR-Embedding-2_R", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add proper Sentence Transformers integration (#1)
Verified signature- Add ST-specific configuration files with model.save() (7260df65f5d871b2743995da4cc2342b8f954844) - Also add a transformers tag (c58c14f76620c82c5e8e307c91e8edda2eda2a72) - Following SFR-Embedding-Mistral, set max seq length to 4096 (6cf3bfedf3c5c2d24b7730664985cdc11ffbb154)3388895