Only include tokenizer.json in git-lfs, not *.py, *.md, *.json 8573a0b
Tom Aarsen commited on
How to use Salesforce/SFR-Embedding-Code-2B_R with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Salesforce/SFR-Embedding-Code-2B_R", trust_remote_code=True)
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-Code-2B_R with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="Salesforce/SFR-Embedding-Code-2B_R", trust_remote_code=True) # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Salesforce/SFR-Embedding-Code-2B_R", trust_remote_code=True, dtype="auto")