BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
Paper • 2402.03216 • Published • 7
How to use juampahc/bge-m3-baai-quant-opt with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("juampahc/bge-m3-baai-quant-opt")
sentences = [
"That is a happy person",
"That is a happy dog",
"That is a very happy person",
"Today is a sunny day"
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]For more details please refer to the original github repo: https://github.com/FlagOpen/FlagEmbedding
This is the original model with O2 optimization applied after quantization. Hub
Base model
BAAI/bge-m3