Retrieval and Retrieval-augmented LLMs
A new member of the BGE model series! BGE-M3 stands for Multi-linguality, Multi-granularities (input length up to 8192), and Multi-Functionality (unification of dense, lexical, multi-vec retrieval). It is the first embedding model which supports all three retrieval methods.
For more details please refer to Technical Report and Code.
An effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM by x100 times. We extend the context length of Llama-2-chat-7b from 4K to 400K.
For more details please refer to paper and code
Merge language models (e.g., Llama, bge) to improve the general ability of models. This method can be used to:
Create the first release #131
bge-*-v1.5
:
bge-reranker-*
: cross-encoders that can rerank the top-k retrieved resultsnormalize_embeddings=True
manually when using sentence-transformers.