Mockingbird: A RAG-Focused LLM(vectara.com)
vectara.com
Mockingbird: A RAG-Focused LLM
https://vectara.com/blog/mockingbird-a-rag-and-structured-output-focused-llm/
2 comments
This rocks! An LLM tailored for RAG.
https://vectara.com/blog/mockingbird-a-rag-and-structured-output-focused-llm/
At <10B parameters it's an LLM trained to provide optimal results for RAG and structured outputs. Although significantly smaller (and thus faster) than GPT-4 or Gemini-1.5 Pro, it performs at a comparable level for generation, citations, and structured outputs.