2 results found Sort:

PotatoSpudowski
fastLLaMa PotatoSpudowski
26
408
mit
11
fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.
c cpp lama python lamacpp
Created 2023-03-21
64 commits to main branch, last one about a year ago
umbertogriffo
rag-chatbot umbertogriffo
54
222
apache-2.0
3
RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.
gpu llm rag llama3 chatbot lamacpp chromadb streamlit vector-database
Created 2023-06-28
190 commits to main branch, last one 17 days ago