🎯
Focusing
-
23:09
(UTC -07:00)
Stars
5
stars
written in C
Clear filter
zanussbaum / gpt4all.cpp
Forked from antimatter15/alpaca.cppLocally run an Assistant-Tuned Chat-Style LLM
fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.
Creating overlays is easy like never before