Recently Updated Pages
OmniQuant
Summary OmniQuant (omnidirectionally calibrated quantization) is a quantization technique publish...
llama.cpp
llama.cpp is the most popular backend for inferencing Llama models for single users. Started o...
Airoboros LMoE
Here we experiment w/ getting a local mixture of experts. Released 2023-08-23: https://x.com/jon_...
Apple Silicon Macs
Macs are popular with (non-ML) developers, and the combination of (potentially) large amounts of ...
ChatGPT Code Interpreter
In beta for a several months, OpenAI made the Code Interpreter available to all ChatGPT Plus user...
Replit Models
Replit has trained a very strong 3B parameter code completion foundational model on The Stack. On...
Hardware
Resources on deciding what hardware to use for powering your local LLMs. Relatively maintained r...
Colophon
This site runs on BookStack, a PHP-based Wiki/documentation software. While there are other docum...
Code Evaluation
Running human-eval: https://github.com/abacaj/code-eval