Minimalist Minecraft server for memory-restrictive embedded systems

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Tool to statically recompile N64 games into native executables

Module, Model, and Tensor Serialization/Deserialization

A high-throughput and memory-efficient inference and serving engine for LLMs

Official inference library for Mistral models

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Using LoRa and self-instruct to fine-tune Llama 2 7B to give you tips on Super Smash Bros. Melee

Create Q&A's for a topic of your choice using the Wikipedia API and GPT for study guides, data generation for self-instruct etc