dgolchin

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

OpenDevin

🐚 OpenDevin: Code Less, Make More

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

axolotl

Go ahead and axolotl questions

alignment-handbook

Robust recipes to align language models with human and AI preferences

mergekit

Tools for merging pretrained large language models.

whisper-asr-webservice

OpenAI Whisper ASR Webservice API

schedule_free

Schedule-Free Optimization in PyTorch

llm-datasets

High-quality datasets, tools, and concepts for LLM fine-tuning.

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Gemini

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

laserRMT

This is our own implementation of 'Layer Selective Rank Reduction'

OpenChatML

detect-pretrain-code-contamination

kraken

AllTheWorldAPlay

All the world is a play, we are but actors in it.

generate

model-similarity

Simple Model Similarities Analysis

extract-expert

Extract a single expert from a Mixture Of Experts model using slerp interpolation.

Vanguard_L3_70B

Vanguard is an Office 365 Add-in for advanced email scanning to prevent malicous attacks on an enterprise scale

synth

synth. is a framework designed for the generation of synthetic instructions to enhance LLM training.