dgolchin

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.

kraken

extract-expert

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

AllTheWorldAPlay

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

llm-datasets

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

OpenChatML

schedule_free

Schedule-Free Optimization in PyTorch

OpenDevin

🐚 OpenDevin: Code Less, Make More

generate

model-similarity

Simple Model Similarities Analysis

whisper-asr-webservice

OpenAI Whisper ASR Webservice API

self-rewarding-lm-pytorch

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

laserRMT

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

detect-pretrain-code-contamination

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Gemini

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

mergekit

Tools for merging pretrained large language models.

alignment-handbook

Robust recipes to align language models with human and AI preferences

axolotl

Go ahead and axolotl questions

FastChat

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