A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.

Python bindings for llama.cpp

LLM Chain for answering questions from documents with citations

LangChain + LLama Index for Document Understanding application

Come join the movement to make the world's best open source GPT led by H2O.ai - 100% private chat and document search, no data leaks, Apache 2.0

GPT4 & LangChain Chatbot for large PDF docs

A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

An Artificial Intelligence Automation Platform. AI Instruction management from various providers, has an adaptive memory, and a versatile plugin system with many commands including web browsing. Su…

Port of OpenAI's Whisper model in C/C++

4 bits quantization of LLaMA using GPTQ

A Open Database-GPT Experiment, which based on vicuna-13b and fastchat, meanwhile it use langchain and llama-index for in-context learning and QA

Home of StarCoder: fine-tuning & inference!

Starter App to Build Your Own App to Query Doc Collections with Large Language Models (LLMs) using LlamaIndex, Langchain, OpenAI and more (MIT Licensed)

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

LLM that combines the principles of wizardLM and vicunaLM

A library of data loaders for LLMs made by the community -- to be used with GPT Index and/or LangChain

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

Let ChatGPT teach your own chatbot in hours with a single GPU!

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

Evaluation of the Open-Assistant language models

A framework for the evaluation of autoregressive code generation language models.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Fine-tuning LLaMA to follow instructions within 1 Hour and 1.2M Parameters

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

The current release is only for M1 and M2 macs. We are working on Intel Mac and Windows support. Soon we'll release for all the platforms.

Train transformer language models with reinforcement learning.

Alpaca-LoRA as Chatbot service