madisonmay

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

langchain

🦜🔗 Build context-aware reasoning applications

the-algorithm

Source code for Twitter's Recommendation Algorithm

llama_index

LlamaIndex is a data framework for your LLM applications

babyagi

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

OpenChatKit

surya

OCR, layout analysis, reading order, line detection in 90+ languages

litgpt

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

point-e

Point cloud diffusion for 3D model synthesis

outlines

Structured Text Generation

daytona

The Open Source Dev Environment Manager.

pdfminer.six

Community maintained fork of pdfminer - we fathom PDF

chat-langchain

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

autolabel

Label, clean and enrich text datasets with LLMs.

llm-security

New ways of breaking app-integrated LLMs

lorax

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

FLAN

cramming

Cramming the training of a (BERT-type) language model into limited compute.

LlamaAcademy

A school for camelids

ThoughtSource

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

pal

PaL: Program-Aided Language Models (ICML 2023)

xsdata

Naive XML & JSON Bindings for python

nanodl

A Jax-based library for designing and training transformer models from scratch.

simple-hierarchical-transformer

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT

recursive_llm

Implement recursion using English as the programming language and an LLM as the runtime.

fuxion

Sythetic data generation and normalization functions

Doc2Dict

Code accompanying Doc2Dict paper