xingyaoww

langchain

🦜🔗 Build context-aware reasoning applications

tldr

📚 Collaborative cheatsheets for console commands

llama_index

LlamaIndex is a data framework for your LLM applications

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

gpt4-pdf-chatbot-langchain

GPT4 & LangChain Chatbot for large PDF docs

fauxpilot

FauxPilot - an open-source alternative to GitHub Copilot server

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Awesome-LLM-Robotics

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

t5x

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

RL4LMs

A modular RL library to fine-tune language models to human preferences

code_contests

jellyfish

🪼 a python library for doing approximate and phonetic matching of strings.

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

rpyc

RPyC (Remote Python Call) - A transparent and symmetric RPC library for python

ai2thor

An open-source platform for Visual AI.

PythonProgrammingPuzzles

A Dataset of Python Challenges for AI Research

bigcode-evaluation-harness

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

OpenELM

Evolution Through Large Models

CodeT

paxml

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

procthor

🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses

Implicit-Language-Q-Learning

Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"

DrRepair

[ICML 2020] DrRepair: Learning to Repair Programs from Error Messages

ChatGPT-Assistant

code-bert-score

CodeBERTScore: an automatic metric for code generation, based on BERTScore

bloom-jax-inference