Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

The python package that returns response of Google Bard through API.

A reverse engineered Python API wrapper for OpenPlayground (nat.dev)

Reverse engineering of Google's Bard API

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

An LLM playground you can run on your laptop

SOTA algorithms for imitation learning (LfD and LfO) - Ranking algorithms for imitation learning (TMLR 2023)

Reflexion: an autonomous agent with dynamic memory and self-reflection

⚡ Building applications with LLMs through composability ⚡

Demonstration of how to leverage Azure OpenAI and Cognitive Search to enable Information Search and Discovery over organizational content

hanabi_learning_environment is a research platform for Hanabi experiments.

Point cloud diffusion for 3D model synthesis

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

Python library for real-time control of a robotic manipulator

Code for the ICLR 2021 paper "A Distributional Approach to Controlled Text Generation"

A grid-world game engine for game AI research

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Robust Speech Recognition via Large-Scale Weak Supervision

Official implementation of VQ-Diffusion

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

🌊 Online machine learning in Python

Contextual bandit benchmarking

Self-Taught Data Science

Modified OpenAI's spinningup to use environments exploiting revealed randomness

Rembg is a tool to remove images background.

Implementation of the transformer architecture in PyTorch, just for fun & educational purposes.

Pytorch implementation of state-of-the-art offline reinforcement learning algorithms.

A benchmark for offline reinforcement learning.