Devin doing QA

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

LLM Workshop by Sourab Mangrulkar

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Domain Adapted Language Modeling Toolkit - E2E RAG

Publication-ready NN-architecture schematics.

Giving Feedback on Interactive Student Programs with Meta-Exploration (NeurIPS 2022)

Code for the paper "Learning Options via Compression" at NeurIPS 2022

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Model API for GALACTICA

Reinforcement Learning Cheat Sheet

Applying RL to grade coding games. NeurIPS 2021.

RoboTHOR Challenge

A fully functional FastAPI application that acts as a marketplace for cleaners and potential cleaning jobs.

A library that scrapes Linkedin for user data

Approximate Nearest Neighbor Search for Sparse Data in Python!

Decoupled Reward-free ExplorAtion and Execution for Meta-reinforcement learning

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Older version of periph, see new version at https://github.com/periph

A toolkit for developing and comparing reinforcement learning algorithms.

IBM Space Tech - Cognitive Autonomous Framework

A modern Python application packaging and distribution tool

Python Driver for the Adafruit SHT31-D Breakout

All Algorithms implemented in Python