Efficient Triton Kernels for LLM Training

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

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

Godot Rl support for web to play and use in the browser.

RegularPolygon2D Node for Godot game Engine. Quickly create polygons with equal sides and angles.

Large Language Model Text Generation Inference

⚗️ AI Feedback framework for scalable LLM alignment

A command-line tool for the conversion of 3D model assets on the FBX file format to the glTF file format.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

https://tralexium.itch.io/chippy

Transformers are Sample Efficient World Models

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

Mesh splitting and merging script for Godot

Unity Machine Learning Agents Toolkit

Code and links for trained Atari agents

Public repo for HF blog posts

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Virtual ML.NET 2021 Hackathon Submission