Standardize benchmark wrapping so the community can wrap various otherwise-incompatible benchmarks uniformly and use them everywhere.

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

A comprehensive framework to test audio comprehension of Large Audio Language Models.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A bibliography and survey of the papers surrounding o1

👨‍💻 An awesome and curated list of best code-LLM for research.

PyTorch native quantization for training and inference

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

🙌 OpenHands: AI-Driven Development

Large Language Model Text Generation Inference

PyTorch native post-training library

xLAM: A Family of Large Action Models to Empower AI Agent Systems

🌎💪 BrowserGym, a Gym environment for web task automation

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

AgentTuning: Enabling Generalized Agent Abilities for LLMs

A library for advanced large language model reasoning

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

An Open-Ended Embodied Agent with Large Language Models

The benchmark to evaluate lifelong reinforcement learning algorithms

This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

JAX-based neural network library