A project to improve skills of large language models

Scalable RL solution for advanced reasoning of language models

Recipes to scale inference-time compute of open models

The Open Cookbook for Top-Tier Code Large Language Model

Official inference repo for FLUX.1 models

An Open Large Reasoning Model for Real-World Solutions

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

GenRM-CoT: Data release for verification rationales

Grok open release

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

GTP engine and self-play learning in Go

Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).

Retrieval-Augmented Theorem Provers for Lean

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Tools to download and cleanup Common Crawl data

Tools for merging pretrained large language models.

Stat 320 materials

Learning from synthetic data - code and models

Tool for data extraction and interacting with Lean programmatically.

Set-of-Mark Prompting for GPT-4V and LMMs

Official implementations for paper: Anydoor: zero-shot object-level image customization

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.