verl: Volcano Engine Reinforcement Learning for LLMs

Arena-Hard-Auto: An automatic LLM benchmark.

Fully open reproduction of DeepSeek-R1

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Minimalistic 4D-parallelism distributed training framework for education purpose

Code for BLT research paper

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Automation scripts for setting up a basic development environment.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Tools for merging pretrained large language models.

Mamba SSM architecture

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

LLM101n: Let's build a Storyteller

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/master/instruction_following_eval)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

健康学习到150岁 - 人体系统调优不完全指南

Large World Model -- Modeling Text and Video with Millions Context

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Minimalistic large language model 3D-parallelism training

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

The official implementation of Self-Play Fine-Tuning (SPIN)

Ongoing research training transformer models at scale

Building a quick conversation-based search demo with Lepton AI.

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI