A comprehensive collection of process reward models.

AllenAI's post-training codebase

Textbook on reinforcement learning from human feedback

Democratizing Reinforcement Learning for LLMs

Clash 下载|持续收藏Clash版本|2026年1月更新

2026年1月更新，百度网盘(百度云)不限速工具分享。

南科大tis选课系统抢课脚本 操作简单 功能稳定 效率可观

NewHookVip

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

verl: Volcano Engine Reinforcement Learning for LLMs

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

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

多模态 MM +Chat 合集

🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

🎥 Command line media player

大模型基础: 一文了解大模型基础知识

Reverse Engineering: Decompiling Binary Code with Large Language Models

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Official Repo for Open-Reasoner-Zero

Curated list of datasets and tools for post-training.

Summarize existing representative LLMs text datasets.

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

This is the repository for the Tool Learning survey.

Fully open reproduction of DeepSeek-R1

Synthetic data curation for post-training and structured data extraction

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DataComp for Language Models