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

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

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。👩‍🎓👨‍🎓

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

LangChain 的中文入门教程

Robust recipes to align language models with human and AI preferences

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

基于Eigen运算库的深度学习框架(支持CUDA加速)

autograd mir and CUDA library for dynamic neural networks in D.

Tensors and differentiable operations (like TensorFlow) in Rust

A PyTorch implementation of Learning to learn by gradient descent by gradient descent

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Open-Sora: Democratizing Efficient Video Production for All

A Hearthstone AI based on Monte Carlo tree search and neural nets written in modern C++.

Multi-Agent Reinforcement Learning (MARL) papers

📚 List of Top-tier Conference Papers on Reinforcement Learning (RL)，including: NeurIPS, ICML, AAAI, IJCAI, AAMAS, ICLR, ICRA, etc.

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Python Implementation of Reinforcement Learning: An Introduction

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

a Fine-tuned LLaMA that is Good at Arithmetic Tasks

DSPy: The framework for programming—not prompting—foundation models

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

Deep learning at the speed of light.