A curated list of reinforcement learning with human feedback resources (continually updated)

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Train transformer language models with reinforcement learning.

Fully open reproduction of DeepSeek-R1

Simple RL training for reasoning

verl: Volcano Engine Reinforcement Learning for LLMs

Minimal reproduction of DeepSeek R1-Zero

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Papers & Works for large languange models (OpenAI GPT-4, Meta Llama, etc.).

https://hrl.boyuai.com/

Unsupervised text tokenizer for Neural Network-based text generation.

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

🦜🔗 The platform for reliable agents.

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

Segment Anything for Stable Diffusion WebUI

Image to prompt with BLIP and CLIP

Graph Convolutional Networks in PyTorch

Graph Convolution Network for PyTorch

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Implementation of Graph Convolutional Networks in TensorFlow

WebUI extension for ControlNet

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Stable Diffusion web UI

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821