后训练 / RLHF

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

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Train transformer language models with reinforcement learning.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Robust recipes to align language models with human and AI preferences

Llama3-中文后训练版

LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.

[CVPR' 2026] JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens