OpenRLHF vs LLMs-from-scratch

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

OpenRLHFLLMs-from-scratch
TaglineAn Easy-to-use, Scalable and High-performance Agentic RL Framework based on RayImplement a ChatGPT-like LLM in PyTorch from scratch
Stars9.8k99k
Forks98115k
Open issues3424
LanguagePythonJupyter Notebook
LicenseApache-2.0Other
Last pushedJul 6, 2026Jun 2, 2026
CategoriesModel Training, Developer ToolsModel Training, LLM Frameworks

OpenRLHF

OpenRLHF is an open-source framework for reinforcement learning from human feedback. It combines Ray and vLLM distributed architecture with a unified agent-based design paradigm, offering high performance and scalability.

Python

LLMs-from-scratch

Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.

Jupyter Notebook