OpenRLHF vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| OpenRLHF | LLMs-from-scratch | |
|---|---|---|
| Tagline | An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 9.8k | 99k |
| Forks | 981 | 15k |
| Open issues | 342 | 4 |
| Language | Python | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | Jul 6, 2026 | Jun 2, 2026 |
| Categories | Model Training, Developer Tools | Model 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