LLMs-from-scratch vs FlashRAG
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| LLMs-from-scratch | FlashRAG | |
|---|---|---|
| Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch | FlashRAG: A Python Toolkit for Efficient RAG Research |
| Stars | 99k | 3.5k |
| Forks | 15k | 306 |
| Open issues | 4 | 37 |
| Language | Jupyter Notebook | Python |
| License | Other | MIT |
| Last pushed | Jun 2, 2026 | Apr 10, 2026 |
| Categories | Model Training, LLM Frameworks | LLM Frameworks |
LLMs-from-scratch
Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.
Jupyter Notebook
FlashRAG
FlashRAG is a Python toolkit designed for efficient research in Retrieval Augmented Generation (RAG), offering pre-processed datasets, state-of-the-art algorithms, and an easy-to-use UI.
Python