FlashRank vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| FlashRank | LLMs-from-scratch | |
|---|---|---|
| Tagline | Ultra-lite & Super-fast Python library for re-ranking search results. | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 989 | 99k |
| Forks | 70 | 15k |
| Open issues | 10 | 4 |
| Language | Python | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | Jan 1, 2026 | Jun 2, 2026 |
| Categories | Data & Retrieval | Model Training, LLM Frameworks |
FlashRank
FlashRank is a lightweight, fast library for enhancing existing search and retrieval systems with pairwise or listwise re-ranking techniques based on both cross-encoders and large language models (LLMs).
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