sunnweiwei/RankGPT
quality grade D, 48 out of 100Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
- stars
- 669
- stars gained this week
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,474 results
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
An MCP for WireShark (tshark). Empower LLM's with realtime network traffic analysis capability
AI-First Album: Chat with your gallery using plain language! LLM Vision + RAG + Album/Gallery.
The official repository of "ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory".
Distill large CLI outputs into small answers for LLMs and save tokens!
A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
State-of-the-art bilingual open-sourced Math reasoning LLMs.
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
A framework to evaluate the generalization capability of safety alignment for LLMs
Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.
CLI tool to convert GitHub repositories to text files for LLMs
LLM that combines the principles of wizardLM and vicunaLM
🪿 LinGoose is a Go framework for building awesome AI/LLM applications.
Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
The LLM abstraction layer for modern AI agent applications.
Salesforce open-source LLMs with 8k sequence length.
A minimal LLM chat app that runs entirely in your browser
Generate textbook-quality synthetic LLM pretraining data
SkyAGI: Emerging human-behavior simulation capability in LLM
☁️ 구름(KULLM): 고려대학교에서 개발한, 한국어에 특화된 LLM
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
A Gym for Agentic LLMs
24,522 repositories in the index in total.