🏆 #5,016 overall#1826 of 2,559 in Natural Language Processing

DaoyuanLi2816 /pairjudge

Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.

$ git clone https://github.com/DaoyuanLi2816/pairjudge.git
GitHub social preview for DaoyuanLi2816/pairjudge
Stars
170
170
This week
—
Forks
12
12
Language
Python
License
MIT
Created
Sep 17, 2024
2.2 years old
Last push
Oct 9, 2026

Categories

GitHub topics

More in Natural Language Processing

Natural Language Processing

ymcui/Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

🤖 Language Models
PythonApache-2.0updated Apr 19, 2026
GitHub ↗★ 18.9K⑂ 1.8K
Natural Language Processing

datawhalechina/base-llm

从 NLP 到 LLM 的算法全栈教程,在线阅读地址:https://datawhalechina.github.io/base-llm/

Jupyter Notebookno licenseupdated Sep 30, 2026
GitHub ↗★ 1.1K⑂ 124
Natural Language Processing

Tzohar/PassLLM🔥 active

World's most accurate password guessing AI tool. A PyTorch implementation of PassLLM (USENIX 2025) that leverages PII and LoRA fine-tuning to outperform existing tools by over 45% on consumer hardware.

PythonGPL-3.0updated Nov 6, 2026
GitHub ↗★ 132⑂ 23
Natural Language Processing

bupticybee/FastLoRAChat

Instruct-tune LLaMA on consumer hardware with shareGPT data

🤖 Language Models
Jupyter NotebookApache-2.0updated Apr 20, 2023
GitHub ↗★ 123⑂ 2

Data from GitHub · snapshot Nov 13, 2026