liziniu/GEM
Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)
This project offers an alternative method to train large language models (LLMs) more effectively. By replacing the standard training loss, it helps ensure that the fine-tuned LLMs can generate a wider variety of responses and avoid becoming too specialized or "overfit" to their training data. It's for researchers or engineers who fine-tune LLMs for various applications.
No commits in the last 6 months.
Use this if you are training or fine-tuning large language models and want to improve their ability to generate diverse and high-quality outputs without overfitting.
Not ideal if you are looking for a plug-and-play solution for using LLMs without involvement in their training or fine-tuning process.
Stars
52
Forks
5
Language
Python
License
—
Category
Last pushed
May 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/liziniu/GEM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DaoD/INTERS
This is the repository for our paper "INTERS: Unlocking the Power of Large Language Models in...
declare-lab/instruct-eval
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca...
Haiyang-W/TokenFormer
[ICLR2025 Spotlightš„] Official Implementation of TokenFormer: Rethinking Transformer Scaling...
hkust-nlp/deita
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
kehanlu/DeSTA2
Code and model for ICASSP 2025 Paper "Developing Instruction-Following Speech Language Model...