JIA-Lab-research/TGDPO
[ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
This project offers a method to significantly improve the performance of large language models (LLMs) by integrating detailed feedback during their training. It takes existing LLM training data and pre-trained token-level reward models as input, producing an enhanced LLM that generates higher-quality text. This is designed for AI researchers and machine learning engineers who are actively working on fine-tuning and optimizing LLMs.
No commits in the last 6 months.
Use this if you are a researcher or engineer looking to boost the response quality and win rates of your fine-tuned large language models by leveraging token-level guidance.
Not ideal if you are looking for a plug-and-play solution for basic LLM deployment or if you do not have access to significant computational resources (like multiple high-end GPUs).
Stars
10
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JIA-Lab-research/TGDPO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
stair-lab/mlhp
Machine Learning from Human Preferences
princeton-nlp/SimPO
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
uclaml/SPPO
The official implementation of Self-Play Preference Optimization (SPPO)
general-preference/general-preference-model
[ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment...
sail-sg/dice
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards