🆘 Help: PPO Training with HuggingFace Model for Text Summarization using TRL

Sasi_Kiran_Royal · July 4, 2025, 6:39am

Hi everyone ,

I’m trying to train a Hugging Face pretrained model for Telugu text summarization using PPO (Proximal Policy Optimization) with the trl library, but I’m running into some issues.
with PPO config setup and library compatibility issues and training ,
another issue i was facing which is size mismatch .
please help me or give any example

gent.spah · July 4, 2025, 6:55am

Check out the Generative AI for Large Languages course, one of the Labs uses PPO in the training, maybe you can use some of that knowledge.

Topic		Replies	Views
Week3 - I have just completed the course, excited to put my knowledge into practice! Generative AI with Large Language Models week-module-1	2	50	October 15, 2024
Navigating Huggingface Docs Generative AI with Large Language Models week-module-3	1	440	July 16, 2023
Pre-trained model for invoice parser AI Discussions	2	76	January 7, 2023
The uses of Tokenizer Generative AI with Large Language Models week-module-1	1	380	October 2, 2023
Why only Text Summarisation? Generative AI with Large Language Models feedback , week-module-1 , week-module-2 , week-module-3	2	310	February 27, 2024

🆘 Help: PPO Training with HuggingFace Model for Text Summarization using TRL

Related topics