# Finetuing GPT model?
**URL:**
**Author:**  [@moma1820](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmoma1820)%5C
**Post date:** [August 28, 2021, 10:16am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuing-gpt-model%2F9549%2F1 "2021-08-28T10:16:05Z")
Hi does someone know a fine tuning example with the HF trainer API?
Have never fintined a gpt before so any tipis is much appreciated
---
**Author:**  [@fatihbeyhan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffatihbeyhan)%5C
**Post date:** [August 28, 2021, 4:20pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuing-gpt-model%2F9549%2F2 "2021-08-28T16:20:29Z")
I’ve never used GPT models before. However, if they are available on huggingface, I guess fine-tuning it won’t be different than fine-tuning any other model. I use PyTorch Lightning for training and replacing any huggingface models with each other wouldn’t change the process I guess…
---
**Author:**  [@moma1820](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmoma1820)%5C
**Post date:** [August 29, 2021, 2:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuing-gpt-model%2F9549%2F3 "2021-08-29T14:58:34Z")
Thanks for the reply man,
i was just wondering about the hyper paramtres used during the fine tuning stage.
Is there any guide on that?