# Gpt instead of flan t5 **URL:** \ **Category:** Generative AI with Large Language Models\ **Tags:** week-module-1\ **Created:** [September 17, 2023, 9:24pm UTC](https://community.deeplearning.ai/t/gpt-instead-of-flan-t5/448064 "2023-09-17T21:24:17Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![quantumx](https://avatars.discourse-cdn.com/v4/letter/q/8e7dd6/32.png) [@quantumx](https://community.deeplearning.ai/u/quantumx)\ **Post date:** [September 17, 2023, 9:24pm UTC](https://community.deeplearning.ai/t/gpt-instead-of-flan-t5/448064/1 "2023-09-17T21:24:17Z")
What are the major changes in result if we use gpt ---
**Author:** ![Noor\_Ul\_Huda\_Ajmal](https://avatars.discourse-cdn.com/v4/letter/n/dc4da7/32.png) [@Noor\_Ul\_Huda\_Ajmal](https://community.deeplearning.ai/u/Noor_Ul_Huda_Ajmal)\ **Post date:** [September 18, 2023, 10:20pm UTC](https://community.deeplearning.ai/t/gpt-instead-of-flan-t5/448064/2 "2023-09-18T22:20:31Z")
As GPT is not an encoder-decoder model, which might make it less ideal for generating summaries. In lectures, it has been highlighted that decoder-only models are frequently employed for text generation. Larger decoder-only models have demonstrated robust zero-shot inference capabilities and can excel in various tasks. If you want to assess GPT’s performance in text summarization, you can experiment with a simple approach mentioned on the Hugging Face website, where you append “TL;DR” at the end of the input text to have GPT-2 generate summaries. ---
**Author:** ![fuzi](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/fuzi/32/38455_2.png) [@fuzi](https://community.deeplearning.ai/u/fuzi)\ **Post date:** [September 19, 2023, 2:24pm UTC](https://community.deeplearning.ai/t/gpt-instead-of-flan-t5/448064/3 "2023-09-19T14:24:38Z")
FLAN-T5 is open-source, for this reason here using FLAN-T5 that I think so.