Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature request] Change default text generation model from gpt2 to distilgpt2 #45

Closed
chelouche9 opened this issue Mar 22, 2023 · 2 comments
Labels
enhancement New feature or request

Comments

@chelouche9
Copy link
Contributor

Currently, the default model is gpt2 for text generation. It isn't good and I could not configure it to work correctly.

I used distilgpt2 and it works great out of the box. I want to create a PR and change it. @xenova What do you think?

@chelouche9 chelouche9 added the enhancement New feature or request label Mar 22, 2023
@xenova
Copy link
Owner

xenova commented Mar 22, 2023

The only reason I use gpt2 as the default, is because HF uses it as a default:

https://github.com/huggingface/transformers/blob/5fd4e3c87c685fba2dd9615be62131748a8b5ee3/src/transformers/pipelines/__init__.py#LL280

I think default performance might improve once I add more generation parameters (no repeat n grams, etc.)

@xenova
Copy link
Owner

xenova commented Apr 6, 2023

I think default performance might improve once I add more generation parameters (no repeat n grams, etc.)

We recently added repetition_penalty and no_repeat_ngram_size generation parameters by the way :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants