Dataset and training code ?

[marson666]

Hi, thanks for you great work about "Promptist: reinforcement learning for automatic prompt optimization".

Will you release the dataset the paper mentioned in the paper and the training code?

[ming1523]

same here. looking forward the release of optimizing prompts for text to image generation

[amritkumar9595]

yup ! me as well ! waiting for the release of promptist code

[dkkim93]

+1 :) The release of the dataset used in the paper will be really helpful! Thank you for the great work!

[donglixp]

@YRdddream

[YRdddream]

We have released the source code of Promptist.

[dkkim93]

Thank you for uploading the Promptist code @YRdddream! The uploaded code is very helpful 👍 I would like to reproduce the results by training Promptist on our server. Would it be possible to additionally share the training dataset (i.e., 360K data in Section 3.1) and the supervised fine-tuned GPT model? Thank you again for your great work!

[YRdddream]

We have released the data at https://drive.google.com/file/d/1EsuYEb9BuinJCdzvQ_gqa_Gu_sTyLWbf/view?usp=drive_link.

[dkkim93]

Perfect! Thank you so much for your quick response :)