Hotfix: Disable Idefics-80b-Instruct API in AI_Meme_Generator to Resolve Space Failure

#7
by nnilayy - opened

This PR provides a hotfix for the issue due to which the Space was not operational. By default, the Space is set to use HuggingFaceM4/idefics-80b-instruct as the base model. Both HuggingFaceM4/idefics-80b-instruct and HuggingFaceM4/idefics-9b-instruct are called through the inference API. However, the HuggingFaceM4/idefics-80b-instruct model, being too large at 159GB, was not able to process any queries, leading to the Space being unoperational.

error.png

This hotfix changes the base model to HuggingFaceM4/idefics-9b-instruct, which successfully processes queries through the Inference API without any issues.

nnilayy changed pull request title from fix AI_Meme_Generator to Hotfix: Disable Large Model in AI_Meme_Generator to Resolve Space Failure
nnilayy changed pull request title from Hotfix: Disable Large Model in AI_Meme_Generator to Resolve Space Failure to Hotfix: Disable Idefics-80b-Instruct API in AI_Meme_Generator to Resolve Space Failure
nnilayy changed pull request status to open
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment