OSU-NLP-Group / SeeAct

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
https://osu-nlp-group.github.io/SeeAct/
Other
571 stars 69 forks source link

fix typo: 'nase64' -> 'base64' #11

Closed Xiao9905 closed 6 months ago

Xiao9905 commented 7 months ago

There seems a typo in the inference engine. GPTV API calling should use 'base64' rather than 'nase64', or there will be an error in the execution.

cc13qq commented 7 months ago

Very useful! Thanks a lot!

boyugou commented 6 months ago

merged. Thanks for pointing out this typo!