No groma conversation template

FoundationVision / Groma

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

https://groma-mllm.github.io/

Apache License 2.0

483 stars 55 forks source link

Closed Gabesarch closed 2 months ago

Gabesarch commented 2 months ago

Hello,

Thank you for the exciting work and code release!

It seems that eval_lvis requests conv_temp='groma', but conversation.py does not have a 'groma' conv_templates. Which template should we use?

Thanks in advance!

machuofan commented 2 months ago

Sorry, it's a typo here. It should be conv_temp='llava'. Thanks for your feedback.