GVT
GVT copied to clipboard
TencentARC
Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".
Thanks authors for the insightful work! I want to understand more details about tuning the visual tokenizer. Could you mind explaining about what kind of dataset used in training your...
Good job on the really insightful and useful paper! The quantitative metrics are really useful when working with these models. **Question:** When evaluating the LLava baseline (Table 4 in paper),...
transformers==4.28.0 and salesforce-lavis 1.0.2 conflict。Can you provide the version of lavis？
Hello there, Great work! And similar to [issue](https://github.com/TencentARC/GVT/issues/2), how about performances of [LLaMA-Adapter](https://github.com/ZrrSkywalker/LLaMA-Adapter) V1 & V2 and InstructBLIP available on LAVIS. Thanks!
Hey, do you have a timeline for when you will release the code and pre-trained models?
Metadata
Owner
Metadata
Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".