Qingni Wang comments

Results 8 comments of


                                            Qingni Wang

Evaluation on large-scale dataset

I need this too! Do u know how to evaluate on large-scale dataset now?

How to get the whisper, clip, and llama model used by macaw?

Me,too.Any updates?

MultiModality not working, missing weights when initializing?

metoo,anybody know?

> Hi @Michael4933, I use the huggingface link you suggested, but still get .satetensors files. Did you use the llama parameters from https://huggingface.co/yahma/llama-7b-hf/tree/main to generate bin files? Thank you! hi,...

some problem with the combine

> Now I have figured it out. It is very likely that the llama weights you select is not appropriate. My former attempt failed at choose a incorrect .pth file...

Inference inputs multiple modalities other than text at once

> The current model is not trained on joint multimodal data, so it may not perform well at the test time. But I see you run the test on Music-AVQA...

Whether the embedings generated by different modal data has comparability?

> Well, since we didn't train the model on exact pair data, the comparability might not satisfy your expectation at this time. > > Thanks for your attention. But I...