YZ
I just want to know if the LAVIS support to finetune the CLIP modal for retrieval task, such as coco or flickr30k dataset? I see that there is nothing about...
In the folder of run_script, only the prompt script about the Refcoco task is available, I want to know if the scripts of other tasks can be released, i.e., SNLI-VE,...
In the function of https://github.com/ExplainableML/ProbVLM/blob/cb69f28b1ab23142a1c671e004b09b5cb5d8a204/src/losses.py#L81, `nn.L1Loss` is inconsistent with Eq.3 in the paper, and Eq. 3 does not include the `nn.L1Loss`. Waiting for your help! @udion @sgk98
Where can I find the three files ve_train.json, ve_dev.json, ve_test.json? From `https://github.com/CpuKnows/SNLI-VE`, only get snli_ve_train.jsonl, snli_ve_dev.jsonl,snli_ve_test.jsonl, which can not be used in this code. I hope you can help me.
Nice Job! We can not find the extracted features for Flickr30k dataset from the link you provided, could you provide it? Thanks!
Is the 4-bit quantization performed only on all layers of the language model? What about vision encoders? No quantification?