ReloJeffrey

Cannot repeat the result Fine-tune the unsupervised pre-trained model in task_adaptation/image_classification

4

For fine-tune the unsupervised pre-trained model, Only the erm reult can be repeat, the co_tuning、bi_tuning accuray is lower than erm

The codebase has provided the training code. But how the reproduce the eval result in the paper 'DeepNet: Scaling Transformers to 1,000 Layers'. Could you please provide the code to...

For datacomp datasets

1

Hi, I was reading through the mlfoundations issue on GitHub and was impressed by the comprehensive dataset you provided. Unfortunately, I'm only able to retrieve about part of datacomp small...