AdaMerging

AdaMerging copied to clipboard

Couldn't Reproduce the Code

9

Hello, I attempted to reproduce the code, but encountered some issues. Could you please provide some insights into how much memory is expected to be used? Additionally, I suspect there...

monody1

code to fine-tune on individual tasks

1

Hello. thank you for your work i am interested in fine-tuning individual task. do you have the code for that. thank you

sorobedio

Memory management in training process

10

Hello, Thank you for providing the codes. The training process in provided code calculates the loss for each dataset and aggregates it to update the coefficients. Therefore, the coefficients (lambdas)...

KIM-JAKE

Reproduce EuroSAT Results with ViT-L-14 and ViT-B-32 Models

2

Hello, I am trying to reproduce the results of EuroSAT dataset for the ViT-L-14 and ViT-B-32 models, but I am unable to match the performance reported in the paper. I...

FarisXiong

ModuleNotFoundError: No module named 'open_clip.transformer'

1

When I try to load the model,I meet a problem `ModuleNotFoundError: No module named 'open_clip.transformer'`. Do you have any insight to solve it?

Polly-LYP

Cannot Load Models - Missing VisualTransformer in open_clip

1

Hi. Nice paper. When trying to load a model checkpoint using torch.load(), the following error occurs: `AttributeError: Can't get attribute 'VisualTransformer' on ` It seems that open_clip no longer contains...

aryajalali

[Question] Concerns about gradient propagation through .cuda() operations in CPU→GPU transfers

2

Hello! Thank you for sharing your excellent research and implementation. Your paper and code have been incredibly informative, and I'm learning a great deal about this novel approach to model...

lejelly