Yakhyokhuja Valikhujaev

I think changing torch.flatten to nn.Flatten() is more flexible.

Azure config param throws error.

1

Hi, thank you for this nice tool. I was using Azure TTS and set some custom config but getting error from the lib packages. I was curious how to tackle...

How to build a custom tokenizer on top of a exsiting Llama 3.2 tokenizer?

7

Hi, I was trying to create a custom tokenizer for a different language which is not included in llama 3.2 tokenizer. I could not find exactly what tokenizer I can...

Alternative version of the repository with fixes and improvements

1

Hi there, I noticed that there are some issues in this repository that haven't received responses yet. I've encountered similar challenges while using the code, and after spending some time...

new reproduced version of this repo with several new backbones and weights of them

1

huge thanks to the owner of this repo. I have reproduced this repo and added several different feature extractors. feature extractors i added: - mobilenetv1_0.25 - mobilenetv1_0.50 - mobilenetv1 -...