Daniel Kusuma

[Q] Initialize multiple runs and update them simultaneously

4

Thank you for the never ending support of the API! I have a scenario where I have multiple forward passes in each step. I imagine initialising multiple wandb runs and...

Did anyone happen to learn the model only on VOC2012 dataset? If yes, how is the model performance learned with the default parameters? As for me, it scores only 65%...

Wrapping the ```init``` function inside ```jax.jit```

1

I'm currently doing a runtime analysis of the attention matrix of a transformer. Specifically, I'd like to know how the time complexity behaves w.r.t. to the size of the attention...

Hello thanks again for the conversion work! I noticed something strange when doing batch inference. The generated text is somehow gibberish and I'm not sure if this is due to...

Hi, thanks for the conversion work on the Llama models! I have a question regarding the version of the Llama models. So there are two versions for Llama2 models, the...