Sajad Norouzi comments

Results 14 comments of


                                            Sajad Norouzi

thread '<unnamed>' panicked at /home/runner/work/tokenizers/tokenizers/tokenizers/src/tokenizer/added_vocabulary.rs:428:22: AddedVocabulary bad split

I'm facing this error too

Add Kohya fix to SD pipeline for high resolution generation

You mean moving the new pipeline to examples/community folder? how about unet_2d_condition_high_res?

Kohya Hires fix

Hey, I'll work on this.

Kohya Hires fix

I'm planning to open the PR this weekend. If you think you can finish it up sooner, feel free to go ahead.

Kohya Hires fix

I need 1 or 2 days more, sorry about the delay.

Kohya Hires fix

Hi, I reproduced the results on SD model (I don't have enough GPU memory for SDXL). Here are some examples with a resolution of 1000x1600: prompt: "a dog sitting on...

XGBoost training failed with xgboost.core.XGBoostError error

any update on this? I'm seeing the same error.

Number on Django different from what paper reported

and same point about WikiSQL

training script

Hi Isaam, The model is trained using maximum likelihood, so the training script is what we have in the density estimation of the readme and I'll state it below again:...

Kohya Hires fix

@Depfek6 I guess you're using the code snippet from a thread above, in the final commit I renamed `layer_num` to `block_num`. I think if you just do the same renaming...