breadbrowser comments

Results 115 comments of


                                            breadbrowser

Gpu vram runs out on colab

> > use kaggle > > @breadbrowser I use kaggle, and I get the same VRAM Problems your dataset is too big. i would use http://textfilesplitter.org/ to put the text...

I always get short chunks of text

same

I always get short chunks of text

whats the max_length and n_embd you trained it with. because the max_length you trained it with is the max max_length for the generation

I always get short chunks of text

or just set batch size to 50

AWS SageMaker Multiple GPU Training Fails

kaggle never has this issue

Train on large textfile

> Hi, I'm trying to train a model from scratch as I want it to generate text in another language (Swedish). My trainingdata is a large collection of novels, about...

MemoryError fine-tuning GPT2(355M) model with small datasets (3MB)

did you change n_embd size. that's most likely the problem. just set it back to 256

> Fine Tuning one not working https://colab.research.google.com/drive/15qBZx5y9rdaQSyWpsreMDnTiZ5IlN0zD?usp=sharing > > I am facing an error > > > TypeError: **init**() got an unexpected keyword argument 'show_progress_bar' > > Solution required at...

train stops

use keggle

train stops

https://www.kaggle.com/code/lostgoldplayer/aitextgen-training-2