aletote

Yes, I saw that but still I would like a simple example script.py like the Jupyter Notebook example that includes the loading and saving of the last checkpoint or, like...

> > Yes, I saw that but still I would like a simple example script.py like the Jupyter Notebook example that includes the loading and saving of the last checkpoint...

https://github.com/williamFalcon/minGPT has no trainer.py or train.py

Any news on when this is going to be updated for the main branch? Also, how much faster is it?

(base) ales-MacBook-Pro:code ale$ python3 zero_demo.py Using TensorFlow backend. WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by...

In my experience neither works. When I run the 2 files into one, it treats them as different from each other and generates either one kind or the other. And...

I think a mini-full example without the '...' would help, like for example, this is what I get now when trying to use Functional API: from attn_augconv import augmented_conv2d input_shape=(700,...

I use gpt-2-simple and it has 1024 as max output, is that the case with this model too? I need 4096.