Benjamin Wolff

On page 910 in the code example you see the following code example ```python sentence1 = 'follow the white rabbit neo' sentence2 = 'no one can be told what the...

Dear Daniel, on page 892 there a links to Hugging Face, that are not working anymore (footnotes 165 - 167). Best Benjamin

Dear Daniel, first of all: Great book! I do enjoy reading it! In Figure 8.6 for the input __x__ and the hidden-input __y__ both vectors are transformed with the weight...

Sliding filter, Code snippet in Chapter 3.2.1

1

In Chapter 3.2.1, there is an implementation of sliding the filter over the input: ```python filter = [1, 0, -1] input = [1, 0, 2, -1, 1, 2] output =...

Chapter 3.4.4 - Dimensions after nn.Flattening-Module

1

In Chapter 3.4.4 the code is shown for creating a first CNN. For using nn.Flattening before the last Layer, it says in the code comments (in the book it's point...

Chapter 3.5 - Code indentation error

1

In Chapter 3.5 is the following Code example:  The indentation should not end stop after `w, h = img.shape`.

Chapter 3.4.2 - wrong dimensions in step 3 in figure 3.11

1

In the figure 3.11, that shows convolution in Chapter 3.4.2 the output should have the same dimensions as the original image. Original Image is 7x7 (without padding), however the output...

Update Chapter_1.ipynb

1

Fix loading MNIST_784 dataset as numpy array

Finetune LLaVaNeXT -> ValueError: Image features and image tokens do not match

4

Hi everyone, I tried running the notebook provided here for finetuning LLaVaNeXT: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/LLaVa-NeXT/Fine_tune_LLaVaNeXT_on_a_custom_dataset_(with_PyTorch_Lightning).ipynb However, during training, I encountered the following error: `ValueError: Image features and image tokens do not match:...