# Week 7 - Transformers & Hugging Face

## Course session

**Explanatory Session Part 1**

Self-attention and multihead attention

**Hugging Face Introduction**

Library and Use of HuggingFace for working with transfomer models

{% embed url="<https://colab.research.google.com/drive/17B8QU2hM8sxmrbvvigq1orH_Angf9qsP?usp=sharing>" %}

**Explanatory Session Part 2**

Transformer Encoder and Positional Encoding

**Explanatory Session Part 3**

Vision Transformer

**Walk-through**

Finetuning Vision Transformer on Kaggle Paddy Dataset

{% embed url="<https://colab.research.google.com/drive/1hRMznfY1zPhR36-Qs2IteU215Zyo2qQL?usp=sharing>" %}

## To-do

😊

Look at current Kaggle competitions and make proposals

😊😊

Go through this excellent site explaining Transformers:&#x20;

{% embed url="<http://jalammar.github.io/illustrated-transformer/>" %}

Do Chapter 1-3 of the HuggingFace NLP course

{% embed url="<https://huggingface.co/learn/nlp-course/chapter1/1>" %}

😊😊😊

{% embed url="<https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial6/Transformers_and_MHAttention.html>" %}

Look closer at the Pytorch module `nn.Transformer` ([documentation](https://pytorch.org/docs/stable/generated/torch.nn.Transformer.html)) and go through a [tutorial](https://pytorch.org/tutorials/beginner/transformer_tutorial.html) on how to use it for next token prediction.

Watch this excellent "Build from Scratch" video from Andrej Karpathy

{% embed url="<https://youtu.be/kCc8FmEb1nY>" %}

{% embed url="<https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial15/Vision_Transformer.html>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://opencampus.gitbook.io/opencampus-machine-learning-program/courses/intermediate-machine-learning/week-7-transformers-and-hugging-face.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.