yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-01 05:12:56 +00:00
Code Issues Packages Projects Releases Wiki Activity
LLMs-from-scratch/ch06/01_main-chapter-code
History
Sebastian Raschka d1e99f6092
Fix timeout issue related to spam data backup url (#544) 
* Add backup url for Spam Dataset

* import urllib

* fix url

* fix timeout issue
2025-02-20 09:26:23 -06:00
..
ch06.ipynb
Fix timeout issue related to spam data backup url (#544)
2025-02-20 09:26:23 -06:00
exercise-solutions.ipynb
minor markdown fixes (#236)
2024-06-21 13:55:34 -05:00
gpt_class_finetune.py
Fix timeout issue related to spam data backup url (#544)
2025-02-20 09:26:23 -06:00
gpt_download.py
Add backup URL for gpt2 weights (#469)
2025-01-05 11:28:09 -06:00
load-finetuned-model.ipynb
remove redundant code line
2024-10-13 15:58:11 -05:00
previous_chapters.py
fixed num_workers (#229)
2024-06-19 17:36:46 -05:00
README.md
Add missing bullet point
2024-09-21 12:59:12 -05:00
tests.py
Add standalone finetuning and evaluation scripts for chapter 7 (#234)
2024-06-21 05:23:24 -05:00

README.md

Chapter 6: Finetuning for Classification

Main Chapter Code

  • ch06.ipynb contains all the code as it appears in the chapter
  • previous_chapters.py is a Python module that contains the GPT model we coded and trained in previous chapters, alongside many utility functions, which we reuse in this chapter
  • gpt_download.py contains the utility functions for downloading the pretrained GPT model weights
  • exercise-solutions.ipynb contains the exercise solutions for this chapter

Optional Code

  • load-finetuned-model.ipynb is a standalone Jupyter notebook to load the finetuned model we created in this chapter
  • gpt_class_finetune.py is a standalone Python script file with the code that we implemented in ch06.ipynb to finetune the GPT model (you can think of it as a chapter summary)