yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-09 17:23:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
LLMs-from-scratch/ch04/02_performance-analysis
History
Daniel Kleine dcbdc1d2e5
fixes for code (#206) 
* updated .gitignore

* removed unused GELU import

* fixed model_configs, fixed all tensors on same device

* removed unused tiktoken

* update

* update hparam search

* remove redundant tokenizer argument

---------

Co-authored-by: rasbt <mail@sebastianraschka.com>
2024-06-11 20:59:48 -05:00
..
flops-analysis.ipynb
fixes for code (#206)
2024-06-11 20:59:48 -05:00
previous_chapters.py
Remove leftover instances of self.tokenizer (#201)
2024-06-08 14:57:34 -05:00
README.md
flops analysis
2024-05-23 20:35:41 -05:00
requirements-extra.txt
flops analysis
2024-05-23 20:35:41 -05:00

README.md

Chapter 4: Implementing a GPT Model from Scratch To Generate Text

  • flops-analysis.ipynb analyses the floating point operations per second (FLOPS) of the GPT model(s) implemented in the main chapter.
  • previous_chapters.py is a Python module containing the GPTModel code we implemented in chapter 4 and other code implemented in previous chapters, which we import in the analysis notebook.
  • requirements-extra.txt includes additional Python libraries that need to be installed (via pip install -r requirements-extra.txt.