mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2025-08-08 08:42:56 +00:00
09a3a73f2d
* remove all non-English texts and notice 1. almost 18GB txt left after `is_english` filtered. 2. remove notice use gutenberg's strip_headers 3. after re-run get_data.py, seems all data are under `gutenberg/data/.mirror` folder. * some improvements * update readme --------- Co-authored-by: rasbt <mail@sebastianraschka.com>
Chapter 5: Pretraining on Unlabeled Data
Main Chapter Code
- 01_main-chapter-code contains the main chapter code
Bonus Materials
- 02_alternative_weight_loading contains code to load the GPT model weights from alternative places in case the model weights become unavailable from OpenAI
- 03_bonus_pretraining_on_gutenberg contains code to pretrain the LLM longer on the whole corpus of books from Project Gutenberg
- 04_learning_rate_schedulers contains code implementing a more sophisticated training function including learning rate schedulers and gradient clipping
- 05_bonus_hparam_tuning contains an optional hyperparameter tuning script