mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-02 02:41:00 +00:00

History

Daniel Kleine 99058c3d07 minor fixes (#248 )

* removed duplicated numpy req

* labels to array

* autopep8 NBs

2024-06-26 08:52:51 -05:00

minor fixes (#246 )

2024-06-25 17:30:30 -05:00

minor fixes (#235 )

2024-06-21 08:40:54 -05:00

minor fixes (#248 )

2024-06-26 08:52:51 -05:00

Update README.md

2024-06-23 08:25:01 -05:00

minor fixes (#246 )

2024-06-25 17:30:30 -05:00

README.md

2024-06-23 21:48:25 -05:00

Chapter 7: Finetuning to Follow Instructions

Main Chapter Code

02_dataset-utilities contains utility code that can be used for preparing an instruction dataset.
03_model-evaluation contains utility code for evaluating instruction responses using a local Llama 3 model and the GPT-4 API.
04_preference-tuning-with-dpo implements code for preference finetuning with DPO (in progress)
05_dataset-generation contains code to generate synthetic datasets for instruction finetuning