Chapter 7: Instruction and Preference Finetuning

This folder contains utility code that can be used for preparing an instruction dataset.

Install the additional package requirements via:

pip install -r requirements-extra.txt

Finding near duplicates

The find-near-duplicates.py function can be used to identify duplicates and near-duplicates in an instruction dataset. For example,

python find-near-duplicates.py --json_file instruction-examples.json

==================================================
Searching 'instruction' for duplicates ...
==================================================
Duplicate pair found with similarity 0.94:
1. Edit the following sentence to make it more formal.
2. Edit the sentence to make it more formal.

Duplicate pair found with similarity 1.00:
1. Name a dwarf planet in our solar system.
2. Name a dwarf planet in our solar system.

Duplicate pair found with similarity 0.91:
1. Change the sentences from active voice to passive voice.
2. Change the sentence from passive to active voice.



==================================================
Searching 'input' for duplicates ...
==================================================
No duplicates found


==================================================
Searching 'output' for duplicates ...
==================================================
Duplicate pair found with similarity 1.00:
1. One dwarf planet in our solar system is Pluto.
2. One dwarf planet in our solar system is Pluto.

&nbsp You can use the --threshold setting with a value between 0 and 1 to decrease or increase the sensitivity. The default threshold is 0.9.