PyPI page
Home page
Author:
Daoyuan Li
License:
MIT
Summary:
Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract and a two-phase Train→Nudge schedule (silver-medal NVIDIA Nemotron reasoning recipe).
Latest version:
0.1.0
Required dependencies:
numpy
|
pandas
|
pyyaml
Optional dependencies:
accelerate
|
datasets
|
pandas
|
peft
|
pytest
|
torch
|
transformers
|
trl
Downloads last day:
9
Downloads last week:
23
Downloads last month:
146