search

bclarkson-code / Tricycle

Autograd to GPT-2 completely from scratch
104 stars 7 forks source link

Train codeparrot #65

Closed bclarkson-code closed 3 months ago

bclarkson-code commented 3 months ago

Completed training script for the codeparrot dataset. train_smol_gpt.py now successfully trains a small language model to produce python code