CG80499 / KAN-GPT-2

Training small GPT-2 style models using Kolmogorov-Arnold networks.
87 stars 4 forks source link

Colab example #2

Open AjibolaPy opened 1 month ago

AjibolaPy commented 1 month ago

Is there a colab/jupyter notebook example?

CG80499 commented 1 month ago

No I'm afraid not. Try looking at transformer.py for guidance.