search

CG80499 / KAN-GPT-2

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

datasets #3

Open gyunggyung opened 1 month ago

gyunggyung commented 1 month ago

Did you use the dataset below? Can you give me a more detailed explanation of how to proceed with the learning?

https://huggingface.co/datasets/roneneldan/TinyStories/tree/main

CG80499 commented 1 month ago

Yes. You should be able to use transformer.py for the training.

gyunggyung commented 1 month ago

We need it

2024년 5월 22일 (수) 오전 5:41, CG80499 @.***>님이 작성:

Yes. You should be able to use transformer.py for the training.

— Reply to this email directly, view it on GitHub https://github.com/CG80499/KAN-GPT-2/issues/3#issuecomment-2123406526, or unsubscribe https://github.com/notifications/unsubscribe-auth/AGL6VOVRCLZDKSWXW7TUJR3ZDOWORAVCNFSM6AAAAABIBR5PXCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMRTGQYDMNJSGY . You are receiving this because you authored the thread.Message ID: @.***>