Press Space to continue
Fine-tune Gemma 4 E2B on single GPU to translate Classical Korean
Press Space to continue
Decoding centuries-old text can be a complex challenge. This project shows how to fine-tune Gemma 4 E2B on a single GPU. The model translates Classical Korean to modern text. The accuracy improved from 4% to 80%!
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.