Fine-tune DeepSeek-OCR on your own language!
(100% local)
Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow.
DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents.
It is a 3B-parameter vision model that achieves 97% precision while using 10x fewer vision tokens than text-based LLMs.
In fact, you can easily fine-tune it for your specific use case on a single GPU.
I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate.
↳ Base model: 149% character error rate (CER)
↳ Fine-tuned model: 60% CER (57% more accurate)
↳ Training time: 60 steps on a single GPU
Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with.
I've shared the complete guide in the next tweet, which includes the code, notebooks, and environment setup ready to run with a single click.
Everything is 100% open-source!
Spor salonunda çalışan kadının erkeğin 'dostum o hareketi yanlış yapıyorsun' 'o hareket öyle yapılmaz kardeşim' tacizinde bulunan erkeği dövdüğü içerik de Campus Univers Cascade adlı gruba ait.
https://t.co/g4dc5jfSVf
@randomable_ padahal ini bare minimum loh... masih banyak hal lain yg harus dibahas masyarakat bersama DPR dan Pemerintah... kalo ini aja ga bisa dijalanin, gimana kedepannya? sebenernya mereka serius dan niat mau Indonesia maju gak sih? udah dikasih kisi-kisi sama rakyat sendiri malah ngeluh
@BaseBDG Btw bener kan, bakalan speak up kalo udah diri sendiri or orang sekitar yang kena. Kemaren affan dan teman2 yang lain. Besok bisa jadi aku, kamu, kita.