Home / 🧱 AI Foundation Stack / 🏋️ Training / Fine-tuning

shlokchorge/Fine-Tuning-QWEN2vl

Fine-tuned Qwen2-VL-7B for LaTeX OCR using LoRA and Unsloth on the LaTeX OCR dataset. Built augmentation pipeline (rotation, noise, contrast jitter), ran LoRA rank sweep (r=8/16/32), and evaluated across CER, Token F1, BLEU-4, and Exact Match. Deployed as a Gradio Space with live metric computation.