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.

语言：Jupyter Notebook · GitHub 星标：34 · Fork：1

话题：computer-vision · deep-learning · fine-tuning · gradio · latex · lora · ocr · qwen2

在 GitHub 上查看原仓库