https://github.com/pavansomisetty21/qwen2-vision-finetuning-unsloth---maths-ocr-formulae-extraction-

we finetune unsloth llama model to extract mathematical fomulas in the images with optical character recognition(OCR)
https://github.com/pavansomisetty21/qwen2-vision-finetuning-unsloth---maths-ocr-formulae-extraction-

llama llm maths ocr ocr-recognition optical-character-recognition qwen2 qwen2-vl unsloth vision-language-model vlm

Last synced: 8 months ago
JSON representation

we finetune unsloth llama model to extract mathematical fomulas in the images with optical character recognition(OCR)

• Host: GitHub
• URL: https://github.com/pavansomisetty21/qwen2-vision-finetuning-unsloth---maths-ocr-formulae-extraction-
• Owner: Pavansomisetty21
• License: mit
• Created: 2025-01-02T07:44:53.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2025-01-08T14:05:14.000Z (10 months ago)
• Last Synced: 2025-01-27T18:13:39.461Z (9 months ago)
• Topics: llama, llm, maths, ocr, ocr-recognition, optical-character-recognition, qwen2, qwen2-vl, unsloth, vision-language-model, vlm
• Language: Jupyter Notebook
• Homepage:
• Size: 43 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
we finetune unsloth llama model to extract mathematical fomulaes in the images with optical character recognition(OCR) For that purpose we use Unsloth package

i.e, we extract formulaes in maths from images