Hugging Face's logo

BooMarshmello
/
Qwen2.5-VL-OCR-3B-Instruct

Safetensors
qwen2_5_vl
Model card Files Community
Qwen2.5-VL-OCR-3B-Instruct / README.md
BooMarshmello's picture
BooMarshmello
Update README.md
12c6d41 verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
license: other
license_name: qwen
license_link: LICENSE
datasets:
  - linxy/LaTeX_OCR
  - OleehyO/latex-formulas
metrics:
  - cer
base_model:
  - Qwen/Qwen2.5-VL-3B-Instruct

Model Card for Model ID

summary

This is a finetuned version of Qwen2.5-VL-3B-Instruct, focusing on the task img2latex.

The model is finetuned on the dataset OleehyO/latex-formulas with 2 epochs to enhance latex ocr capability, and one epoch on linxy/LaTeX-OCR to regulate the model's output.

This work is inspired by prithivMLmods/Qwen2-VL-OCR-2B-Instruct.

evaluation

model metric value
prithivMLmods/Qwen2-VL-OCR-2B-Instruct (bf16) rouge-l: f1-score 0.88
CER 0.24
etherealgemini/Qwen2_5-VL-OCR-3B-Instruct (bf16) rouge-l: f1-score 0.91
CER 0.21

The improvement probably comes from:

  1. model's upgrade, for sure...?
  2. larger dataset: 100K -> 550K

There is an even MUCH larger dataset OleehyO/latex-formulas-80M, but my computing resources are limited.