Vision
Collection
Vision AI models • 2 items • Updated
How to use esalahterus/qwen3.5-4b-latex-ocr with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline
pipe = pipeline("image-to-text", model="esalahterus/qwen3.5-4b-latex-ocr") # Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("esalahterus/qwen3.5-4b-latex-ocr")
model = AutoModelForMultimodalLM.from_pretrained("esalahterus/qwen3.5-4b-latex-ocr", device_map="auto")A fine-tuned Qwen3.5-4B model for converting mathematical expressions from images into LaTeX.
This model is fine-tuned to recognize mathematical expressions from images and generate their corresponding LaTeX representations. It is intended for OCR tasks involving mathematical formulas and scientific documents.
This model is based on:
The model was fine-tuned using Unsloth and the Hugging Face TRL library on a custom mathematical OCR dataset.
Apache-2.0