Modelpublic

xu2409324124/qwen3-4b-latex-correction-v3-bf16

sourceHugging Facemitupdated 3mo agoView on Hugging Face

0likes9downloads

Model Card

Qwen3 4B LaTeX Correction v3 BF16

This repository contains the full BF16 merged checkpoint for the Qwen3 4B LaTeX correction SFT release.

The model restores noisy, colloquial, or pseudocode-like math descriptions into canonical LaTeX formulas. It is trained to return formula-only output in a strict display dialect: fractions use the standard LaTeX frac command with two braced arguments, matrices use the bmatrix environment, and superscripts/subscripts are braced, for example x_{i} and x^{2}.

Recommended Use

Use this BF16 repository for Transformers-compatible inference, vLLM-compatible conversion, continued fine-tuning, or producing new quantizations.

A local-inference GGUF build is published separately:

—GGUF Q4KM: https://huggingface.co/xu2409324124/qwen3-4b-latex-correction-v3-gguf-q4-k-m

Evaluation

Clean evaluation split: 292 examples.

model	exact accuracy	semantic accuracy	parse coverage
Base Qwen3-4B-Instruct-2507	2.40%	13.36%	36.99%
Qwen3-4B LaTeX Correction LoRA v3	83.22%	98.97%	100.00%

semantic_accuracy is computed by the repository's local LaTeX AST matcher and is the primary metric.

Source

Project and training workflow: https://github.com/2409324124/Qwen-Desktop-Assistant-Classic