Qwen3-Math-Reasoning-LoRA
A LoRA fine-tuned version of Qwen3-0.6B, trained on a math reasoning dataset (NVIDIA Math) to improve step-by-step problem-solving and numerical answer extraction.
Model Details
Base model: Qwen/Qwen3-0.6B
Fine-tuning: LoRA (Low-Rank Adaptation)
Task: Mathematical reasoning (percentages, geometry, arithmetic)
Dataset
nvidia/AceReason-Math
Intended Use
Educational & research purposes
Math tutoring, reasoning and explanation generation
Not intended for high-stakes or safety-critical use.
License: MIT