|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- nvidia/AceReason-Math |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- Qwen/Qwen3-0.6B |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- maths |
|
|
- reasoning |
|
|
- qwen |
|
|
library_name: transformers |
|
|
--- |
|
|
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 |
