---
license: apache-2.0
language:
- en
tags:
- mathematics
- math
- sft
- instruction-tuning
- transformers
pipeline_tag: text-generation
pretty_name: MathInstruct v1
library_name: transformers
datasets:
- nvidia/OpenMathInstruct-2
base_model:
- Qwen/Qwen3-0.6B
---

# MathInstruct v1

MathInstruct v1 is a mathematics-focused instruction-tuned language model created by supervised fine-tuning a pretrained base model on curated mathematics training data.

This release aims to improve mathematical instruction following, solution generation, and benchmark performance while maintaining the original capabilities of the base model.


## Results

Benchmark performance compared with the original base model is shown below.

![Benchmark Results](./1.png)

MathInstruct v1 demonstrates improvements across mathematical evaluation tasks and stronger instruction-following behavior.

## Training

MathInstruct v1 was trained using supervised fine-tuning (SFT) on the NVIDIA OpenMath dataset.

The model was trained for **0.1 epoch** to adapt the base model toward stronger mathematical instruction following and solution generation while preserving its original capabilities.

Training setup:

* Supervised fine-tuning (SFT)
* Dataset: NVIDIA OpenMath
* Training duration: 0.1 epoch
* No manual filtering or removal of noisy samples
* Original dataset distribution preserved
* Minimal preprocessing for training compatibility


## Limitations

The model may still generate incorrect reasoning or inaccurate answers. Verify outputs before using them in important scenarios.