---
base_model:
- Qwen/Qwen3-4B-Thinking-2507
tags:
- text-generation-inference
- transformers
- reasoning
- qwen3
- math
- thinking
- conversational
license: apache-2.0
language:
- en
datasets:
- nvidia/OpenMathReasoning
---
# Qwen3-MATH-R1-4B
## Model Description
This is a fine-tuned version of [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) on parts of the [nvidia/OpenMathReasoning](https://huggingface.co/datasets/nvidia/OpenMathReasoning) dataset which was used to win the [AIMO](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/leaderboard) (AI Mathematical Olympiad) challenge!
- **recommended settings for instruct inference:** temperature = 0.7, top_p = 0.8, top_k = 20
- **For reasoning chat based inference :** temperature = 0.6, top_p = 0.95, top_k = 20
- **License :** apache-2.0
- **Finetuned from model :** Qwen/Qwen3-4B-Thinking-2507