UniReason-Qwen3-14B-think-SFT / paper_metadata.json
Ibisbill's picture
Upload paper_metadata.json with huggingface_hub
aeb01b5 verified
{
"paper": {
"title": "Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning",
"arxiv_id": "2507.00432",
"arxiv_url": "https://arxiv.org/abs/2507.00432",
"abstract": "Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting?"
},
"model": {
"name": "UniReason-Qwen3-14B-think-SFT",
"base_model": "Qwen3-14B-Base",
"training_method": "Distill from Qwen3-32B-Instruct (thinking mode) through Reject Sampling",
"task_focus": "math-reasoning",
"upload_date": "2025-07-05T00:53:17.090139"
},
"repository": {
"repo_name": "ReasoningTransferability/UniReason-Qwen3-14B-think-SFT",
"huggingface_url": "https://huggingface.co/ReasoningTransferability/UniReason-Qwen3-14B-think-SFT"
}
}