Add `library_name` metadata and GitHub link to model card (#1)
Browse files- Add `library_name` metadata and GitHub link to model card (f4b694dd4dadeaadc3524a781f6459c184c7c0f0)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
|
|
|
| 4 |
tags:
|
| 5 |
- text-generation
|
| 6 |
- math-reasoning
|
|
@@ -8,12 +13,8 @@ tags:
|
|
| 8 |
- RL-GRPO
|
| 9 |
- research-paper
|
| 10 |
- qwen
|
| 11 |
-
base_model: qwen3-14b
|
| 12 |
-
datasets:
|
| 13 |
-
- math
|
| 14 |
-
- reasoning
|
| 15 |
-
pipeline_tag: text-generation
|
| 16 |
arxiv: 2507.00432
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# UniReason-Qwen3-14B-RL
|
|
@@ -22,6 +23,7 @@ This model is associated with the research paper:
|
|
| 22 |
**"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning"**
|
| 23 |
|
| 24 |
📄 **Paper**: [2507.00432](https://arxiv.org/abs/2507.00432)
|
|
|
|
| 25 |
|
| 26 |
## Abstract
|
| 27 |
|
|
@@ -29,7 +31,7 @@ Math reasoning has become the poster child of progress in large language models
|
|
| 29 |
|
| 30 |
## Model Description
|
| 31 |
|
| 32 |
-
This model is a **RL-GRPO**-tuned version of qwen3-14b focused on **math-reasoning** capabilities.
|
| 33 |
The model was developed as part of research investigating the transferability of mathematical reasoning skills to general language tasks.
|
| 34 |
|
| 35 |
### Key Research Questions Addressed:
|
|
@@ -126,7 +128,7 @@ If you use this model in your research, please cite both the model and the assoc
|
|
| 126 |
```bibtex
|
| 127 |
@article{math_reasoning_transfer_2025,
|
| 128 |
title={Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning},
|
| 129 |
-
author={Maggie Huan and Yuetai Li and Tuney Zheng and Xiaoyu Xu and Seungone
|
| 130 |
journal={arXiv preprint arXiv:2507.00432},
|
| 131 |
year={2025},
|
| 132 |
url={https://arxiv.org/abs/2507.00432}
|
|
@@ -146,4 +148,4 @@ This work builds upon the research presented in "Does Math Reasoning Improve Gen
|
|
| 146 |
|
| 147 |
---
|
| 148 |
|
| 149 |
-
*Model uploaded on 2025-07-03*
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: qwen3-14b
|
| 3 |
+
datasets:
|
| 4 |
+
- math
|
| 5 |
+
- reasoning
|
| 6 |
language: en
|
| 7 |
license: apache-2.0
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
tags:
|
| 10 |
- text-generation
|
| 11 |
- math-reasoning
|
|
|
|
| 13 |
- RL-GRPO
|
| 14 |
- research-paper
|
| 15 |
- qwen
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
arxiv: 2507.00432
|
| 17 |
+
library_name: transformers
|
| 18 |
---
|
| 19 |
|
| 20 |
# UniReason-Qwen3-14B-RL
|
|
|
|
| 23 |
**"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning"**
|
| 24 |
|
| 25 |
📄 **Paper**: [2507.00432](https://arxiv.org/abs/2507.00432)
|
| 26 |
+
💻 **Code**: [https://github.com/ReasoningTransfer/Transferability-of-LLM-Reasoning](https://github.com/ReasoningTransfer/Transferability-of-LLM-Reasoning)
|
| 27 |
|
| 28 |
## Abstract
|
| 29 |
|
|
|
|
| 31 |
|
| 32 |
## Model Description
|
| 33 |
|
| 34 |
+
This model is a **RL-GRPO**-tuned version of qwen3-14b focused on **math-reasoning** capabilities.
|
| 35 |
The model was developed as part of research investigating the transferability of mathematical reasoning skills to general language tasks.
|
| 36 |
|
| 37 |
### Key Research Questions Addressed:
|
|
|
|
| 128 |
```bibtex
|
| 129 |
@article{math_reasoning_transfer_2025,
|
| 130 |
title={Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning},
|
| 131 |
+
author={Maggie Huan and Yuetai Li and Tuney Zheng and Xiaoyu Xu and Kim, Seungone and Du, Minxin and Poovendran, Radha and Neubig, Graham and Yue, Xiang},
|
| 132 |
journal={arXiv preprint arXiv:2507.00432},
|
| 133 |
year={2025},
|
| 134 |
url={https://arxiv.org/abs/2507.00432}
|
|
|
|
| 148 |
|
| 149 |
---
|
| 150 |
|
| 151 |
+
*Model uploaded on 2025-07-03*
|