Improve model card: Add project page and relevant tags
#2
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,9 +1,13 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- Qwen/Qwen3-14B
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Fast-Math-Qwen3-14B
|
|
@@ -12,6 +16,8 @@ library_name: transformers
|
|
| 12 |
|
| 13 |
**[A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning](https://huggingface.co/papers/2507.08267)**
|
| 14 |
|
|
|
|
|
|
|
| 15 |
This model enables **approx. 65% faster inference on average, with minimal loss in performance**, compared to the base `Qwen3-14B`.
|
| 16 |
|
| 17 |
Technical details can be found in [our github repository](https://github.com/analokmaus/kaggle-aimo2-fast-math-r1/tree/master).
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- Qwen/Qwen3-14B
|
| 4 |
+
library_name: transformers
|
| 5 |
license: apache-2.0
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- mathematics
|
| 9 |
+
- reasoning
|
| 10 |
+
- qwen
|
| 11 |
---
|
| 12 |
|
| 13 |
# Fast-Math-Qwen3-14B
|
|
|
|
| 16 |
|
| 17 |
**[A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning](https://huggingface.co/papers/2507.08267)**
|
| 18 |
|
| 19 |
+
Project page: [https://analokmaus.github.io/kaggle-aimo2-fast-math-r1/](https://analokmaus.github.io/kaggle-aimo2-fast-math-r1/)
|
| 20 |
+
|
| 21 |
This model enables **approx. 65% faster inference on average, with minimal loss in performance**, compared to the base `Qwen3-14B`.
|
| 22 |
|
| 23 |
Technical details can be found in [our github repository](https://github.com/analokmaus/kaggle-aimo2-fast-math-r1/tree/master).
|