Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,10 @@ license: mit
|
|
| 3 |
---
|
| 4 |
## Achieving Superior Performance over QwQ-32B Using Only 965 Strategically Curated Samples
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
### Model description
|
| 7 |
Most existing mthods focused on distilling DeepSeek-R1 to improve reasoning ability. However, as far as we know, there is no distilled model could surpass DeepSeek-R1 or QwQ-32B. We introduce NTele-R1-32B-DS , a state-of-the-art mathematical reasoning model that outperforms QwQ-32B across common reasoning benchmarks, including AIME2024/2025, MATH500 and GPQA-Diamond.
|
| 8 |
Notely, NTele-R1-32B-DS is the first that achieves **more than 80/70 in challenging AIME2024/2025**.
|
|
|
|
| 3 |
---
|
| 4 |
## Achieving Superior Performance over QwQ-32B Using Only 965 Strategically Curated Samples
|
| 5 |
|
| 6 |
+
### NTele-R1-32B-V1
|
| 7 |
+
[NTele-R1-32B-V1](https://huggingface.co/ZTE-AIM/NTele-R1-32B-V1) is the continuation of NTele-R1-32B-Preview, and its capabilities can be accessed [here](https://huggingface.co/ZTE-AIM/NTele-R1-32B-V1).
|
| 8 |
+
|
| 9 |
+
|
| 10 |
### Model description
|
| 11 |
Most existing mthods focused on distilling DeepSeek-R1 to improve reasoning ability. However, as far as we know, there is no distilled model could surpass DeepSeek-R1 or QwQ-32B. We introduce NTele-R1-32B-DS , a state-of-the-art mathematical reasoning model that outperforms QwQ-32B across common reasoning benchmarks, including AIME2024/2025, MATH500 and GPQA-Diamond.
|
| 12 |
Notely, NTele-R1-32B-DS is the first that achieves **more than 80/70 in challenging AIME2024/2025**.
|