|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
## Achieving Superior Performance over QwQ-32B Using Only 965 Strategically Curated Samples |
|
|
|
|
|
### NTele-R1-32B-V1 |
|
|
[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). |
|
|
|
|
|
|
|
|
### Model description |
|
|
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. |
|
|
Notely, NTele-R1-32B-DS is the first that achieves **more than 80/70 in challenging AIME2024/2025**. |
|
|
| Model | Trained From | Release Date | AIME2024 | AIME2025 | MATH500 | GPQA-Diamond | |
|
|
|-------|-------|-------|-------|-------|-------|-------| |
|
|
| QwQ-32B | - | 25.3.6 | 76.25 | 67.30 | 94.6 | 63.6 | |
|
|
| DeepSeek-32B-Distill | Qwen2.5-32B-Instruct | 25.1.20 | 64.17 | 55.21 | 89.8 | 62.1 | |
|
|
| Light-R1-32B-DS | DeepSeek-R1-Distill-Qwen-32B | 25.3.12 | 74.79 | 68.54 | 92 | **69.19** | |
|
|
| AReal-boba-SFT-32B | DeepSeek-R1-Distill-Qwen-32B | 25.3.30 | 70.63 | 63.54 | 88.8 | 64.65 | |
|
|
| NTele-R1-32B-DS(ours) | DeepSeek-R1-Distill-Qwen-32B | 25.4.17 | **80.42**| **73.54** | **95.4** | 66.16 | |
|
|
|
|
|
|
|
|
### Data Curation |
|
|
We start from the S1 dataset and conduct the following procedures: |
|
|
1. QwQ-32B as a Better Teacher : |
|
|
- We find that QwQ-32B, with its smoother flow in CoT reasoning, serves as a better teacher compared to DeepSeek-R1. For each question in S1 dataset, we sampled 50 responses from QwQ-32B. |
|
|
2. Focusing on Harder Questions : |
|
|
- We evaluated the correctness of the responses for each question. After that, we filtered out the easier questions with a pass rate exceeding 0.6. |
|
|
3. Diverse Reasoning Paths Break the Limitation of Distillation : |
|
|
- To maximize the diversity of reasoning paths, we calculated the Levenshtein distance between all answers for each question. For every question, we selected up to 5 answers for each question with the greatest distances, resulting in the final dataset with 965 samples. |
|
|
|
|
|
You can access our [dataset](https://huggingface.co/datasets/ZTE-AIM/NTele-R1-Data) to get 965 training data |
|
|
|
|
|
 |
|
|
|
|
|
### Evaluation |
|
|
We evaluate models with [SkyThought](https://github.com/NovaSky-AI/SkyThought). |
|
|
|
|
|
### Training Details |
|
|
NTele-R1-32B-DS was trained from DeepSeek-32B-Distill on 8xH800. |
|
|
|
|
|
#### Training hyperparameter |
|
|
- learning_rate: 1e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- gradient_accumulation_steps: 6 |
|
|
- total_train_batch_size: 48 |
|
|
- total_eval_batch_size: 48 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 10.0 |
|
|
|
