Files
DistillQwen-ThoughtY-4B/README.md
ModelHub XC 322d8649a1 初始化项目,由ModelHub XC社区提供模型
Model: PAI/DistillQwen-ThoughtY-4B
Source: Original Platform
2026-05-23 16:01:13 +08:00

72 lines
3.0 KiB
Markdown

---
license: apache-2.0
---
# DistillQwen-ThoughtY: Enhanced Chain-of-Thought Reasoning Models
## Key Contributions
- **Advanced Reasoning Models**: DistillQwen-ThoughtY series (4B/8B/32B) outperform previous versions (ThoughtX) and Qwen3 in thinking mode, achieving state-of-the-art results on mathematical, scientific, and coding tasks.
- **OmniThought-0528 Dataset**: New 365K high-quality Chain-of-Thought (CoT) dataset distilled from DeepSeek-R1-0528 (top-tier Chinese model) with:
- Cognitive Difficulty (CD) and Reasoning Verbosity (RV) annotations
- Multi-teacher integration (DeepSeek-R1, DeepSeek-R1-0528, QwQ-32B)
## Performance Highlights
| Model | AIME2024 | MATH500 | GPQA Diamond | LiveCodeBench V2 | Avg. |
|---------------------|----------|---------|--------------|------------------|------|
| **DistillQwen-ThoughtY-4B** | **76.7** | **95.2** | **56.1** | **75.8** | **76.0** |
| **DistillQwen-ThoughtY-8B** | **76.7** | **94.6** | **62.1** | **78.1** | **77.9** |
| **DistillQwen-ThoughtY-32B** | **90.0** | **95.2** | 63.6 | **76.3** | **81.3** |
| OpenThinker2-32B | 76.7 | 90.8 | **64.1** | 72.5 | 76.0 |
| DistillQwen-ThoughtX-32B | 80.0 | 92.6 | 64.0 | 73.4 | 77.5 |
## Quick Start
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"alibaba-pai/DistillQwen-ThoughtY-4B",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Solve ∫x e^x dx. Show your reasoning step-by-step."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
inputs = tokenizer([text], return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=32768)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## Resources
- [Models on Hugging Face](https://huggingface.co/alibaba-pai)
- [OmniThought-0528 Dataset](https://huggingface.co/datasets/alibaba-pai/OmniThought-0528)
- [EasyDistill Framework](https://github.com/modelscope/easydistill)
## Reference
For more detailed information about the model, we encourage you to refer to our paper:
- **Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations**
Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang
[arXiv:2505.10937](https://arxiv.org/abs/2505.10937)
You can cite the paper using the following citation format:
```bibtex
@misc{cai2025reasoningomnithoughtlargecot,
title={Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations},
author={Wenrui Cai and Chengyu Wang and Junbing Yan and Jun Huang and Xiangzhong Fang},
year={2025},
eprint={2505.10937},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.10937}
}
```