72 lines
3.0 KiB
Markdown
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}
|
|
}
|
|
```
|