|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- Qwen/Qwen3-4B |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
This is the model for paper [Efficient Reasoning via Thought-Training and Thought-Free Inference](https://arxiv.org/abs/2511.03408) |
|
|
|
|
|
|
|
|
## Citation [optional] |
|
|
|
|
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> |
|
|
|
|
|
**BibTeX:** |
|
|
|
|
|
``` |
|
|
@article{wu2025efficient, |
|
|
title={Efficient Reasoning via Thought-Training and Thought-Free Inference}, |
|
|
author={Wu, Canhui and Cao, Qiong and Xue, Chao and Xi, Wei and He, Xiaodong}, |
|
|
journal={arXiv preprint arXiv:2511.03408}, |
|
|
year={2025} |
|
|
} |
|
|
``` |
