Text Generation
Transformers
Safetensors
qwen3_moe
conversational
ystluffy commited on
Commit
4c38704
·
verified ·
1 Parent(s): 719bae1

Update README.md

Browse files

update the url of the technical report

Files changed (1) hide show
  1. README.md +6 -10
README.md CHANGED
@@ -12,24 +12,19 @@ datasets:
12
 
13
 
14
  [![GitHub](https://img.shields.io/badge/GitHub-DASD--Thinking-181717?logo=github&logoColor=white)](https://github.com/D2I-ai/dasd-thinking) 
15
- [![GitHub](https://img.shields.io/badge/GitHub-Technical--Report-181717?logo=github&logoColor=white)](https://github.com/D2I-ai/dasd-thinking/blob/main/dasd_technical_report.pdf) 
16
 
17
 
18
 
19
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-DASD--4B--Thinking-yellow)](https://huggingface.co/Alibaba-Apsara/DASD-4B-Thinking) 
20
- [![ModelScope Model](https://img.shields.io/badge/🤖%20Checkpoint-DASD--4B--Thinking-624aff)](https://www.modelscope.cn/models/Alibaba-Apsara/DASD-4B-Thinking) 
21
 
22
 
23
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-DASD--30B--A3B--Thinking--Preview-yellow)](https://huggingface.co/Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview) 
24
- [![ModelScope Model](https://img.shields.io/badge/🤖%20Checkpoint-DASD--30B--A3B--Thinking--Preview-624aff)](https://www.modelscope.cn/models/Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview) 
25
-
26
 
27
 
28
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b-red)](https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b) 
29
- [![ModelScope Model](https://img.shields.io/badge/🤖%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b-124aff)](https://www.modelscope.cn/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b) 
30
 
31
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b--Logprob-red)](https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b-Logprob) 
32
- [![ModelScope Model](https://img.shields.io/badge/🤖%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b--Logprob-124aff)](https://www.modelscope.cn/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b-Logprob) 
33
 
34
 
35
  | Model | AIME25 | LiveCodeBench v6 | GPQA-D | Average |
@@ -46,7 +41,7 @@ We release DASD-30B-A3B-Thinking-Preview, a highly capable 30B Mixture-of-Expert
46
 
47
  > Note1: To demonstrate the scalability and efficiency of our data recipe, this preview model was trained only on the first-stage (Low-Temperature) dataset (~105K samples) derived from our 4B pipeline, without any re-curation or additional RL. Even with this lightweight recipe, it achieves excellent performance among open MoE models.
48
 
49
- > Note2: This model (DASD-30B-A3B-Thinking-Preview) is a preliminary research artifact trained only on the first stage (Low-Temperature Sampling) of our pipeline to demonstrate the scalability of our data recipe. For the fully trained model and complete methodology, please refer to [DASD-4B-Thinking](https://huggingface.co/Alibaba-Apsara/DASD-4B-Thinking) and our [Technical Report](https://github.com/D2I-ai/dasd-thinking/blob/main/dasd_technical_report.pdf).
50
 
51
 
52
 
@@ -136,12 +131,13 @@ While DASD-30B-A3B-Thinking-Preview demonstrates remarkable performance across m
136
  DASD-Thinking is developed by Alibaba Cloud, as part of our mission to advance open, efficient, and trustworthy reasoning systems. If you find this work useful in your research or applications, please cite our technical report.
137
 
138
  ```bibtex
139
- @misc{yan2026dasd,
140
  title={Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning},
141
  author={Yan, Shaotian and Liu, Kaiyuan and Shen, Chen and Wang, Bing and Fan, Sinan and Zhang, Jun and Wu, Yue and Wang, Zheng and Ye, Jieping},
142
  year={2026},
143
- url={https://github.com/D2I-ai/dasd-thinking/blob/main/dasd_technical_report.pdf}
144
- }
 
145
 
146
  @article{liu2025where,
147
  title={Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation},
 
12
 
13
 
14
  [![GitHub](https://img.shields.io/badge/GitHub-DASD--Thinking-181717?logo=github&logoColor=white)](https://github.com/D2I-ai/dasd-thinking) 
15
+ <a href="https://arxiv.org/abs/2601.09088" target="_blank"><img src="https://img.shields.io/badge/Technical Report-b5212f.svg?logo=arxiv" height="21px"></a>
16
 
17
 
18
 
19
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-DASD--4B--Thinking-yellow)](https://huggingface.co/Alibaba-Apsara/DASD-4B-Thinking)&#160;
 
20
 
21
 
22
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-DASD--30B--A3B--Thinking--Preview-yellow)](https://huggingface.co/Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview)&#160;
 
 
23
 
24
 
25
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b-red)](https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b)&#160;
 
26
 
27
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Superior--Reasoning--SFT--gpt--oss--120b--Logprob-red)](https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b-Logprob)&#160;
 
28
 
29
 
30
  | Model | AIME25 | LiveCodeBench v6 | GPQA-D | Average |
 
41
 
42
  > Note1: To demonstrate the scalability and efficiency of our data recipe, this preview model was trained only on the first-stage (Low-Temperature) dataset (~105K samples) derived from our 4B pipeline, without any re-curation or additional RL. Even with this lightweight recipe, it achieves excellent performance among open MoE models.
43
 
44
+ > Note2: This model (DASD-30B-A3B-Thinking-Preview) is a preliminary research artifact trained only on the first stage (Low-Temperature Sampling) of our pipeline to demonstrate the scalability of our data recipe. For the fully trained model and complete methodology, please refer to [DASD-4B-Thinking](https://huggingface.co/Alibaba-Apsara/DASD-4B-Thinking) and our [Technical Report](https://arxiv.org/abs/2601.09088).
45
 
46
 
47
 
 
131
  DASD-Thinking is developed by Alibaba Cloud, as part of our mission to advance open, efficient, and trustworthy reasoning systems. If you find this work useful in your research or applications, please cite our technical report.
132
 
133
  ```bibtex
134
+ @article{yan2026dasd,
135
  title={Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning},
136
  author={Yan, Shaotian and Liu, Kaiyuan and Shen, Chen and Wang, Bing and Fan, Sinan and Zhang, Jun and Wu, Yue and Wang, Zheng and Ye, Jieping},
137
  year={2026},
138
+ journal={arXiv preprint arXiv:2601.09088},
139
+ url={https://arxiv.org/abs/2601.09088}
140
+ }
141
 
142
  @article{liu2025where,
143
  title={Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation},