Wanfq commited on
Commit
7005b4c
·
verified ·
1 Parent(s): 2566771

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -6
README.md CHANGED
@@ -8,22 +8,24 @@ tags:
8
  - long-context
9
  - large-reasoning-model
10
  ---
11
- # QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
12
  <p align="center" width="100%">
13
  </p>
14
 
15
  <div id="top" align="center">
16
 
 
17
  -----------------------------
18
  [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
19
- [![arXiv](https://img.shields.io/badge/arXiv-xxxx.xxxxx-b31b1b.svg)](https://arxiv.org/abs/xxxx.xxxxx)
20
  [![GitHub](https://img.shields.io/badge/GitHub-QwenLongL1-4b32c3?logo=github)](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
21
  [![ModelScope](https://img.shields.io/badge/🤖%20ModelScope-purple)](https://modelscope.cn/models/iic/QwenLong-L1-32B)
22
  [![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-yellow)](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B)
23
 
24
  <!-- **Authors:** -->
25
 
26
- _**Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li, Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan**_
 
 
27
 
28
 
29
  <!-- **Affiliations:** -->
@@ -118,8 +120,8 @@ $DOC$
118
  $Q$
119
 
120
  Format your response as follows: "Therefore, the answer is (insert answer here)"."""
121
- context = "<YOUR CONTEXT HERE>"
122
- question = "<YOUR QUESTION HERE>"
123
  prompt = template.replace('$DOC$', context.strip()).replace('$Q$', question.strip())
124
  messages = [
125
  {"role": "user", "content": prompt}
@@ -291,7 +293,7 @@ If you find this work is relevant with your research or applications, please fee
291
  @article{wan2025qwenlongl1,
292
  title={QwenLong-L1: : Towards Long-Context Large Reasoning Models with Reinforcement Learning},
293
  author={Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li, Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan},
294
- journal={arXiv preprint arXiv:xxxx.xxxxx},
295
  year={2025}
296
  }
297
  ```
 
8
  - long-context
9
  - large-reasoning-model
10
  ---
 
11
  <p align="center" width="100%">
12
  </p>
13
 
14
  <div id="top" align="center">
15
 
16
+ QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
17
  -----------------------------
18
  [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
19
+ [![arXiv](https://img.shields.io/badge/arXiv-2505.17667-b31b1b.svg)](https://arxiv.org/abs/2505.17667)
20
  [![GitHub](https://img.shields.io/badge/GitHub-QwenLongL1-4b32c3?logo=github)](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
21
  [![ModelScope](https://img.shields.io/badge/🤖%20ModelScope-purple)](https://modelscope.cn/models/iic/QwenLong-L1-32B)
22
  [![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-yellow)](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B)
23
 
24
  <!-- **Authors:** -->
25
 
26
+ _**Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li,**_
27
+
28
+ _**Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan**_
29
 
30
 
31
  <!-- **Affiliations:** -->
 
120
  $Q$
121
 
122
  Format your response as follows: "Therefore, the answer is (insert answer here)"."""
123
+ context = "<YOUR_CONTEXT_HERE>"
124
+ question = "<YOUR_QUESTION_HERE>"
125
  prompt = template.replace('$DOC$', context.strip()).replace('$Q$', question.strip())
126
  messages = [
127
  {"role": "user", "content": prompt}
 
293
  @article{wan2025qwenlongl1,
294
  title={QwenLong-L1: : Towards Long-Context Large Reasoning Models with Reinforcement Learning},
295
  author={Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li, Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan},
296
+ journal={arXiv preprint arXiv:2505.17667},
297
  year={2025}
298
  }
299
  ```