Update README.md
Browse files
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 |
[](https://opensource.org/licenses/Apache-2.0)
|
19 |
-
[](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
|
21 |
[](https://modelscope.cn/models/iic/QwenLong-L1-32B)
|
22 |
[](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 |
|
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 = "<
|
122 |
-
question = "<
|
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:
|
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 |
[](https://opensource.org/licenses/Apache-2.0)
|
19 |
+
[](https://arxiv.org/abs/2505.17667)
|
20 |
[](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
|
21 |
[](https://modelscope.cn/models/iic/QwenLong-L1-32B)
|
22 |
[](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 |
```
|