Wanfq nielsr HF Staff commited on
Commit
ea9a058
·
verified ·
1 Parent(s): 043c874

Add link to project page (#6)

Browse files

- Add link to project page (c7c500d28109aede73a979a0c7d9ec0d55c3776a)


Co-authored-by: Niels Rogge <[email protected]>

Files changed (1) hide show
  1. README.md +24 -10
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
- license: apache-2.0
3
- datasets:
4
- - Tongyi-Zhiwen/DocQA-RL-1.6K
5
  base_model:
6
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
 
 
 
 
 
7
  tags:
8
  - long-context
9
  - large-reasoning-model
10
- pipeline_tag: text-generation
11
- library_name: transformers
12
  ---
13
 
14
  # QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
@@ -23,6 +23,7 @@ library_name: transformers
23
  [![GitHub](https://img.shields.io/badge/GitHub-QwenLongL1-4b32c3?logo=github)](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
24
  [![ModelScope](https://img.shields.io/badge/🤖%20ModelScope-purple)](https://modelscope.cn/models/iic/QwenLong-L1-32B)
25
  [![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-yellow)](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B)
 
26
 
27
  <!-- **Authors:** -->
28
 
@@ -155,8 +156,10 @@ try:
155
  except ValueError:
156
  index = 0
157
 
158
- thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
159
- content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
 
 
160
 
161
  print("thinking content:", thinking_content)
162
  print("content:", content)
@@ -335,11 +338,18 @@ PROJ_DIR="<YOUR_PROJ_DIR_HERE>"
335
  DATA="<YOUR_DATA_HERE>" # e.g., docmath, frames, 2wikimqa, hotpotqa, musique, narrativeqa, pasper
336
  python ${PROJ_DIR}/eval/${DATA}_verify.py \
337
  --save_dir "${PROJ_DIR}/results/${DATA}" \
338
- --save_file "${MODEL_NAME}" \
339
- --judge_model "deepseek-chat" \
340
  --batch_size 20
341
  ```
342
 
 
 
 
 
 
 
 
343
  ## 📝 Citation
344
 
345
  If you find this work is relevant with your research or applications, please feel free to cite our work!
@@ -350,4 +360,8 @@ If you find this work is relevant with your research or applications, please fee
350
  journal={arXiv preprint arXiv:2505.17667},
351
  year={2025}
352
  }
353
- ```
 
 
 
 
 
1
  ---
 
 
 
2
  base_model:
3
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
4
+ datasets:
5
+ - Tongyi-Zhiwen/DocQA-RL-1.6K
6
+ library_name: transformers
7
+ license: apache-2.0
8
+ pipeline_tag: text-generation
9
  tags:
10
  - long-context
11
  - large-reasoning-model
 
 
12
  ---
13
 
14
  # QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
 
23
  [![GitHub](https://img.shields.io/badge/GitHub-QwenLongL1-4b32c3?logo=github)](https://github.com/Tongyi-Zhiwen/QwenLong-L1)
24
  [![ModelScope](https://img.shields.io/badge/🤖%20ModelScope-purple)](https://modelscope.cn/models/iic/QwenLong-L1-32B)
25
  [![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-yellow)](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B)
26
+ [Project Page](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B)
27
 
28
  <!-- **Authors:** -->
29
 
 
156
  except ValueError:
157
  index = 0
158
 
159
+ thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("
160
+ ")
161
+ content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("
162
+ ")
163
 
164
  print("thinking content:", thinking_content)
165
  print("content:", content)
 
338
  DATA="<YOUR_DATA_HERE>" # e.g., docmath, frames, 2wikimqa, hotpotqa, musique, narrativeqa, pasper
339
  python ${PROJ_DIR}/eval/${DATA}_verify.py \
340
  --save_dir "${PROJ_DIR}/results/${DATA}" \
341
+ --save_file \"${MODEL_NAME}\" \
342
+ --judge_model \"deepseek-chat\" \
343
  --batch_size 20
344
  ```
345
 
346
+ ## 🌐 Join the Community
347
+ Chinese users can scan QR codes to join WeChat/DingTalk groups.
348
+
349
+ | WeChat | DingTalk |
350
+ |----------|---------|
351
+ | ![Alt Text](./assets/weichat_group.png) | ![Alt Text](./assets/dingding_group.png) |
352
+
353
  ## 📝 Citation
354
 
355
  If you find this work is relevant with your research or applications, please feel free to cite our work!
 
360
  journal={arXiv preprint arXiv:2505.17667},
361
  year={2025}
362
  }
363
+ ```
364
+
365
+ ## ⭐️ Star History
366
+
367
+ [![Star History Chart](https://api.star-history.com/svg?repos=Tongyi-Zhiwen/QwenLong-L1&type=Timeline)](https://star-history.com/#Tongyi-Zhiwen/QwenLong-L1&Timeline)