stzhao nielsr HF Staff commited on
Commit
6aa44ec
·
verified ·
1 Parent(s): ce84f40

Correct pipeline tag and add link to Github repo (#1)

Browse files

- Correct pipeline tag and add link to Github repo (fc06ce2fdfd8774759bbe413dc9fcec1a3000d5f)


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

Files changed (1) hide show
  1. README.md +14 -9
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
 
 
 
 
2
  library_name: transformers
3
  license: mit
4
- datasets:
5
- - X-ART/LeX-R1-60K
6
- base_model:
7
- - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
8
- pipeline_tag: text-generation
9
  tags:
10
- - art
11
- - text-rendering
12
  ---
13
 
14
  [![lexart](https://img.shields.io/badge/Paper-LeXArt-2b9348.svg?logo=arXiv)](https://arxiv.org/abs/2503.21749)
@@ -73,7 +73,9 @@ def create_user_prompt(simple_caption):
73
  "5. The detailed caption should be human readable and fluent. "
74
  "6. Avoid using vague expressions such as \"may be\" or \"might be\"; the generated caption must be in a definitive, narrative tone. "
75
  "7. Do not use negative sentence structures, such as \"there is nothing in the image,\" etc. The entire caption should directly describe the content of the image. "
76
- "8. The entire output should be limited to 200 words.\n\n"
 
 
77
  f"SIMPLE CAPTION: {simple_caption}"
78
  )
79
 
@@ -98,4 +100,7 @@ output = model.generate(
98
  )
99
 
100
  print("*" * 80)
101
- # Output will stream via TextStreamer
 
 
 
 
1
  ---
2
+ base_model:
3
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
4
+ datasets:
5
+ - X-ART/LeX-R1-60K
6
  library_name: transformers
7
  license: mit
8
+ pipeline_tag: text-to-image
 
 
 
 
9
  tags:
10
+ - art
11
+ - text-rendering
12
  ---
13
 
14
  [![lexart](https://img.shields.io/badge/Paper-LeXArt-2b9348.svg?logo=arXiv)](https://arxiv.org/abs/2503.21749)
 
73
  "5. The detailed caption should be human readable and fluent. "
74
  "6. Avoid using vague expressions such as \"may be\" or \"might be\"; the generated caption must be in a definitive, narrative tone. "
75
  "7. Do not use negative sentence structures, such as \"there is nothing in the image,\" etc. The entire caption should directly describe the content of the image. "
76
+ "8. The entire output should be limited to 200 words.
77
+
78
+ "
79
  f"SIMPLE CAPTION: {simple_caption}"
80
  )
81
 
 
100
  )
101
 
102
  print("*" * 80)
103
+ # Output will stream via TextStreamer
104
+ ```
105
+
106
+ Github repository: https://github.com/zhaoshitian/LeX-Art