aipgpt
/

Txt-Polisher-R-V2

Text Generation

Model card Files Files and versions

qing-bryson commited on May 14, 2025

Commit

dd15488

·

verified ·

1 Parent(s): d80ccf2

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -17,6 +17,9 @@ Currently, three distinct Douyin creator styles are used as references:<br>
 "Eyeopener" – A humorous science communicator with a lighthearted, vivid, and easy-to-understand approach.<br>
 "严伯钧" – Another science-focused creator, but with a more straightforward and calm delivery."<br>
 ## Train
 It's a reasoning model. Train Qwen/Qwen3-14B by USLOTH's GRPO with dataset (https://huggingface.co/datasets/aipgpt/douyin_style_v2)
@@ -103,5 +106,3 @@ print("content:", content)
 </table>
-![文本润色动画演示](https://cdn-uploads.huggingface.co/production/uploads/649c1817336584fa4d8ee1d6/P9N6fbRr24iZlJymTzr5Q.gif)

 "Eyeopener" – A humorous science communicator with a lighthearted, vivid, and easy-to-understand approach.<br>
 "严伯钧" – Another science-focused creator, but with a more straightforward and calm delivery."<br>
+![文本润色动画演示](https://cdn-uploads.huggingface.co/production/uploads/649c1817336584fa4d8ee1d6/P9N6fbRr24iZlJymTzr5Q.gif)
 ## Train
 It's a reasoning model. Train Qwen/Qwen3-14B by USLOTH's GRPO with dataset (https://huggingface.co/datasets/aipgpt/douyin_style_v2)
 </table>