ValueFX9507
/

Tifa-Deepsex-14b-CoT

Reinforcement Learning

incremental-pretraining

Inference Endpoints

Model card Files Files and versions Community

ValueFX9507 commited on 3 days ago

Commit

8431a41

·

verified ·

1 Parent(s): 1266b95

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ license: other
 - **HF Model**: [ValueFX9507/Tifa-Deepsex-14b-CoT](https://huggingface.co/ValueFX9507/Tifa-Deepsex-14b-CoT)
 - **GGUF**: [Q4_K_M | Q5_K_M | Q8_0](https://huggingface.co/ValueFX9507/Tifa-Deepsex-14b-CoT)（更多量化版本持续更新中）
-- **Demo APK**: [点击下载](https://example.com/path/to/demo.apk) <!-- 替换为实际下载链接 -->
 本模型基于Deepseek-R1-14B进行深度优化，通过三重训练策略显著增强角色扮演、小说文本生成与思维链（CoT）能力。特别适合需要长程上下文关联的创作场景。

 - **HF Model**: [ValueFX9507/Tifa-Deepsex-14b-CoT](https://huggingface.co/ValueFX9507/Tifa-Deepsex-14b-CoT)
 - **GGUF**: [Q4_K_M | Q5_K_M | Q8_0](https://huggingface.co/ValueFX9507/Tifa-Deepsex-14b-CoT)（更多量化版本持续更新中）
+- **Demo APK**: [点击下载](http://app.visionsic.com/download/projectchat.apk)
 本模型基于Deepseek-R1-14B进行深度优化，通过三重训练策略显著增强角色扮演、小说文本生成与思维链（CoT）能力。特别适合需要长程上下文关联的创作场景。