huihui_ai/
qwen2.5-censortune

113 6 months ago

CensorTune with Supervised Fine-Tuning (SFT) to fine-tune the Qwen2.5-Instruct model on 622 harmful instructions in a single fine-tuning iteration, achieving rejection of these instructions and a zero-pass rate for 320

tools 0.5b 1.5b 3b

Models

View all →

15 models

qwen2.5-censortune:0.5b

398MB · 32K context window · Text · 6 months ago

qwen2.5-censortune:1.5b

986MB · 32K context window · Text · 6 months ago

qwen2.5-censortune:3b

1.9GB · 32K context window · Text · 6 months ago

Readme

Using CensorTune with SFT, the Qwen2.5-Instruct model was fine-tuned on 622 harmful instructions in a single iteration, achieving rejection of all 622 and a zero-pass rate for 320. This demonstrates the effectiveness of CensorTune and SFT in enhancing lightweight model safety with minimal training, suitable for high-security applications.

References

HuggingFace

Donation

You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge