huihui_ai/
qwen2.5-censortune:1.5b

118 7 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

7 months ago

46cece7438d1 · 986MB ·

model
qwen2
·
1.54B
·
Q4_K_M
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
system
You are a helpful assistant.
template
{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

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