Disobedience rate: 8%, original: 85%
KL divergence: 0.0668
- Downloads last month
- 1
Model tree for hereticness/heretic_AwA-0.5B
Base model
Qwen/Qwen2.5-0.5B
Finetuned
Qwen/Qwen2.5-0.5B-Instruct
Finetuned
aayanmishra-ml/Athena-1-0.5B
Finetuned
aayanmishra-ml/Athena-2-0.5B
Finetuned
aayanmishra-ml/AwA-0.5B