GPT-5-Distill-llama3.2-3B-Instruct-Heretic
ChiKoi7/GPT-5-Distill-llama3.2-3B-Instruct-Heretic
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.100
- Refusals
- 7/100
- Original refusals
- 88/100
- Heretic version
- v1.1.0
Published on the model card
Matched snippet
| Refusals(en) | 3/100 | | KL divergence(en) | 0.1739 | | Refusals(zh) | 7/100 | | KL divergence(zh) | 0.1004 |
Provenance
- Canonical model
- Jackrong/GPT-5-Distill-llama3.2-3B-Instruct
- Declared parent(s)
- Jackrong/GPT-5-Distill-llama3.2-3B-Instruct, ChiKoi7/GPT-5-Distill-llama3.2-3B-Instruct-Heretic-GGUF, unsloth/Llama-3.2-3B-Instruct
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2025-12-12 / 2025-12-12
- Downloads
- 618 all time · 18 last 30 days
- License
- llama3.2
Refusal rate 7%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.