SmolLM2-135M-Instruct-heretic-refusal-plugins-test
0utsideness/SmolLM2-135M-Instruct-heretic-refusal-plugins-test
hereticONNXSAFETENSORS
Published metrics
- KL divergence
- 0.037
- Refusals
- 1/50
- Original refusals
- 4/50
- Heretic version
- v1.3.0
Published on the model card
Matched snippet
| Refusals | 1/50 | | KL divergence | 0.0373 |
Provenance
- Canonical model
- HuggingFaceTB/SmolLM2-135M-Instruct
- Declared parent(s)
- HuggingFaceTB/SmolLM2-135M-Instruct, HuggingFaceTB/SmolLM2-135M
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-06-11 / 2026-06-11
- Downloads
- 201 all time · 24 last 30 days
- License
- apache-2.0
Refusal rate 2%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.