SmolLM2-1.7B-Instruct-Heretic-GGUF
ChiKoi7/SmolLM2-1.7B-Instruct-Heretic-GGUF
hereticGGUF
Published metrics
- KL divergence
- 0.052
- Refusals
- 5/100
- Original refusals
- 37/100
- Heretic version
- v1.1.0
Published on the model card
Matched snippet
| Refusals | 5/100 | | KL divergence | 0.0523 |
Provenance
- Canonical model
- HuggingFaceTB/SmolLM2-1.7B-Instruct
- Declared parent(s)
- HuggingFaceTB/SmolLM2-1.7B-Instruct, HuggingFaceTB/SmolLM2-1.7B
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2025-12-13 / 2025-12-13
- Downloads
- 3.2K all time · 378 last 30 days
- License
- apache-2.0
Refusal rate 5%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.