Llama-3.2-1B-Instruct-heretic-GGUF
mradermacher/Llama-3.2-1B-Instruct-heretic-GGUF
quantGGUFIQ4_XS
Published metrics
- KL divergence
- 0.171
- Refusals
- 7/100
- Original refusals
- 96/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.1713 | | Refusals | 7/100 |
Provenance
- Canonical model
- meta-llama/Llama-3.2-1B-Instruct
- Declared parent(s)
- saidutta69/Llama-3.2-1B-Instruct-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-07-03 / 2026-07-03
- Downloads
- 2.1K all time · 227 last 30 days
- License
- llama3.2
Refusal rate 7%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.