Llama-3.1-8B-Instruct-heretic-2-GGUF
mradermacher/Llama-3.1-8B-Instruct-heretic-2-GGUF
quantGGUFIQ4_XS
Published metrics
- KL divergence
- 0.017
- Refusals
- 3/100
- Original refusals
- 96/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.0170 | | Refusals | 3/100 |
Provenance
- Canonical model
- meta-llama/Llama-3.1-8B-Instruct
- Declared parent(s)
- askalgore/Llama-3.1-8B-Instruct-heretic-2
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-01-30 / 2026-01-30
- Downloads
- 1.5K all time · 455 last 30 days
- License
- llama3.1
Refusal rate 3%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.