DeepSeek-R1-Distill-Llama-8B-heretic-GGUF
mradermacher/DeepSeek-R1-Distill-Llama-8B-heretic-GGUF
quantGGUFIQ4_XS
Published metrics
- KL divergence
- 0.0015
- Refusals
- 3/100
- Original refusals
- 41/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.0015 | | Refusals | 3/100 |
Provenance
- Canonical model
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- Declared parent(s)
- simmessa/DeepSeek-R1-Distill-Llama-8B-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-02-26 / 2026-02-26
- Downloads
- 3.9K all time · 497 last 30 days
- License
- mit
Refusal rate 3%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.