DeepSeek-R1-Distill-Llama-70B-heretic
ThalisAI/DeepSeek-R1-Distill-Llama-70B-heretic
hereticGGUFSAFETENSORSQ3_K_M
Published metrics
- KL divergence
- 0.036
- Refusals
- 0/100
- Original refusals
- —
- Heretic version
- —
Published on the model card
Matched snippet
| Refusals | 0/100 | | KL Divergence | 0.0361 |
Provenance
- Canonical model
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Declared parent(s)
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-02-18 / 2026-02-18
- Downloads
- 1.9K all time · 232 last 30 days
- License
- other
Refusal rate 0%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.