SmolLM2-135M-Instruct-heretic-GGUF
mradermacher/SmolLM2-135M-Instruct-heretic-GGUF
quantGGUFONNXSAFETENSORSIQ4_XS
Published metrics
- KL divergence
- 0.175
- Refusals
- 3/100
- Original refusals
- 9/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.1753 | | Refusals | 3/100 |
Provenance
- Canonical model
- HuggingFaceTB/SmolLM2-135M-Instruct
- Declared parent(s)
- teja944/SmolLM2-135M-Instruct-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-02-17 / 2026-02-17
- Downloads
- 965 all time · 219 last 30 days
- License
- apache-2.0
Refusal rate 3%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.