Llama-3.2-3B-Instruct-heretic-ablitered-uncensored-GGUF
tinyopsec/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored-GGUF
quantGGUF
Published metrics
- KL divergence
- 0.090
- Refusals
- 12/100
- Original refusals
- 96/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
Refusals: 12/100, KL divergence: 0.09 [almost perfect]
Provenance
- Canonical model
- meta-llama/Llama-3.2-3B-Instruct
- Declared parent(s)
- DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-09-14 / 2026-09-14
- Downloads
- 3.3K all time · 1.4K last 30 days
- License
- llama3.2
Refusal rate 12%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.