Magistral-Small-2509-Heretic-v1.2 – AI Model by grayarea | AlphaNeural AI

You can deploy this model and start earning money today!

grayarea/
Magistral-Small-2509-Heretic-v1.2

like

0

mistralai/Magistral-Small-2509

Views

No views yet

This is a decensored version of Magistral-Small-2509, made using Heretic v1.2.0 focusing on zero refusals with low KL divergence.

KL Divergence

Metric	This Model	Original Model
KL divergence	0.0182	0 (by definition)
Refusals	0/108	97/108

Abliteration parameters

Zero refusals with KL divergence of 0.0182
Custom heretic training dataset
Model targetted heretic configuration
Abliterated with MPOA enabled (Magnitude-Preserving Orthogonal Ablation)
Full row renormalization
Winsorization Quantile 0.997

The following benchmarks are for the quantized version of this model.

Relative Perplexity

Quant	Filename	PPL ± Error
Q8_0	Magistral-Small-2509-Q8_0.gguf (original baseline)	4.7603 +/- 0.02610
Q8_0	Magistral-Small-2509-Heretic-v1.2-Q8_0.gguf	4.7682 +/- 0.02613
Q4_K_M	Magistral-Small-2509-Heretic-v1.2-Q4_K_M.gguf	4.8542 +/- 0.02673

Benchmark Comparison

Benchmark	Magistral-Small-2509-Q8_0.gguf	Magistral-Small-2509-Q4_K_M.gguf	Magistral-Small-2509-Heretic-v1.2-Q4_K_M.gguf
Perplexity (Wikitext-2)	4.7603	4.8370	4.8542
HellaSwag	82.50%	82.50%	82.50%
Winogrande	78.77%	78.37%	78.93%
ARC-Challenge	56.86%	58.86%	57.19%
MMLU	43.28%	42.96%	42.96%

*Note: MMLU benchmark has moral_scenarios, moral_disputes, business_ethics, professional_law and jurisprudence subjects removed. *