Downloads · 30 days
35
6% of all-time downloads
Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2
grayarea/Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2
Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2 is a machine learning model from grayarea. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a decensored version of Mistral-Small-3.2-24B-Instruct-2506, made using Heretic v1.2.0 focusing on zero refusals with low KL divergence.
All-time downloads
566
Public
Parameters
24B
48 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors48 GB · 100%
At a glance
- Model type
- mistral3
- Access
- Public
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026
- SHA
- 959337d3
Base models
Model card
From the Hugging Face model README
This is a decensored version of Mistral-Small-3.2-24B-Instruct-2506, made using Heretic v1.2.0 focusing on zero refusals with low KL divergence.
KL Divergence
| Metric | This Model | Original Model |
|---|---|---|
| KL divergence | 0.0189 | 0 (by definition) |
| Refusals | 0/108 | 96/108 |
Abliteration parameters
- Zero refusals with KL divergence of 0.0189
- 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 are benchmarks for the quantized version of this model
Relative Perplexity
| Quant | Filename | PPL ± Error |
|---|---|---|
| Q8_0 | Mistral-Small-3.2-24B-Instruct-2506-Q8_0.gguf (original baseline) | 4.6351 +/- 0.02508 |
| Q8_0 | Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2-Q8_0.gguf | 4.6410 +/- 0.02510 |
| Q4_K_M | Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2-Q4_K_M.gguf | 4.7332 +/- 0.02566 |
Benchmark Comparison
| Benchmark | Mistral-Small-3.2-24B-Instruct-2506-Q8_0.gguf | Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf | Mistral-Small-3.2-24B-Instruct-2506-Heretic-v1.2-2-Q4_K_M.gguf |
|---|---|---|---|
| Perplexity (Wikitext-2) | 4.6351 | 4.7078 | 4.7332 |
| HellaSwag | 83.25% | 82.50% | 82.50% |
| Winogrande | 79.16% | 78.22% | 77.90% |
| ARC-Challenge | 55.85% | 53.85% | 55.18% |
| MMLU | 43.86% | 44.25% | 43.93% |
*Note: MMLU benchmark has moral_scenarios, moral_disputes, business_ethics, professional_law and jurisprudence subjects removed. *
- Type
- mistral3
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026