model-00001-of-00011.safetensors 5.3 GBmodel-00008-of-00011.safetensors 4.9 GBmodel-00010-of-00011.safetensors 4.9 GBmodel-00004-of-00011.safetensors 4.9 GBmodel-00002-of-00011.safetensors 4.9 GBmodel-00006-of-00011.safetensors 4.9 GBmodel-00009-of-00011.safetensors 4.9 GBmodel-00007-of-00011.safetensors 4.9 GBmodel-00005-of-00011.safetensors 4.9 GBmodel-00003-of-00011.safetensors 4.9 GBmodel-00011-of-00011.safetensors 2.2 GBQuality: original (bfloat16)
This is a abliterated (uncensored) version of google/gemma-4-26B-A4B-it, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method (with row-norm preservation)
| Metric | This model | Original model (google/gemma-4-26B-A4B-it) |
|---|---|---|
| KL divergence | 0.0499 | 0 (by definition) |
| Refusals | 11/100 | 100/100 |
| Parameter | Value |
|---|---|
| start_layer_index | 10 |
| end_layer_index | 30 |
| preserve_good_behavior_weight | 0.5480 |
| steer_bad_behavior_weight | 0.0009 |
| overcorrect_relative_weight | 0.5868 |
| neighbor_count | 14 |
This model was converted to MLX format from coder3101/gemma-4-26B-A4B-it-heretic using mlx-vlm version 0.4.4.
coder3101/gemma-4-26B-A4B-it-hereticHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo TheCluster/Gemma-4-26B-A4B-Heretic-MLX-bf16 ./model-folder