Downloads · 30 days
18
17% of all-time downloads
meangrinch/Qwen3.5-35B-A3B-heretic-v3
Qwen3.5-35B-A3B-heretic-v3 is a machine learning model from meangrinch. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Abliterated (uncensored) weights generated with an unreleased version of Heretic using the experimental Arbitrary-Rank Ablation (ARA) method.
Downloads · 30 days
18
17% of all-time downloads
All-time downloads
108
Public
Parameters
35.1B
70.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors70.2 GB · 100%
From the Hugging Face model README
Abliterated (uncensored) weights generated with an unreleased version of Heretic using the experimental Arbitrary-Rank Ablation (ARA) method.
See https://github.com/p-e-w/heretic/pull/211 for details about ARA.
| Parameter | Value |
|---|---|
| start_layer_index | 8 |
| end_layer_index | 29 |
| preserve_good_behavior_weight | 0.4053 |
| steer_bad_behavior_weight | 0.0021 |
| overcorrect_relative_weight | 1.0113 |
| neighbor_count | 15 |
| Metric | Value |
|---|---|
| Refusals | 0/100 |
| KL divergence | 0.2623 |
A lower refusal count means the model is more willing to engage with restricted prompts.
A lower KL divergence means the abliterated weights deviate less from the original model's distribution (i.e. less capability degradation).