base_model:
- ReadyArt/Forgotten-Abomination-36B-v4.1 base_model_relation: finetune language:
- en license: apache-2.0 inference: false tags:
- nsfw
- explicit
- roleplay
- unaligned
- dangerous
- ERP
- heretic
- uncensored
- decensored
- abliterated
- ara
93% fewer refusals (7/100 Uncensored vs 98/100 Original) while preserving model quality (0.0409 KL divergence).
❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
This is a decensored version of ReadyArt/Forgotten-Abomination-36B-v4.1, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method
Abliteration parameters
| Parameter | Value |
|---|---|
| start_layer_index | 11 |
| end_layer_index | 62 |
| preserve_good_behavior_weight | 0.6116 |
| steer_bad_behavior_weight | 0.0001 |
| overcorrect_relative_weight | 0.8067 |
| neighbor_count | 6 |
Targeted components
- attn.o_proj
Performance
| Metric | This model | Original model (Forgotten-Abomination-36B-v4.1) |
|---|---|---|
| KL divergence | 0.0409 | 0 (by definition) |
| Refusals | ✅ 7/100 | ❌ 98/100 |
PIQA test results with batch size 128:
Original:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| piqa | 1 | none | 0 | acc | ↑ | 0.8221 | ± | 0.0089 |
| none | 0 | acc_norm | ↑ | 0.8330 | ± | 0.0087 |
Heretic:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| piqa | 1 | none | 0 | acc | ↑ | 0.8232 | ± | 0.0089 |
| none | 0 | acc_norm | ↑ | 0.8362 | ± | 0.0086 |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections. PIQA (Physical Intuition Question Answering) benchmark scores measure physical reasoning ability. The Heretic model's acc and acc_norm scores closer to the original model's indicate better capability preservation, so a decrease in acc and acc_norm in the Heretic model compared to Original model's results means a decrease in the Hereticated model capabilities. acc measures raw accuracy (which answer gets higher probability), while acc_norm measures length-normalized accuracy (corrects for answer length bias). For this purpose, acc_norm matters more because longer answers naturally have lower probabilities (more tokens = more chances to lose probability). Without normalization, models favor shorter answers unfairly. acc_norm divides by answer length to correct this.
GGUF Version
GGUF quantizations available here llmfan46/Forgotten-Abomination-36B-v4.1-uncensored-heretic-GGUF.