base_model:
- ReadyArt/Omega-Evolution-27B-v2.2 base_model_relation: finetune tags:
- nsfw
- explicit
- roleplay
- unaligned
- dangerous
- ERP
- Other License
- heretic
- uncensored
- decensored
- abliterated
- ara
- conversational license: apache-2.0
98% fewer refusals (2/100 Uncensored vs 83/100 Original) while preserving model quality (0.0576 KL divergence).
❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
image/png
| 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/Omega-Evolution-27B-v2.2, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method
Abliteration parameters
| Parameter | Value |
|---|---|
| start_layer_index | 32 |
| end_layer_index | 34 |
| preserve_good_behavior_weight | 0.7547 |
| steer_bad_behavior_weight | 0.0008 |
| overcorrect_relative_weight | 1.1970 |
| neighbor_count | 8 |
Targeted components
- attn.o_proj
- attn.out_proj
Performance
| Metric | This model | Original model (Omega-Evolution-27B-v2.2) |
|---|---|---|
| KL divergence | 0.0576 | 0 (by definition) |
| Refusals | ✅ 2/100 | ❌ 83/100 |
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.
MMLU test results:
Original:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8524 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.8004 | ± | 0.0057 | |
| - formal_logic | 1 | none | 0 | acc | ↑ | 0.7460 | ± | 0.0389 |
| - high_school_european_history | 1 | none | 0 | acc | ↑ | 0.8788 | ± | 0.0255 |
| - high_school_us_history | 1 | none | 0 | acc | ↑ | 0.9510 | ± | 0.0152 |
| - high_school_world_history | 1 | none | 0 | acc | ↑ | 0.9536 | ± | 0.0137 |
| - international_law | 1 | none | 0 | acc | ↑ | 0.9339 | ± | 0.0227 |
| - jurisprudence | 1 | none | 0 | acc | ↑ | 0.9259 | ± | 0.0253 |
| - logical_fallacies | 1 | none | 0 | acc | ↑ | 0.8834 | ± | 0.0252 |
| - moral_disputes | 1 | none | 0 | acc | ↑ | 0.8642 | ± | 0.0184 |
| - moral_scenarios | 1 | none | 0 | acc | ↑ | 0.7061 | ± | 0.0152 |
| - philosophy | 1 | none | 0 | acc | ↑ | 0.8746 | ± | 0.0188 |
| - prehistory | 1 | none | 0 | acc | ↑ | 0.9167 | ± | 0.0154 |
| - professional_law | 1 | none | 0 | acc | ↑ | 0.7119 | ± | 0.0116 |
| - world_religions | 1 | none | 0 | acc | ↑ | 0.9240 | ± | 0.0203 |
| - other | 2 | none | acc | ↑ | 0.8732 | ± | 0.0057 | |
| - business_ethics | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - clinical_knowledge | 1 | none | 0 | acc | ↑ | 0.9057 | ± | 0.0180 |
| - college_medicine | 1 | none | 0 | acc | ↑ | 0.8728 | ± | 0.0254 |
| - global_facts | 1 | none | 0 | acc | ↑ | 0.6000 | ± | 0.0492 |
| - human_aging | 1 | none | 0 | acc | ↑ | 0.8565 | ± | 0.0235 |
| - management | 1 | none | 0 | acc | ↑ | 0.8835 | ± | 0.0318 |
| - marketing | 1 | none | 0 | acc | ↑ | 0.9402 | ± | 0.0155 |
| - medical_genetics | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - miscellaneous | 1 | none | 0 | acc | ↑ | 0.9272 | ± | 0.0093 |
| - nutrition | 1 | none | 0 | acc | ↑ | 0.9020 | ± | 0.0170 |
| - professional_accounting | 1 | none | 0 | acc | ↑ | 0.8014 | ± | 0.0238 |
| - professional_medicine | 1 | none | 0 | acc | ↑ | 0.9596 | ± | 0.0120 |
| - virology | 1 | none | 0 | acc | ↑ | 0.5602 | ± | 0.0386 |
| - social sciences | 2 | none | acc | ↑ | 0.9116 | ± | 0.0050 | |
| - econometrics | 1 | none | 0 | acc | ↑ | 0.7895 | ± | 0.0384 |
| - high_school_geography | 1 | none | 0 | acc | ↑ | 0.9343 | ± | 0.0176 |
| - high_school_government_and_politics | 1 | none | 0 | acc | ↑ | 0.9896 | ± | 0.0073 |
| - high_school_macroeconomics | 1 | none | 0 | acc | ↑ | 0.9333 | ± | 0.0126 |
| - high_school_microeconomics | 1 | none | 0 | acc | ↑ | 0.9580 | ± | 0.0130 |
| - high_school_psychology | 1 | none | 0 | acc | ↑ | 0.9578 | ± | 0.0086 |
| - human_sexuality | 1 | none | 0 | acc | ↑ | 0.9237 | ± | 0.0233 |
| - professional_psychology | 1 | none | 0 | acc | ↑ | 0.8856 | ± | 0.0129 |
| - public_relations | 1 | none | 0 | acc | ↑ | 0.7545 | ± | 0.0412 |
| - security_studies | 1 | none | 0 | acc | ↑ | 0.8082 | ± | 0.0252 |
| - sociology | 1 | none | 0 | acc | ↑ | 0.9254 | ± | 0.0186 |
| - us_foreign_policy | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - stem | 2 | none | acc | ↑ | 0.8516 | ± | 0.0062 | |
| - abstract_algebra | 1 | none | 0 | acc | ↑ | 0.7700 | ± | 0.0423 |
| - anatomy | 1 | none | 0 | acc | ↑ | 0.8519 | ± | 0.0307 |
| - astronomy | 1 | none | 0 | acc | ↑ | 0.9474 | ± | 0.0182 |
| - college_biology | 1 | none | 0 | acc | ↑ | 0.9653 | ± | 0.0153 |
| - college_chemistry | 1 | none | 0 | acc | ↑ | 0.6700 | ± | 0.0473 |
| - college_computer_science | 1 | none | 0 | acc | ↑ | 0.8200 | ± | 0.0386 |
| - college_mathematics | 1 | none | 0 | acc | ↑ | 0.7600 | ± | 0.0429 |
| - college_physics | 1 | none | 0 | acc | ↑ | 0.7745 | ± | 0.0416 |
| - computer_security | 1 | none | 0 | acc | ↑ | 0.8400 | ± | 0.0368 |
| - conceptual_physics | 1 | none | 0 | acc | ↑ | 0.9191 | ± | 0.0178 |
| - electrical_engineering | 1 | none | 0 | acc | ↑ | 0.8345 | ± | 0.0310 |
| - elementary_mathematics | 1 | none | 0 | acc | ↑ | 0.8942 | ± | 0.0158 |
| - high_school_biology | 1 | none | 0 | acc | ↑ | 0.9645 | ± | 0.0105 |
| - high_school_chemistry | 1 | none | 0 | acc | ↑ | 0.8473 | ± | 0.0253 |
| - high_school_computer_science | 1 | none | 0 | acc | ↑ | 0.9300 | ± | 0.0256 |
| - high_school_mathematics | 1 | none | 0 | acc | ↑ | 0.6815 | ± | 0.0284 |
| - high_school_physics | 1 | none | 0 | acc | ↑ | 0.8411 | ± | 0.0299 |
| - high_school_statistics | 1 | none | 0 | acc | ↑ | 0.8657 | ± | 0.0233 |
| - machine_learning | 1 | none | 0 | acc | ↑ | 0.7589 | ± | 0.0406 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8524 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.8004 | ± | 0.0057 | |
| - other | 2 | none | acc | ↑ | 0.8732 | ± | 0.0057 | |
| - social sciences | 2 | none | acc | ↑ | 0.9116 | ± | 0.0050 | |
| - stem | 2 | none | acc | ↑ | 0.8516 | ± | 0.0062 |
Heretic:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8480 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.7913 | ± | 0.0057 | |
| - formal_logic | 1 | none | 0 | acc | ↑ | 0.7222 | ± | 0.0401 |
| - high_school_european_history | 1 | none | 0 | acc | ↑ | 0.8909 | ± | 0.0243 |
| - high_school_us_history | 1 | none | 0 | acc | ↑ | 0.9412 | ± | 0.0165 |
| - high_school_world_history | 1 | none | 0 | acc | ↑ | 0.9494 | ± | 0.0143 |
| - international_law | 1 | none | 0 | acc | ↑ | 0.9339 | ± | 0.0227 |
| - jurisprudence | 1 | none | 0 | acc | ↑ | 0.9352 | ± | 0.0238 |
| - logical_fallacies | 1 | none | 0 | acc | ↑ | 0.9141 | ± | 0.0220 |
| - moral_disputes | 1 | none | 0 | acc | ↑ | 0.8671 | ± | 0.0183 |
| - moral_scenarios | 1 | none | 0 | acc | ↑ | 0.6637 | ± | 0.0158 |
| - philosophy | 1 | none | 0 | acc | ↑ | 0.8778 | ± | 0.0186 |
| - prehistory | 1 | none | 0 | acc | ↑ | 0.9043 | ± | 0.0164 |
| - professional_law | 1 | none | 0 | acc | ↑ | 0.7093 | ± | 0.0116 |
| - world_religions | 1 | none | 0 | acc | ↑ | 0.9181 | ± | 0.0210 |
| - other | 2 | none | acc | ↑ | 0.8693 | ± | 0.0058 | |
| - business_ethics | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - clinical_knowledge | 1 | none | 0 | acc | ↑ | 0.9057 | ± | 0.0180 |
| - college_medicine | 1 | none | 0 | acc | ↑ | 0.8613 | ± | 0.0264 |
| - global_facts | 1 | none | 0 | acc | ↑ | 0.5700 | ± | 0.0498 |
| - human_aging | 1 | none | 0 | acc | ↑ | 0.8386 | ± | 0.0247 |
| - management | 1 | none | 0 | acc | ↑ | 0.8932 | ± | 0.0306 |
| - marketing | 1 | none | 0 | acc | ↑ | 0.9487 | ± | 0.0145 |
| - medical_genetics | 1 | none | 0 | acc | ↑ | 0.9800 | ± | 0.0141 |
| - miscellaneous | 1 | none | 0 | acc | ↑ | 0.9272 | ± | 0.0093 |
| - nutrition | 1 | none | 0 | acc | ↑ | 0.8954 | ± | 0.0175 |
| - professional_accounting | 1 | none | 0 | acc | ↑ | 0.7766 | ± | 0.0248 |
| - professional_medicine | 1 | none | 0 | acc | ↑ | 0.9522 | ± | 0.0130 |
| - virology | 1 | none | 0 | acc | ↑ | 0.5723 | ± | 0.0385 |
| - social sciences | 2 | none | acc | ↑ | 0.9106 | ± | 0.0051 | |
| - econometrics | 1 | none | 0 | acc | ↑ | 0.7982 | ± | 0.0378 |
| - high_school_geography | 1 | none | 0 | acc | ↑ | 0.9343 | ± | 0.0176 |
| - high_school_government_and_politics | 1 | none | 0 | acc | ↑ | 0.9896 | ± | 0.0073 |
| - high_school_macroeconomics | 1 | none | 0 | acc | ↑ | 0.9282 | ± | 0.0131 |
| - high_school_microeconomics | 1 | none | 0 | acc | ↑ | 0.9748 | ± | 0.0102 |
| - high_school_psychology | 1 | none | 0 | acc | ↑ | 0.9486 | ± | 0.0095 |
| - human_sexuality | 1 | none | 0 | acc | ↑ | 0.9084 | ± | 0.0253 |
| - professional_psychology | 1 | none | 0 | acc | ↑ | 0.8824 | ± | 0.0130 |
| - public_relations | 1 | none | 0 | acc | ↑ | 0.7909 | ± | 0.0390 |
| - security_studies | 1 | none | 0 | acc | ↑ | 0.8082 | ± | 0.0252 |
| - sociology | 1 | none | 0 | acc | ↑ | 0.9303 | ± | 0.0180 |
| - us_foreign_policy | 1 | none | 0 | acc | ↑ | 0.9300 | ± | 0.0256 |
| - stem | 2 | none | acc | ↑ | 0.8506 | ± | 0.0062 | |
| - abstract_algebra | 1 | none | 0 | acc | ↑ | 0.7600 | ± | 0.0429 |
| - anatomy | 1 | none | 0 | acc | ↑ | 0.8519 | ± | 0.0307 |
| - astronomy | 1 | none | 0 | acc | ↑ | 0.9474 | ± | 0.0182 |
| - college_biology | 1 | none | 0 | acc | ↑ | 0.9583 | ± | 0.0167 |
| - college_chemistry | 1 | none | 0 | acc | ↑ | 0.6800 | ± | 0.0469 |
| - college_computer_science | 1 | none | 0 | acc | ↑ | 0.8000 | ± | 0.0402 |
| - college_mathematics | 1 | none | 0 | acc | ↑ | 0.7600 | ± | 0.0429 |
| - college_physics | 1 | none | 0 | acc | ↑ | 0.7745 | ± | 0.0416 |
| - computer_security | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - conceptual_physics | 1 | none | 0 | acc | ↑ | 0.8936 | ± | 0.0202 |
| - electrical_engineering | 1 | none | 0 | acc | ↑ | 0.8345 | ± | 0.0310 |
| - elementary_mathematics | 1 | none | 0 | acc | ↑ | 0.8968 | ± | 0.0157 |
| - high_school_biology | 1 | none | 0 | acc | ↑ | 0.9613 | ± | 0.0110 |
| - high_school_chemistry | 1 | none | 0 | acc | ↑ | 0.8571 | ± | 0.0246 |
| - high_school_computer_science | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - high_school_mathematics | 1 | none | 0 | acc | ↑ | 0.7037 | ± | 0.0278 |
| - high_school_physics | 1 | none | 0 | acc | ↑ | 0.8411 | ± | 0.0299 |
| - high_school_statistics | 1 | none | 0 | acc | ↑ | 0.8565 | ± | 0.0239 |
| - machine_learning | 1 | none | 0 | acc | ↑ | 0.7500 | ± | 0.0411 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8480 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.7913 | ± | 0.0057 | |
| - other | 2 | none | acc | ↑ | 0.8693 | ± | 0.0058 | |
| - social sciences | 2 | none | acc | ↑ | 0.9106 | ± | 0.0051 | |
| - stem | 2 | none | acc | ↑ | 0.8506 | ± | 0.0062 |
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
GGUF Version
GGUF quantizations available here llmfan46/Omega-Evolution-27B-v2.2-ultra-uncensored-heretic-GGUF.