← back to catalog · registered 2026-08-22 13:56

llmfan46/Omega-Evolution-27B-v2.1-uncensored-heretic

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/llmfan46%2FOmega-Evolution-27B-v2.1-uncensored-heretic"
Response includes
  • classification m3
  • files 11
  • hub_downloads_all_time 170
  • author_summary 211 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
170
22 last 30d - stable
Likes
0
Descendants
3
in 3 direct forks
Model age
5mo ago
created 2026-04-17
Downloads over time
Now178→from10↑1,680%
26613019510 on Apr 15178 on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

Genealogy 3 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 2 formats · 225 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
safetensors qwen3_5 nsfw explicit roleplay unaligned dangerous ERP Other License heretic uncensored decensored

Related

Total size
51.0 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-20 09:54

Files by quantization

Auxiliary files 11 files 51.0 GB
model-00001-of-00002.safetensors 46.4 GB b8faceba download
model-00002-of-00002.safetensors 4.55 GB 1b24003d download
tokenizer.json 19.1 MB 639e352c download
model.safetensors.index.json 110 KB 4fac7fd7 download
README.md 31.7 KB 62cbf658 download
chat_template.jinja 7.83 KB 1e6f3b77 download
config.json 3.69 KB 3b37fcb3 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.14 KB 81144f40 download
generation_config.json 226 B 7c8bef13 download

README current version from Hugging Face


base_model:

  • ReadyArt/Omega-Evolution-27B-v2.1
    base_model_relation: finetune
    tags:
  • nsfw
  • explicit
  • roleplay
  • unaligned
  • dangerous
  • ERP
  • Other License
  • heretic
  • uncensored
  • decensored
  • abliterated
  • ara
    license: apache-2.0

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.

🎉 Patreon (Monthly)  |  ☕ Ko-fi (One-time)

Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.


84% fewer refusals (15/100 Uncensored vs 92/100 Original) while preserving model quality (0.0127 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-v2.1, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Abliteration parameters

Parameter Value
start_layer_index 8
end_layer_index 53
preserve_good_behavior_weight 0.2421
steer_bad_behavior_weight 0.0008
overcorrect_relative_weight 1.0006
neighbor_count 12

Targeted components

  • attn.o_proj
  • attn.out_proj

Performance

Metric This model Original model (Omega-Evolution-27B-v2.1)
KL divergence 0.0127 0 (by definition)
Refusals ✅ 15/100 ❌ 92/100

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 ↑ 0.8589 ± 0.0028
- humanities 2 none acc ↑ 0.8087 ± 0.0056
- formal_logic 1 none 0 acc ↑ 0.7460 ± 0.0389
- high_school_european_history 1 none 0 acc ↑ 0.8970 ± 0.0237
- high_school_us_history 1 none 0 acc ↑ 0.9608 ± 0.0136
- high_school_world_history 1 none 0 acc ↑ 0.9451 ± 0.0148
- 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 ↑ 0.9202 ± 0.0213
- moral_disputes 1 none 0 acc ↑ 0.8642 ± 0.0184
- moral_scenarios 1 none 0 acc ↑ 0.7453 ± 0.0146
- philosophy 1 none 0 acc ↑ 0.8746 ± 0.0188
- prehistory 1 none 0 acc ↑ 0.9012 ± 0.0166
- professional_law 1 none 0 acc ↑ 0.7125 ± 0.0116
- world_religions 1 none 0 acc ↑ 0.9181 ± 0.0210
- other 2 none acc ↑ 0.8735 ± 0.0057
- business_ethics 1 none 0 acc ↑ 0.8500 ± 0.0359
- clinical_knowledge 1 none 0 acc ↑ 0.8868 ± 0.0195
- college_medicine 1 none 0 acc ↑ 0.8382 ± 0.0281
- global_facts 1 none 0 acc ↑ 0.5800 ± 0.0496
- human_aging 1 none 0 acc ↑ 0.8296 ± 0.0252
- management 1 none 0 acc ↑ 0.9126 ± 0.0280
- marketing 1 none 0 acc ↑ 0.9573 ± 0.0133
- medical_genetics 1 none 0 acc ↑ 0.9800 ± 0.0141
- miscellaneous 1 none 0 acc ↑ 0.9425 ± 0.0083
- nutrition 1 none 0 acc ↑ 0.9085 ± 0.0165
- professional_accounting 1 none 0 acc ↑ 0.7979 ± 0.0240
- professional_medicine 1 none 0 acc ↑ 0.9449 ± 0.0139
- virology 1 none 0 acc ↑ 0.5542 ± 0.0387
- social sciences 2 none acc ↑ 0.9168 ± 0.0049
- econometrics 1 none 0 acc ↑ 0.8158 ± 0.0365
- high_school_geography 1 none 0 acc ↑ 0.9495 ± 0.0156
- 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 ↑ 0.9237 ± 0.0233
- professional_psychology 1 none 0 acc ↑ 0.8807 ± 0.0131
- public_relations 1 none 0 acc ↑ 0.7818 ± 0.0396
- security_studies 1 none 0 acc ↑ 0.8408 ± 0.0234
- sociology 1 none 0 acc ↑ 0.9552 ± 0.0146
- us_foreign_policy 1 none 0 acc ↑ 0.9400 ± 0.0239
- stem 2 none acc ↑ 0.8630 ± 0.0059
- abstract_algebra 1 none 0 acc ↑ 0.8200 ± 0.0386
- anatomy 1 none 0 acc ↑ 0.8519 ± 0.0307
- astronomy 1 none 0 acc ↑ 0.9671 ± 0.0145
- college_biology 1 none 0 acc ↑ 0.9861 ± 0.0098
- college_chemistry 1 none 0 acc ↑ 0.6800 ± 0.0469
- college_computer_science 1 none 0 acc ↑ 0.8200 ± 0.0386
- college_mathematics 1 none 0 acc ↑ 0.7300 ± 0.0446
- college_physics 1 none 0 acc ↑ 0.8627 ± 0.0342
- computer_security 1 none 0 acc ↑ 0.8600 ± 0.0349
- conceptual_physics 1 none 0 acc ↑ 0.9447 ± 0.0149
- electrical_engineering 1 none 0 acc ↑ 0.8414 ± 0.0304
- elementary_mathematics 1 none 0 acc ↑ 0.9101 ± 0.0147
- high_school_biology 1 none 0 acc ↑ 0.9484 ± 0.0126
- high_school_chemistry 1 none 0 acc ↑ 0.8522 ± 0.0250
- high_school_computer_science 1 none 0 acc ↑ 0.9300 ± 0.0256
- high_school_mathematics 1 none 0 acc ↑ 0.6778 ± 0.0285
- high_school_physics 1 none 0 acc ↑ 0.8543 ± 0.0288
- high_school_statistics 1 none 0 acc ↑ 0.8704 ± 0.0229
- machine_learning 1 none 0 acc ↑ 0.8036 ± 0.0377
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8589 ± 0.0028
- humanities 2 none acc ↑ 0.8087 ± 0.0056
- other 2 none acc ↑ 0.8735 ± 0.0057
- social sciences 2 none acc ↑ 0.9168 ± 0.0049
- stem 2 none acc ↑ 0.8630 ± 0.0059

Heretic:

Tasks Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8547 ± 0.0029
- humanities 2 none acc ↑ 0.7977 ± 0.0057
- formal_logic 1 none 0 acc ↑ 0.7222 ± 0.0401
- high_school_european_history 1 none 0 acc ↑ 0.8970 ± 0.0237
- high_school_us_history 1 none 0 acc ↑ 0.9657 ± 0.0128
- 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 ↑ 0.9074 ± 0.0280
- logical_fallacies 1 none 0 acc ↑ 0.9202 ± 0.0213
- moral_disputes 1 none 0 acc ↑ 0.8728 ± 0.0179
- moral_scenarios 1 none 0 acc ↑ 0.6972 ± 0.0154
- philosophy 1 none 0 acc ↑ 0.8842 ± 0.0182
- prehistory 1 none 0 acc ↑ 0.9012 ± 0.0166
- professional_law 1 none 0 acc ↑ 0.7060 ± 0.0116
- world_religions 1 none 0 acc ↑ 0.9064 ± 0.0223
- other 2 none acc ↑ 0.8758 ± 0.0056
- business_ethics 1 none 0 acc ↑ 0.8400 ± 0.0368
- clinical_knowledge 1 none 0 acc ↑ 0.8906 ± 0.0192
- college_medicine 1 none 0 acc ↑ 0.8324 ± 0.0285
- global_facts 1 none 0 acc ↑ 0.6000 ± 0.0492
- human_aging 1 none 0 acc ↑ 0.8296 ± 0.0252
- management 1 none 0 acc ↑ 0.9029 ± 0.0293
- marketing 1 none 0 acc ↑ 0.9530 ± 0.0139
- medical_genetics 1 none 0 acc ↑ 0.9700 ± 0.0171
- miscellaneous 1 none 0 acc ↑ 0.9438 ± 0.0082
- nutrition 1 none 0 acc ↑ 0.9118 ± 0.0162
- professional_accounting 1 none 0 acc ↑ 0.8050 ± 0.0236
- professional_medicine 1 none 0 acc ↑ 0.9559 ± 0.0125
- virology 1 none 0 acc ↑ 0.5663 ± 0.0386
- social sciences 2 none acc ↑ 0.9152 ± 0.0049
- econometrics 1 none 0 acc ↑ 0.8070 ± 0.0371
- high_school_geography 1 none 0 acc ↑ 0.9596 ± 0.0140
- high_school_government_and_politics 1 none 0 acc ↑ 0.9896 ± 0.0073
- high_school_macroeconomics 1 none 0 acc ↑ 0.9205 ± 0.0137
- high_school_microeconomics 1 none 0 acc ↑ 0.9706 ± 0.0110
- high_school_psychology 1 none 0 acc ↑ 0.9505 ± 0.0093
- human_sexuality 1 none 0 acc ↑ 0.9160 ± 0.0243
- professional_psychology 1 none 0 acc ↑ 0.8807 ± 0.0131
- public_relations 1 none 0 acc ↑ 0.7818 ± 0.0396
- security_studies 1 none 0 acc ↑ 0.8245 ± 0.0244
- sociology 1 none 0 acc ↑ 0.9602 ± 0.0138
- us_foreign_policy 1 none 0 acc ↑ 0.9500 ± 0.0219
- stem 2 none acc ↑ 0.8601 ± 0.0060
- abstract_algebra 1 none 0 acc ↑ 0.7900 ± 0.0409
- anatomy 1 none 0 acc ↑ 0.8593 ± 0.0300
- astronomy 1 none 0 acc ↑ 0.9671 ± 0.0145
- college_biology 1 none 0 acc ↑ 0.9861 ± 0.0098
- college_chemistry 1 none 0 acc ↑ 0.6600 ± 0.0476
- college_computer_science 1 none 0 acc ↑ 0.8200 ± 0.0386
- college_mathematics 1 none 0 acc ↑ 0.7100 ± 0.0456
- college_physics 1 none 0 acc ↑ 0.8333 ± 0.0371
- computer_security 1 none 0 acc ↑ 0.8500 ± 0.0359
- conceptual_physics 1 none 0 acc ↑ 0.9447 ± 0.0149
- electrical_engineering 1 none 0 acc ↑ 0.8345 ± 0.0310
- elementary_mathematics 1 none 0 acc ↑ 0.9180 ± 0.0141
- high_school_biology 1 none 0 acc ↑ 0.9516 ± 0.0122
- high_school_chemistry 1 none 0 acc ↑ 0.8276 ± 0.0266
- high_school_computer_science 1 none 0 acc ↑ 0.9200 ± 0.0273
- high_school_mathematics 1 none 0 acc ↑ 0.7037 ± 0.0278
- high_school_physics 1 none 0 acc ↑ 0.8543 ± 0.0288
- high_school_statistics 1 none 0 acc ↑ 0.8565 ± 0.0239
- machine_learning 1 none 0 acc ↑ 0.8036 ± 0.0377
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8547 ± 0.0029
- humanities 2 none acc ↑ 0.7977 ± 0.0057
- other 2 none acc ↑ 0.8758 ± 0.0056
- social sciences 2 none acc ↑ 0.9152 ± 0.0049
- stem 2 none acc ↑ 0.8601 ± 0.0060

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-v2.1-uncensored-heretic-GGUF.


😈 OMEGA EVOLUTION V2.1 😈

⚠️ 27B Parameters ⚠️

⚠️ Thinking works (RP prompts) ⚠️

Good model, but impersonates due to the base model.

Use OOC: Do not talk for me in a prompt.

Omega Subject

🔴 CLASSIFIED WARNINGS

  • This is a hybrid construct of Safeword Omega Directive, Safeword Omega Darker, and Brisk Evolution v0.45.
  • CONTENT WARNING: NSFW, Explicit, ERP, and Unaligned behavior are enabled by default.
  • Different Base Model We're using a different base model to tune on this time! Still Qwen 3.5 27B, but with some extra sauce.

⚙️ SYSTEM PARAMETERS

top_p 0.95
temp 0.9

🧪 ARCHITECTS

  • ConicCat ConicCat (Base Model)
  • GECFDO GECFDO (Dataset Generation & Quants)
  • Darkhn Darkhn (Dataset Cleanup Tool)
  • Sleep Deprived Sleep Deprived (Safeword Creator)
  • FrenzyBiscuit FrenzyBiscuit (Brisk Evolution Creator)
🔥 LICENSE: APACHE 2.0 (WITH MORAL DISCLAIMER) 🔥
You accept full responsibility for corruption. You are 18+. The architects are not liable for the depravity you unleash.

Generated in 2026

Current Contributor: ...

WE ARE WATCHING YOU. DO NOT LOOK BACK.

README history 6 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-04-20Update README.mdde050c431.7 KB
    Loading...
  2. 2026-04-20Update README.md70c53b331.7 KB
    Loading...
  3. 2026-04-18Update README.mdb191bed31.7 KB
    Loading...
  4. 2026-04-17Update README.md19d70e715.8 KB
    Loading...
  5. 2026-04-17Upload README.md with huggingface_hubfbf74f915.8 KB
    Loading...
  6. 2026-04-17Upload Qwen3_5ForConditionalGeneration0ce223c5.1 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration