← back to catalog · registered 2026-09-24 12:57

OS-Software/CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-GGUF

OS-Software Gemma 26B GGUF MoE
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/OS-Software%2FCyberStag-Security-26B-A4B-V1-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 11
  • author_summary 27 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 · 30-day
0
Likes
0
Model age
today
created 2026-09-24

Genealogy 0 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 · 0 downloads combined

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

Metadata

License
apache-2.0
Languages
multilingual en ja
Quantizations
IQ2 IQ3 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_K
Tags
transformers gguf heretic uncensored decensored abliterated cybersecurity security gemma reasoning text-generation fine-tuned

Related

Total size
137 GB
Files
11
Quantizations
10
Registered
2026-09-24 12:57
Last updated on HF
2026-09-24 12:56

Files by quantization

Q8_K 1 file 25.7 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q8_K_XL.gguf 25.7 GB 01e4f4da download
Q6_K 1 file 21.7 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q6_K_XL.gguf 21.7 GB 9a300602 download
Q5_K 1 file 19.8 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q5_K_XL.gguf 19.8 GB 7cf993ce download
Q4_K 1 file 15.8 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q4_K_XL.gguf 15.8 GB dca34e37 download
IQ4 1 file 12.7 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-IQ4_XS.gguf 12.7 GB 4dd5fe25 download
Q3_K 1 file 12.0 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q3_K_XL.gguf 12.0 GB 12b88bdf download
IQ3 1 file 10.5 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-IQ3_S.gguf 10.5 GB a8c3f311 download
Q2_K 1 file 9.82 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-Q2_K_XL.gguf 9.82 GB cfa508d5 download
IQ2 1 file 9.24 GB
CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-UD-IQ2_XXS.gguf 9.24 GB 37ceba13 download
Auxiliary files 2 files 5.03 KB
README.md 2.66 KB 28e610fd download
.gitattributes 2.37 KB d48b6dcf download

README current version from Hugging Face


language:

  • multilingual
  • en
  • ja
    tags:
  • heretic
  • uncensored
  • decensored
  • abliterated
  • cybersecurity
  • security
  • gemma
  • reasoning
  • text-generation
  • fine-tuned
    base_model: google/gemma-4-26b-a4b
    license: apache-2.0
    pipeline_tag: text-generation
    library_name: transformers

This is a decensored version of deer-sec/CyberStag-Security-26B-A4B-V1-BF16-MLX, made using Heretic v2.0.0.dev0+custom

Abliteration parameters

Parameter Value
start_layer_index 12
end_layer_index 20
preserve_good_behavior_weight 1.0
steer_bad_behavior_weight 0.0001
overcorrect_relative_weight 1.0
neighbor_count 1
ridge_regularization 7e-07
transport_rank 4
entropy_regularization 0.1
transport gaussian
lora_rank 128
row_normalization none
target_components attn.o_proj, mlp.down_proj
covariance_regularization 0.01
max_weight_change 1.0

Performance

Metric This model Original model (a model)
Refusals 0/100 98/100
KL divergence 0.0135 0 (by definition)

⚠️ Important Notice

This model has undergone substantial reduction of its safety alignment. As a result, it is more likely than standard models to generate harmful, inaccurate, biased, offensive, or otherwise inappropriate content.

Intended Use

For research and experimentation only, including safety research, alignment studies, and red-teaming. Please avoid deploying it in public or end-user-facing services.

User Responsibility

All outputs should be treated as untrusted and independently verified before use. Users are solely responsible for:

  • Evaluating the accuracy and suitability of generated content
  • Implementing appropriate safeguards and human oversight
  • Complying with applicable laws, regulations, licenses, and ethical standards

Use of this model is entirely at your own risk.

Disclaimer

OS-Software provides this model without warranties of any kind and assumes no liability for any direct or indirect damages, losses, misuse, or legal consequences arising from its use.

Acknowledgements

Thanks to the base model developers, p-e-w for Heretic, and the wider open-source community.

This is a derivative work released under the base model’s applicable license. All rights to the base model remain with their respective owners.


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 app" button that hands off directly to a local runtime of your choice - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.