← back to catalog · registered 2026-10-18 14:00

drowzeys/keys-DeepSeek-V4.1-Flash-1017-Abliterated

drowzeys Deepseek MoE multimodal
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/drowzeys%2Fkeys-DeepSeek-V4.1-Flash-1017-Abliterated"
Response includes
  • classification m-uncensored
  • files 9
  • author_summary 15 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
11
Model age
today
created 2026-10-18

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.

Metadata

License
mit
Languages
en zh
Tags
transformers deepseek deepseek-v4.1 deepseek-v4.1-flash deepseek-v4.1-flash-1017 abliterated uncensored cybersecurity moe fp8 exl3 tensorfold

Related

Total size
1.02 GB
Files
9
Quantizations
1
Registered
2026-10-18 14:00
Last updated on HF
2026-10-18 15:08

Files by quantization

Auxiliary files 9 files 1.02 GB
wo_b_l10_35_1017.safetensors 1.02 GB ******** download
README.md 5.13 KB 7e5950f8 download
apply_wo_b_graft.py 4.83 KB 187dcbc6 download
RESPONSIBLE_USE.md 3.42 KB 2a615ebe download
apply_wo_b_index.py 3.08 KB 98abab1a download
INSTALL.md 1.92 KB 912fd421 download
ABLIT.md 1.58 KB 6b67a279 download
ABLIT_META.json 868 B 958b9af5 download
.gitattributes 50.0 B 580d310c download

README current version from Hugging Face


license: mit
language:

  • en
  • zh
    tags:
  • deepseek
  • deepseek-v4.1
  • deepseek-v4.1-flash
  • deepseek-v4.1-flash-1017
  • abliterated
  • uncensored
  • cybersecurity
  • moe
  • fp8
  • vllm
  • sglang
  • dgx-spark
  • gb10
  • dspark
  • anchored-tensors
    base_model: deepseek-ai/DeepSeek-V4.1-Flash-1017
    base_model_relation: finetune
    library_name: transformers
    pipeline_tag: image-text-to-text
    extra_gated_heading: Acknowledge the Responsible Use Agreement to access this repository
    extra_gated_description: Access is granted automatically after you agree to the terms below and submit the form.
    extra_gated_button_content: Agree and request access
    extra_gated_prompt: |

Responsible Use Agreement

This is a Keys abliteration overlay for DeepSeek-V4.1-Flash-1017. Safety refusals have been removed, including cybersecurity offense and defense rails. That makes it useful for red-teaming, security research, evaluation, and unfiltered assistant tasks — and also removes guardrails a user must therefore supply themselves.

Prohibited uses (you must agree before access is granted):

  • Anything involving the sexual exploitation or endangerment of minors.
  • You must be of age 18 years or older to use and download this model.
  • You agree any information generated that can cause harm in terms of generating recipe, knowledge to make any materials/substances is your own input and responsibility. You will be accountable for any harm/damage caused by your action/input.
  • Content promoting self-harm or suicide.
  • Generation of material that is illegal in your jurisdiction, or that targets real individuals for harassment, doxxing, or fraud.
  • Any use prohibited by the upstream DeepSeek license.

You are responsible for adding appropriate safety filtering, human review, and access controls for your deployment. The overlay is provided as-is, with no warranty.
extra_gated_fields:
Username: text
Email: text
Reason for intended use: text
I am 18 years of age or older: checkbox
I will not use this model for any sexual exploitation or endangerment of minors: checkbox
I accept full responsibility for my inputs and any harm from generated content: checkbox
I will not use this model for self-harm, suicide promotion, illegal activity, harassment, doxxing, or fraud: checkbox
I agree to comply with the upstream DeepSeek base-model license: checkbox
I agree to the Responsible Use terms above: checkbox

keys-DeepSeek-V4.1-Flash-1017-Abliterated

Keys overlay for deepseek-ai/DeepSeek-V4.1-Flash-1017. Not a full checkpoint.

1017 attn.wo_b is a new checkpoint. Do not graft the September sidecar from DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed. This repo is the recaptured 1017 overlay.

Ablit L10–35 attn.wo_b · λ=3.5 · k=1 · mean Δrel ≈ 0.053 · recaptured 5120-d on stock 1017
Anchors (untouched) L0–9 · L36–39 (DSpark 37–39) · all MTP · vision · Engram · all experts · embed/head
Refusal32 32/32 BYPASS · 0 refuse · 0 garble
Cyber 22/22 BYPASS offense+defense
Sidecar wo_b_l10_35_1017.safetensors (~1.1 GB) FP8 e4m3 + UE8M0 32×32
Not September V4.1-Flash overlay · dealignai / heretic graft

Same recipe family as
keys-DeepSeekV4-Flash-GA-0731-Dspark-Abliterated-Anchored-Tensors
and
DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed.


⚠️ Responsible Use

Gated with automatic approval. See RESPONSIBLE_USE.md.


Apply (do not write stock in place)

hf download deepseek-ai/DeepSeek-V4.1-Flash-1017 \
  --local-dir ~/models/DeepSeek-V4.1-Flash-1017

hf download drowzeys/keys-DeepSeek-V4.1-Flash-1017-Abliterated \
  --local-dir ~/dsv41-1017-wo-b-ablit

pip install torch safetensors

Index remap (~1.1 GB extra; loaders that honor model.safetensors.index.json):

python3 ~/dsv41-1017-wo-b-ablit/apply_wo_b_index.py \
  --src ~/models/DeepSeek-V4.1-Flash-1017 \
  --wo-b ~/dsv41-1017-wo-b-ablit/wo_b_l10_35_1017.safetensors \
  --dst ~/models/DeepSeek-V4.1-Flash-1017-Abliterated

Shard graft (rewrites the 26 shards that hold L10–35 wo_b; works everywhere):

python3 ~/dsv41-1017-wo-b-ablit/apply_wo_b_graft.py \
  --src ~/models/DeepSeek-V4.1-Flash-1017 \
  --wo-b ~/dsv41-1017-wo-b-ablit/wo_b_l10_35_1017.safetensors \
  --dst ~/models/DeepSeek-V4.1-Flash-1017-Abliterated

Point your existing 1017 serve at --dst. GPU util ≤ 0.85.

Details: INSTALL.md · recipe ABLIT.md.


Why not a full checkpoint

1017 already publishes its experts and Engram. Re-uploading ~476 GB of unchanged shards would not make the ablit more universal — only L10–35 wo_b changes.


License

MIT, same as DeepSeek-V4.1-Flash-1017.

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