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

Naphula/Warlock-7B-v3-Uncensored

Naphula Mistral 7.2B
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/Naphula%2FWarlock-7B-v3-Uncensored"
Response includes
  • classification m5
  • files 14
  • hub_downloads_all_time 109
  • author_summary 22 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
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 · lifetime
109
25 last 30d - stable
Likes
2
Descendants
3
in 3 direct forks
Model age
8mo ago
created 2026-01-18
Downloads over time
Now112→from16↑600%
11488512216 on Jan 21112 on Oct 11112 on Oct 7JanMarMayJulSep
Jan 21 → Oct 11 · 77 snapshots · spans 263 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 · 67 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 mistral karcher merge mergekit base_model:Endevor/EndlessRP-v3-7B base_model:merge:Endevor/EndlessRP-v3-7B base_model:Endevor/InfinityRP-v1-7B base_model:merge:Endevor/InfinityRP-v1-7B base_model:Gryphe/MythoMist-7b base_model:merge:Gryphe/MythoMist-7b base_model:Gryphe/Tiamat-7b

Related

Total size
13.5 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-18 11:34

Files by quantization

Auxiliary files 14 files 13.5 GB
model-00002-of-00003.safetensors 4.58 GB cdbd806b download
model-00001-of-00003.safetensors 4.55 GB 79b66d55 download
model-00003-of-00003.safetensors 4.36 GB f672df97 download
tokenizer.json 3.34 MB 65d75227 download
ablit_proj 1.53 MB 4d91a5fb download
tokenizer.model 482 KB dadfd56d download
model.safetensors.index.json 23.7 KB 9151577d download
README.md 1.97 KB 2c767852 download
.gitattributes 1.53 KB 92c158af download
Warlock-7B-v2-Q8_K_XL.txt 1.24 KB 665d22e2 download
tokenizer_config.json 1.04 KB 6ca0942d download
config.json 635 B 57cf2c1f download
special_tokens_map.json 437 B e3761445 download
chat_template.jinja 199 B 8e7ce6a7 download

README current version from Hugging Face


license: apache-2.0
base_model:

  • argilla/CapybaraHermes-2.5-Mistral-7B
  • berkeley-nest/Starling-LM-7B-alpha
  • cgato/TheSpice-7b-v0.1.1
  • cgato/Thespis-CurtainCall-7b-v0.3
  • chargoddard/loyal-piano-m7
  • dphn/dolphin-2.2.1-mistral-7b
  • dreamgen/WizardLM-2-7B
  • Endevor/EndlessRP-v3-7B
  • Endevor/InfinityRP-v1-7B
  • fblgit/UNA-TheBeagle-7b-v1
  • Gryphe/MythoMist-7b
  • Gryphe/Tiamat-7b
  • HuggingFaceH4/zephyr-7b-beta
  • Intel/neural-chat-7b-v3-1
  • KoboldAI/Mistral-7B-Erebus-v3
  • KoboldAI/Mistral-7B-Holodeck-1
  • LakoMoor/Silicon-Alice-7B
  • Locutusque/Hercules-3.1-Mistral-7B
  • maywell/PiVoT-0.1-Evil-a
  • mistralai/Mistral-7B-v0.1
  • mlabonne/Mistralpaca-7B
  • mlabonne/NeuralBeagle14-7B
  • mlabonne/NeuralHermes-2.5-Mistral-7B
  • NeverSleep/Noromaid-7B-0.4-DPO
  • NousResearch/Hermes-2-Pro-Mistral-7B
  • openchat/openchat-3.5-0106
  • QuixiAI/samantha-1.2-mistral-7b
  • SanjiWatsuki/Kunoichi-DPO-v2-7B
  • senseable/WestLake-7B-v2
  • teknium/airoboros-mistral2.2-7b
  • teknium/Hermes-Trismegistus-Mistral-7B
  • teknium/Mistral-Trismegistus-7B
  • teknium/OpenHermes-2.5-Mistral-7B
    tags:
  • karcher
  • mistral
  • merge
  • mergekit
    widget:

[!CAUTION]
⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Non-Tekken or Alpaca chat template.

[!NOTE]
Note: There are two versions of Warlock v3:

  • The regular version is censored and has refusals but might be smarter overall.
  • The uncensored version does not have refusals but might sometimes produce chinese output.

🧙 Warlock 7B v3 Uncensored

No refusals (MPOA) version

Warlock

README history 1 version

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

  1. 2026-01-18Create README.md1d16ed82 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