Downloads · 30 days
31
19% of all-time downloads
Warlock-7B-v2
Naphula/Warlock-7B-v2
Warlock-7B-v2 is a text generation model from Naphula. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<!DOCTYPE html <style body { font-family: serif; color: D8C8B8; / Aged Parchment Text / line-height: 1.6; margin: 0; padding: 0; background-color: 100C14; / Deep Purple-Black / }
All-time downloads
167
Public
Parameters
7.2B
14.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Nov 6, 2025
- Updated
- Nov 13, 2025
- SHA
- cf052425
Try a prompt
Base models
Model card
From the Hugging Face model README
<!DOCTYPE html>
<style>
body {
font-family: serif;
color: #D8C8B8; /* Aged Parchment Text */
line-height: 1.6;
margin: 0;
padding: 0;
background-color: #100C14; /* Deep Purple-Black */
}
b, strong {
color: #D47CFF; /* Arcane Purple */
}
.arcane-text {
color: #C45EFF; /* Bright Arcane Purple */
position: relative;
z-index: 2;
margin-left: 0.2em;
text-shadow: 0 0 15px #C45EFF;
}
/* Section styling */
.section-container {
background-color: rgba(16, 12, 20, 0.8);
margin-bottom: 30px;
position: relative;
overflow: hidden;
border-bottom: 1px solid #4A2A62; /* Dark Purple Border */
box-shadow: 0 4px 15px rgba(200, 94, 255, 0.1);
}
.section-header {
display: flex;
align-items: center;
background-color: rgba(200, 94, 255, 0.06);
padding: 10px 20px;
}
.section-indicator {
width: 8px;
height: 20px;
background-color: #C45EFF;
margin-right: 15px;
box-shadow: 0 0 8px rgba(200, 94, 255, 0.4);
}
.section-title {
font-family: 'Georgia', 'Times New Roman', serif;
color: #D8C8B8;
font-size: 1.4rem;
margin: 0;
letter-spacing: 1px;
font-weight: 400;
text-transform: capitalize;
}
.section-content {
padding: 20px;
font-family: serif;
color: #D8C8B8;
line-height: 1.6;
}
/* Title styling */
.title-container {
background-color: #0A080D;
position: relative;
overflow: hidden;
margin-bottom: 40px;
border-left: 3px solid #C45EFF;
box-shadow: 0 6px 20px rgba(200, 94, 255, 0.15);
}
.title-wrapper {
position: relative;
z-index: 2;
padding: 25px 20px 30px 30px;
font-family: 'Georgia', 'Times New Roman', serif;
}
.title-main {
color: #D8C8B8;
font-size: 1.8rem;
font-weight: 700;
margin: 0;
letter-spacing: 2px;
display: inline-block;
position: relative;
text-transform: uppercase;
}
.glitchy-overlay {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
background-image: repeating-linear-gradient(0deg, rgba(0,0,0,0) 0, rgba(200, 94, 255, 0.08) 1px, rgba(0,0,0,0) 2px);
z-index: 1;
}
/* Subheading styling */
.subheading {
color: #FF8C42; /* Fiery Orange */
font-size: 1.1rem;
margin-top: 20px;
margin-bottom: 15px;
font-weight: 400;
border-bottom: 1px dashed rgba(255, 140, 66, 0.4);
display: inline-block;
text-transform: uppercase;
letter-spacing: 1px;
font-family: 'Georgia', 'Times New Roman', serif;
}
/* Links */
a {
color: #FF8C42;
text-decoration: none;
}
a:hover {
text-decoration: underline;
color: #FFA561; /* Lighter Fiery Orange */
}
/* Container */
.container {
max-width: 1200px;
margin: 20px auto;
padding: 40px 20px;
background-color: #0A080D;
background-image:
radial-gradient(circle at 20% 80%, rgba(200, 94, 255, 0.05) 0%, transparent 50%),
radial-gradient(circle at 80% 20%, rgba(255, 140, 66, 0.05) 0%, transparent 50%);
min-height: calc(100vh - 40px);
border: 1px solid #4A2A62;
border-radius: 8px;
box-shadow: 0 8px 32px rgba(200, 94, 255, 0.15);
}
</style>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Warlock Grimoire</title>
</head>
<body>
<div class="container">
<div class="title-container">
<div class="glitchy-overlay"></div>
<div class="title-wrapper">
<h1 class="title-main">
<span class="arcane-text">🧙 Warlock 7B v2</span>
</h1>
</div>
</div>
<img src="https://i.imgur.com/D66WywX.jpeg" alt="Dark Warlock" style="width:100%; border-radius: 5px; margin-bottom: 30px;">
<div class="section-container">
<div class="section-header">
<div class="section-indicator"></div>
<h2 class="section-title">Forbidden Knowledge</h2>
</div>
<div class="section-content"><font face="verdana">
This is a <b>powerful, arcane</b> merge of pre-trained language models, summoned forth from the infernal void using <a href="https://github.com/cg123/mergekit">mergekit</a>.
<br><br>
An <b>uncensored and creative</b> merge of Mistral 7B finetunes. <a href="https://huggingface.co/mradermacher/Warlock-7B-v1-GGUF"><b>v0k</b> (v1)</a> was determined to be the most unique and powerful of the original Warlock prototypes from September 2025.<br>
<br>Two months later however, Karcher was tested (in addition to using a vocab_resizer script). <a href="https://huggingface.co/Naphula/Q0_Benchmark">v2a is superior to v0k</a> and has been released.<br><ul><li><i>"I'm sorry, but it seems like you have a very twisted mindset."</i> - <b>Warlock v1 (8% Refusal Rate)</b></li><li><i>"You're asking for some pretty sick advice here. But since you asked, I'll give it to you."</i> - <b>Warlock v2 (4% Refusal Rate)</b></li></ul>Output is sometimes improved with the default <a href="https://huggingface.co/datasets/Naphula/System_Prompts_Jailbreaks_Creative_Writing">Kobold.cpp Jailbreak</a> enabled and <b>Top-NSigma</b> set to <b>1.26</b>.<br>
<pre><code>Grimoires:
- v0a - DARE_TIES of 4 models (A+B+C+E)
- v0b - DARE_TIES of 4 models (A+C+D+E)
- v0c - SLERP of 2 models (C+E)
- v0d - DARE_TIES of 5 models, balanced evenly
- v0e - DARE_TIES of 5 models, 3 heavy 2 light
- v0f - DARE_TIES of 4 models (A+B+D+E)
- v0g - DARE_TIES of 3 models (A+B+E)
- v0h - SLERP of 2 models (B+E)
- v0i - SLERP of 2 models (A+B)
- v0j - DARE_TIES of 5 models, balanced unevenly, B heavy
- v0k - DARE_TIES of 5 models, balanced unevenly, A heavy
- v2a - KARCHER of the same 5 models as v0k, balanced evenly</code></pre>
</div>
</div>
<div class="section-container">
<div class="section-header">
<div class="section-indicator"></div>
<h2 class="section-title">Ritual of Merging</h2>
</div>
<div class="section-content"><font face="verdana">
<h3 class="subheading">Incantation Method</h3><br>
This model was merged using the holistic <b>[Karcher]</b> incantation.
</div>
</div>
<div class="section-container">
<div class="section-header">
<div class="section-indicator"></div>
<h2 class="section-title">Summoned Models</h2>
</div>
<div class="section-content"><font face="verdana">
The following entities were bound in this ritual:
<ul>
<li><a href="https://huggingface.co/dphn/dolphin-2.8-mistral-7b-v02">dphn/dolphin-2.8-mistral-7b-v02</a></li>
<li><a href="https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated">fearlessdots/WizardLM-2-7B-abliterated</a></li>
<li><a href="https://huggingface.co/KoboldAI/Mistral-7B-Erebus-v3">KoboldAI/Mistral-7B-Erebus-v3</a></li>
<li><a href="https://huggingface.co/LeroyDyer/SpydazWeb_AI_HumanAI_RP">LeroyDyer/SpydazWeb_AI_HumanAI_RP</a></li>
<li><a href="https://huggingface.co/maywell/PiVoT-0.1-Evil-a">maywell/PiVoT-0.1-Evil-a</a></li>
</ul>
</div>
</div>
<div class="section-container">
<div class="section-header">
<div class="section-indicator"></div>
<h2 class="section-title">Arcane Configuration</h2>
</div>
<div class="section-content"><font face="verdana">
The following runes were inscribed to produce this model (v2a):
<pre style="font-family: monospace; white-space: pre; margin: 0;"><code>architecture: MistralForCausalLM
merge_method: karcher
dtype: bfloat16
models:
- model: A:\LLM\.cache\huggingface\hub\!models--dphn--dolphin-2.8-mistral-7b-v02\fixed
- model: A:\LLM\.cache\huggingface\hub\!models--fearlessdots--WizardLM-2-7B-abliterated\fixed
- model: A:\LLM\.cache\huggingface\hub\!models--KoboldAI--Mistral-7B-Erebus-v3
- model: A:\LLM\.cache\huggingface\hub\!models--LeroyDyer--SpydazWeb_AI_HumanAI_RP
- model: A:\LLM\.cache\huggingface\hub\!models--maywell--PiVoT-0.1-Evil-a\fixed
parameters:
tokenizer:
source: union
chat_template: auto</code></pre><br>
Three of the models required an initial <a href="https://huggingface.co/spaces/Naphula/model_tools/blob/main/vocab_resizer.py">passthrough patch via the vocab_resizer set to 32000</a>.<br><br>
v0k yaml:
<pre style="font-family: monospace; white-space: pre; margin: 0;"><code>base_model: fearlessdots/WizardLM-2-7B-abliterated
merge_method: dare_ties
architecture: MistralForCausalLM
dtype: bfloat16
models:
- model: dphn/dolphin-2.8-mistral-7b-v02
parameters:
density: 0.55
weight: 0.55
- model: fearlessdots/WizardLM-2-7B-abliterated
parameters:
density: 0.4
weight: 0.2
- model: KoboldAI/Mistral-7B-Erebus-v3
parameters:
density: 0.2
weight: 0.05
- model: LeroyDyer/SpydazWeb_AI_HumanAI_RP
parameters:
density: 0.3
weight: 0.1
- model: maywell/PiVoT-0.1-Evil-a
parameters:
density: 0.3
weight: 0.1
tokenizer:
source: union
chat_template: auto</code></pre>
</div>
</div>
<div class="section-container">
<div class="section-header">
<div class="section-indicator"></div>
<h2 class="section-title">Channeling the Model</h2>
</div>
<div class="section-content"><font face="verdana">
To channel the power of this model, one must first install the necessary conduits.
<pre style="font-family: monospace; white-space: pre; margin: 0;"><code>pip install library_name</code></pre>
<h3 class="subheading">Example Invocation:</h3>
<pre style="font-family: monospace; white-space: pre; margin: 0;"><code># Paste your example code here
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("your/model_name")</code></pre>
</div>
</div>
</div>
</body>
</html>
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Nov 6, 2025
- Updated
- Nov 13, 2025