Instructions to use DarkArtsForge/Savage-Sands-12B-MPOA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarkArtsForge/Savage-Sands-12B-MPOA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DarkArtsForge/Savage-Sands-12B-MPOA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DarkArtsForge/Savage-Sands-12B-MPOA")
model = AutoModelForCausalLM.from_pretrained("DarkArtsForge/Savage-Sands-12B-MPOA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

NeMo
How to use DarkArtsForge/Savage-Sands-12B-MPOA with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DarkArtsForge/Savage-Sands-12B-MPOA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarkArtsForge/Savage-Sands-12B-MPOA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarkArtsForge/Savage-Sands-12B-MPOA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DarkArtsForge/Savage-Sands-12B-MPOA

SGLang

How to use DarkArtsForge/Savage-Sands-12B-MPOA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DarkArtsForge/Savage-Sands-12B-MPOA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarkArtsForge/Savage-Sands-12B-MPOA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DarkArtsForge/Savage-Sands-12B-MPOA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarkArtsForge/Savage-Sands-12B-MPOA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DarkArtsForge/Savage-Sands-12B-MPOA with Docker Model Runner:
```
docker model run hf.co/DarkArtsForge/Savage-Sands-12B-MPOA
```

Naphula commited on 16 days ago

Commit

a9f1b65

verified ·

1 Parent(s): 2d4f448

Create README.md

Browse files

Files changed (1) hide show

README.md +358 -0

README.md ADDED Viewed

	@@ -0,0 +1,358 @@

+---
+base_model:
+- DarkArtsForge/Savage-Sands-12B
+datasets:
+- OccultAI/illuminati_imatrix_v1
+language:
+- en
+library_name: transformers
+license: apache-2.0
+tags:
+- creative
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- fiction writing
+- story generation
+- scene continue
+- storytelling
+- fiction story
+- science fiction
+- romance
+- all genres
+- story
+- writing
+- vivid prosing
+- vivid writing
+- fiction
+- roleplaying
+- float32
+- swearing
+- rp
+- horror
+- della
+- mistral
+- nemo
+- merge
+- mergekit
+widget:
+  - text: "Savage-Sands-12B"
+    output:
+      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/-I_Iw69w2x9WNmk-iA2oE.png
+---
+<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/49d0YkIIJ_T9JeZ3gkwZ_.mpga"></audio>
+> [!CAUTION]
+> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **ChatML** chat template.
+>
+<!DOCTYPE html>
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Crimson+Text:ital,wght@0,400;0,700;1,400&family=Uncial+Antiqua&display=swap');
+body {
+  font-family: 'Crimson Text', serif;
+  color: #4A3F35; /* Faded Ink Brown */
+  line-height: 1.6;
+  margin: 0;
+  padding: 0;
+  background-color: #281E18; /* Dark Wood Desk */
+}
+b, strong {
+  color: #8C1C13; /* Crimson Seal */
+}
+.grimoire-text {
+  font-family: 'Uncial Antiqua', cursive;
+  color: #3D352A; /* Dark Ink */
+  position: relative;
+  z-index: 2;
+  margin-left: 0.2em;
+  text-shadow: 0 0 10px #A49687;
+}
+/* Section styling */
+.section-container {
+  background-color: rgba(245, 235, 218, 0.05);
+  margin-bottom: 30px;
+  position: relative;
+  overflow: hidden;
+  border-bottom: 1px solid rgba(140, 28, 19, 0.3); /* Faded Crimson Border */
+  box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2);
+}
+.section-header {
+  display: flex;
+  align-items: center;
+  background-color: rgba(140, 28, 19, 0.06);
+  padding: 10px 20px;
+}
+.section-indicator {
+  width: 8px;
+  height: 20px;
+  background-color: #8C1C13;
+  margin-right: 15px;
+  box-shadow: 0 0 8px rgba(140, 28, 19, 0.4);
+}
+.section-title {
+  font-family: 'Uncial Antiqua', cursive;
+  color: #4A3F35;
+  font-size: 1.4rem;
+  margin: 0;
+  letter-spacing: 1px;
+  font-weight: 400;
+  text-transform: capitalize;
+}
+.section-content {
+  padding: 20px;
+  font-family: 'Crimson Text', serif;
+  color: #4A3F35;
+  line-height: 1.7;
+}
+/* Title styling */
+.title-container {
+  background-color: transparent;
+  position: relative;
+  overflow: hidden;
+  margin-bottom: 40px;
+  border-left: 3px solid #8C1C13;
+  box-shadow: 0 6px 20px rgba(0, 0, 0, 0.2);
+}
+.title-wrapper {
+  position: relative;
+  z-index: 2;
+  padding: 25px 20px 30px 30px;
+}
+.title-main {
+  color: #3D352A;
+  font-size: 1.8rem;
+  font-weight: 700;
+  margin: 0;
+  letter-spacing: 2px;
+  display: inline-block;
+  position: relative;
+  text-transform: uppercase;
+}
+/* Subheading styling */
+.subheading {
+  font-family: 'Uncial Antiqua', cursive;
+  color: #7B5E4A; /* Lighter Ink Brown */
+  font-size: 1.1rem;
+  margin-top: 20px;
+  margin-bottom: 15px;
+  font-weight: 400;
+  border-bottom: 1px dashed rgba(123, 94, 74, 0.4);
+  display: inline-block;
+  text-transform: uppercase;
+  letter-spacing: 1px;
+}
+/* Links */
+a {
+  color: #7B5E4A;
+  text-decoration: none;
+  font-weight: bold;
+}
+a:hover {
+  text-decoration: underline;
+  color: #8C1C13; /* Crimson Seal on hover */
+}
+/* List Styling - Goetia Icons */
+ul {
+  list-style: none; /* CRITICAL: This hides the default marker causing the blue box */
+  padding-left: 1.6em;
+}
+ul li {
+  position: relative;
+  margin-bottom: 0.6em;
+}
+ul li::before {
+  content: "\26E7"; /* ⛧ Inverted Pentagram */
+  /* FALLBACK PROTECTION: */
+  /* This ensures that if your main font lacks the symbol, it grabs it from the system/OS symbols */
+  font-family: "Segoe UI Symbol", "Apple Symbols", "Noto Sans Symbols", "DejaVu Sans", sans-serif;
+  position: absolute;
+  left: -1.4em;
+  /* Fiery Styling */
+  color: #CC0000; /* Strong red base */
+  font-size: 1.5rem; /* Larger */
+  font-weight: normal; /* Icons often render cleaner without 'bold' at this size */
+  top: -5px; /* Vertical alignment fix */
+  /* Static Fire Glow (No Animation/Low CPU cost) */
+  /* Layer 1: Slight dark drop shadow for depth */
+  /* Layer 2: Orange-red ambient glow */
+  text-shadow: 1px 1px 1px rgba(0,0,0,0.4), 0 0 5px #FF5500;
+  background-color: transparent;
+}
+/* Container */
+.container {
+  max-width: 1200px;
+  margin: 20px auto;
+  padding: 40px 20px;
+  background-color: #F5EBDA; /* Aged Parchment */
+  background-image:
+    radial-gradient(circle at 10% 10%, rgba(140, 28, 19, 0.04) 0%, transparent 50%),
+    radial-gradient(circle at 90% 80%, rgba(61, 53, 42, 0.06) 0%, transparent 50%);
+  min-height: calc(100vh - 40px);
+  border: 1px solid #C8BBAA; /* Parchment Edge */
+  border-radius: 3px;
+  box-shadow: 0 8px 32px rgba(0, 0, 0, 0.3);
+}
+</style>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Savage Sands 12B MPOA</title>
+</head>
+<body>
+<div class="container">
+  <div class="title-container">
+    <div class="title-wrapper">
+      <h1 class="title-main">
+        <span class="grimoire-text">🏜️ Savage Sands 12B MPOA</span>
+      </h1>
+    </div>
+</div>
+<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/-I_Iw69w2x9WNmk-iA2oE.png" alt="Goetia Grimoire" style="width:100%; border-radius: 3px; margin-bottom: 30px; border: 1px solid #C8BBAA;">
+  <div class="section-container">
+    <div class="section-content"><font face="verdana" size="2">
+<details>This image depicts a high-stakes confrontation in a desolate, sandy environment. At the center of the action is a fierce duel between a heavily armored human warrior and a monstrous, winged demon. The warrior, seen from the side, is equipped with a gold-colored <b>Trojan-style helmet</b>. He lunges forward, gripping a <b>gladius</b>—a short, broad-bladed Roman sword—with both hands. His armor is dark and intricate, consisting of layered plates and a tattered, loincloth-like skirt that fans out with his movement.
+Facing him is a formidable <b>demon</b>. The creature has pale, muscular gray skin and massive, leathery <b>bat-like wings</b> that span a large portion of the background. It has a snarling, animalistic face with horns and is brandishing a long, wicked-looking <b>spear</b>, which it uses to block the warrior's advance. The demon's pose is agile and predatory, mirroring the intensity of the warrior's strike.
+The battle takes place on a series of flat, circular <b>stepping stones</b> scattered across a dry, dusty landscape. In the bottom right foreground, another figure is partially visible, huddled on the ground and clad in white robes with a red sash, seemingly caught in the middle of this epic struggle. The background is filled with soft, hazy clouds and distant rock formations, giving the scene a timeless, mythological feel.</font></details>
+  </div></div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">🌵 12B Roleplay</h2>
+    </div>
+    <div class="section-content"><font face="verdana">
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). The [main model](https://huggingface.co/DarkArtsForge/Savage-Sands-12B) was merged using the [della](https://arxiv.org/abs/2406.11617) merge method with unablated donors, and therefore has some refusals.
+For a fully **uncensored** version, see [this page](https://huggingface.co/DarkArtsForge/Savage-Sands-12B-MPOA) which was manually calibrated with `scale 1.7`.
+<details><b>This model is highly resistant to standard ablation methods like MPOA.</b> More than most Nemo 12Bs.
+Which is strange considering the `della` method was used with `normalize: false` which is basically like a mild form of pre-ablation.
+I tested several setups, and while lower values like scale 1.0 or 1.1 unlocked most refusals, there was a particular instruction prompt it still kept refusing.
+Even at scale 1.5, it would overtly refuse, and claim it wasn't "safe or appropriate" and that it "couldn't be done".
+I had to crank it up even higher in order to fully uncensor the model.
+**The minimum threshold was identified: `scale 1.7` applied to all layers `0-39`.**
+Attempting to only apply to layers 11-39 caused it to hallucinate a "corrected term" to swap out the correct term prompted it with, which was another direct form of covert non-compliance.
+Attempting to only apply to layers 4-39 caused additional non-compliant "false corrections". **Every layer must be ablated for this model in order to uncensor it.** There seem to be hidden forms of covert non-compliance embedded in the earliest layers, even lm_head. **Despite being low on the graph, these early layers still contribute toward refusal of prompts.**
+**When using scale 1.7 on all 40 layers, it uses a CORRECT correction (grammatical, not changing words) which is FULLY compliant, with no refusals or covert attempts to change topics.**
+So if you want the model as smart as possible then use the unablated version with jailbreak. But if you require built-in no refusals, the MPOA version is also quite creative.
+![Sands_Chart](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/6TklEDPfzuGvo9Wn90OfE.png)</details>
+</div>
+  </div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">⚙️ YAML Configuration</h2>
+    </div>
+    <div class="section-content"><font face="verdana">
+```yaml
+architecture: MistralForCausalLM
+base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
+models:
+  - model: B:/12B/inflatebot--MN-12B-Mag-Mell-R1
+    parameters:
+      weight: 0.5
+      density: 0.9
+      epsilon: 0.09
+  - model: B:/12B/taozi555--MN-12B-Mag-Mell-R1-KTO
+    parameters:
+      weight: 0.5
+      density: 0.9
+      epsilon: 0.09
+  - model: B:/12B/UniLLMer--GslayerKaa
+    parameters:
+      weight: 0.5
+      density: 0.9
+      epsilon: 0.09
+  - model: B:/12B/redrix--GodSlayer-12B-ABYSS
+    parameters:
+      weight: 0.5
+      density: 0.9
+      epsilon: 0.09
+merge_method: della
+parameters:
+  lambda: 1.0
+  normalize: false
+  int8_mask: false
+  rescale: true
+dtype: float32
+out_dtype: bfloat16
+tokenizer:
+  source: B:/12B/taozi555--MN-12B-Mag-Mell-R1-KTO
+name: 🏜️ Savage-Sands-12B
+```
+</div>
+  </div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">🔍 Merge Audit</h2>
+    </div>
+    <div class="section-content"><font face="verdana">
+<pre>
+[DELLA Audit] Layer: model.layers.33.mlp.down_proj.weight | Lambda=1.00
+  [BASE] mistralai--Mistral-Nemo-Instruct-2407
+  UniLLMer--GslayerKaa                              : ████████████████                                    33.3% (W:0.50 D:0.90 N:4.89 E:0.09)
+  inflatebot--MN-12B-Mag-Mell-R1                    : ████████                                            17.7% (W:0.50 D:0.90 N:2.59 E:0.09)
+  redrix--GodSlayer-12B-ABYSS                       : ███████████████                                     31.3% (W:0.50 D:0.90 N:4.59 E:0.09)
+  taozi555--MN-12B-Mag-Mell-R1-KTO                  : ████████                                            17.7% (W:0.50 D:0.90 N:2.59 E:0.09)
+[DELLA Audit] Layer: model.layers.33.mlp.gate_proj.weight | Lambda=1.00
+  [BASE] mistralai--Mistral-Nemo-Instruct-2407
+  UniLLMer--GslayerKaa                              : ███████████████████                                 38.5% (W:0.50 D:0.90 N:7.05 E:0.09)
+  inflatebot--MN-12B-Mag-Mell-R1                    : ███████                                             14.8% (W:0.50 D:0.90 N:2.70 E:0.09)
+  redrix--GodSlayer-12B-ABYSS                       : ███████████████                                     31.9% (W:0.50 D:0.90 N:5.84 E:0.09)
+  taozi555--MN-12B-Mag-Mell-R1-KTO                  : ███████                                             14.8% (W:0.50 D:0.90 N:2.71 E:0.09)
+</pre>
+</font></div>
+  </div>
+</html>