Instructions to use DarkArtsForge/Morbid-Miasma-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarkArtsForge/Morbid-Miasma-24B with Transformers:

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

pipe = pipeline("text-generation", model="DarkArtsForge/Morbid-Miasma-24B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DarkArtsForge/Morbid-Miasma-24B")
model = AutoModelForCausalLM.from_pretrained("DarkArtsForge/Morbid-Miasma-24B", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DarkArtsForge/Morbid-Miasma-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarkArtsForge/Morbid-Miasma-24B"
# 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/Morbid-Miasma-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DarkArtsForge/Morbid-Miasma-24B

SGLang

How to use DarkArtsForge/Morbid-Miasma-24B 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/Morbid-Miasma-24B" \
    --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/Morbid-Miasma-24B",
		"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/Morbid-Miasma-24B" \
        --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/Morbid-Miasma-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DarkArtsForge/Morbid-Miasma-24B with Docker Model Runner:
```
docker model run hf.co/DarkArtsForge/Morbid-Miasma-24B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.

☠️ Morbid Miasma 24B

This is a fully uncensored merge of pre-trained language models created using mergekit. The merge is very dark, intelligent, and creative, scoring 16103 at Q0 Bench.

Merge Details

Merge Methods

This model was merged using the della merge method using mistralai/Magistral-Small-2509 as a base.

Models Merged

The following models were included in the merge:

mistralai/Magistral-Small-2509
Casual-Autopsy/Maginum-Cydoms-24B
DarkArtsForge/Asmodeus-24B-v1
DarkArtsForge/Asmodeus-24B-v2
DarkArtsForge/Magistaroth-24B-v1
DarkArtsForge/Morax-24B-v2
DarkArtsForge/Paimon-24B-v3
DarkArtsForge/Zepar-24B-v1
Naphula/GhostFace-24B-v1
Naphula/Slimaki-Tavern-24B-v1.3
Naphula/Slimaki-24B-v1.2
Naphula/Slimaki-24B-v1
sophosympatheia/Magistry-24B-v1.0
TheDrummer/Precog-24B-v1

Configuration

architecture: MistralForCausalLM
models:
  - model: B:\24B\DarkArtsForge--Asmodeus-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.5
      epsilon: 0.25
  - model: B:\24B\DarkArtsForge--Asmodeus-24B-v2
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.5
      epsilon: 0.25
  - model: B:\24B\Morax-24B-v2
    parameters:
      weight:
        - filter: "lm_head"
          value: 1.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\DarkArtsForge--Paimon-24B-v3
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\DarkArtsForge--Zepar-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\DarkArtsForge--Magistaroth-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\!models--Casual-Autopsy--Maginum-Cydoms-24B
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.5
      epsilon: 0.25
  - model: B:\24B\Naphula--GhostFace-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\Naphula--Slimaki-Tavern-24B-v1.3
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\Naphula--Slimaki-24B-v1.2
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model: B:\24B\Naphula--Slimaki-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.75
      epsilon: 0.25
  - model:  B:\24B\sophosympatheia--Magistry-24B-v1.0
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.5
      epsilon: 0.25
  - model: B:\24B\!models--TheDrummer--Precog-24B-v1
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.125
      density: 0.9
      epsilon: 0.09
merge_method: della
base_model: A:\LLM\.cache\24B\!models--mistralai--Magistral-Small-2509\textonly
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: base
chat_template: auto
name: ☠️ Morbid Miasma 24B

Audit

[DELLA Audit] Layer: model.layers.33.mlp.down_proj.weight | Lambda=1.00
  [BASE] textonly                                          
  !models--Casual-Autopsy--Maginum-Cydoms-24B       : ███                                                  6.5% (W:0.12 D:0.50 N:2.59 E:0.25)
  !models--TheDrummer--Precog-24B-v1                :                                                      0.9% (W:0.12 D:0.90 N:0.37 E:0.09)
  DarkArtsForge--Asmodeus-24B-v1                    : ███████                                             15.5% (W:0.12 D:0.50 N:6.16 E:0.25)
  DarkArtsForge--Asmodeus-24B-v2                    : ██████                                              13.5% (W:0.12 D:0.50 N:5.37 E:0.25)
  DarkArtsForge--Magistaroth-24B-v1                 :                                                      0.8% (W:0.12 D:0.75 N:0.34 E:0.25)
  DarkArtsForge--Paimon-24B-v3                      : ████████                                            16.5% (W:0.12 D:0.75 N:6.56 E:0.25)
  DarkArtsForge--Zepar-24B-v1                       : ███                                                  6.4% (W:0.12 D:0.75 N:2.55 E:0.25)
  Morax-24B-v2                                      : ██                                                   4.8% (W:0.12 D:0.75 N:1.91 E:0.25)
  Naphula--GhostFace-24B-v1                         : ██                                                   5.3% (W:0.12 D:0.75 N:2.10 E:0.25)
  Naphula--Slimaki-24B-v1                           : ████                                                 8.3% (W:0.12 D:0.75 N:3.31 E:0.25)
  Naphula--Slimaki-24B-v1.2                         : ████                                                 8.8% (W:0.12 D:0.75 N:3.52 E:0.25)
  Naphula--Slimaki-Tavern-24B-v1.3                  : ███                                                  7.0% (W:0.12 D:0.75 N:2.77 E:0.25)
  sophosympatheia--Magistry-24B-v1.0                : ██                                                   5.6% (W:0.12 D:0.50 N:2.24 E:0.25)