nsfw

furry

Furry

conversational

text-generation-inference

Model card Files Files and versions

xet

Community

Instructions to use Mawdistical/Incandescent-Malevolence-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use Mawdistical/Incandescent-Malevolence-70B with Transformers:

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

pipe = pipeline("text-generation", model="Mawdistical/Incandescent-Malevolence-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Mawdistical/Incandescent-Malevolence-70B")
model = AutoModelForMultimodalLM.from_pretrained("Mawdistical/Incandescent-Malevolence-70B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mawdistical/Incandescent-Malevolence-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mawdistical/Incandescent-Malevolence-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mawdistical/Incandescent-Malevolence-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mawdistical/Incandescent-Malevolence-70B

SGLang

How to use Mawdistical/Incandescent-Malevolence-70B 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 "Mawdistical/Incandescent-Malevolence-70B" \
    --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": "Mawdistical/Incandescent-Malevolence-70B",
		"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 "Mawdistical/Incandescent-Malevolence-70B" \
        --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": "Mawdistical/Incandescent-Malevolence-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mawdistical/Incandescent-Malevolence-70B with Docker Model Runner:
```
docker model run hf.co/Mawdistical/Incandescent-Malevolence-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Incandescent-Malevolence-70B

Model Thumbnail

Explicit Content Warning

Join our Discord Community →

Support Mawdistical finetunes here
Thank you fizz for the help on this model.
Support her here →

This is the world that faces us, a world called 'reality'.

✧ Browse the Incandescent-Malevolence-70B Collection

All Incandescent-Malevolence-70B Quants

✧ Recommended Settings

temperature: 0.6-0.9
Experiment to find your taste.

✧ Technical Details

Base
↳ TheSkullery/Unnamed-Exp-70b-v0.7.A

Training
Training Tokenizer
↳ LLAMA
Reason: Its a LLAMA model...
Dataset
Entries
↳ 1200 Unique Set Scenarios from a pool of 40K
Entry Composition
↳ Mild & Heavy Violence
↳ Dark Themes
↳ Mild to Extensive NSFL
↳ Non lethal but enough to scare people.
↳ Heavy NSFW
↳ Triggered on user action or passively however RP is seen
↳ Castle Like Scenes
↳ Cityscapes Scenes
↳ (French) Noir Scenes
Creation Composition
↳ Hybrid Organic-Synthetic mix
Token Count
↳ 5.27 M
↳ Note: token count calculated solely on outputs.
Type
↳ Private In-House
Focus
↳ Male Leaning
↳ Anthro
↳ Xeno-Likeness
↳ Subtle Passive Negativity - Energy Matching