nsfw

furry

anthro

dark

chat

conversational

text-generation-inference

Model card Files Files and versions

xet

Community

Instructions to use Mawdistical/Kuwutu-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use Mawdistical/Kuwutu-7B with Transformers:

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

pipe = pipeline("text-generation", model="Mawdistical/Kuwutu-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mawdistical/Kuwutu-7B")
model = AutoModelForCausalLM.from_pretrained("Mawdistical/Kuwutu-7B")
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

vLLM

How to use Mawdistical/Kuwutu-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mawdistical/Kuwutu-7B"
# 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/Kuwutu-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mawdistical/Kuwutu-7B

SGLang

How to use Mawdistical/Kuwutu-7B 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/Kuwutu-7B" \
    --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/Kuwutu-7B",
		"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/Kuwutu-7B" \
        --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/Kuwutu-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mawdistical/Kuwutu-7B with Docker Model Runner:
```
docker model run hf.co/Mawdistical/Kuwutu-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kuwutu-7B

Model Thumbnail

Explicit Content Warning

Join our Discord Community →

Support Mawdistical finetunes here

pleasurable Pain, or is it pain in pleasure?

✧ Browse the Kuwutu-7B Collection

All Kuwutu-7B Quants

✧ Recommended Settings

temperature: 0.6-0.9
Experiment to find your taste.

✧ Finetuned Set Info

Entries
↳ 5400~ Unique Set Scenarios from a pool of 40K

Entry Composition
↳ Heavy Violence
↳ Dark Themes
↳ Extensive NSFL
↳ Non-lethal but enough to scare people.
↳ Heavy NSFW
↳ Triggered on user action or passively wherever RP is seen
↳ Modern City Scenes
↳ Dystopia Scenes
↳ Grey Line Consent Scenes
↳ Note: Grey line consent is where consent may be mutual but unspoken at times or considered to be accepted by actions either by character or user. May lead to over-possessiveness in some instances.

Creation Composition
↳ Hybrid Organic-Synthetic mix

Token Count
↳ 21.3 M
↳ Note: token count calculated solely on outputs.

Type
↳ Private In-House

Focus
↳ Male Leaning
↳ Anthro
↳ Xeno-Likeness
↳ Passive Negative Bias with mild narcissistic tendencies, matches energy with subtle languidness.

✧ Technical Details

Base Model
↳ Aurore-Reveil/Koto-Small-7B-IT

Base Model Pre-Training Datasets
Delta Vector
↳ Hydrus-General-Reasoning
↳ Hydrus-IF-Mix-Ai2
↳ Hydrus-Army-Inst
↳ Hydrus-AM-thinking-Science
↳ Hydrus-AM-Thinking-Code-Filtered
↳ Hydrus-AM-Thinking-IF-No-Think
↳ Hydrus-Tulu-SFT-Mix-V2
↳ Hydrus-System-Chat-2.0
↳ Orion-Praxis-Co-Writer
↳ Orion-Co-Writer-51K
↳ Orion-Creative_Writing-Complexity
↳ Orion-vanilla-backrooms-claude-sharegpt
↳ Hydrus-AM-Thinking-Multi-Turn
PocketDoc
↳ Dans-Failuremaxx-Adventure
↳ Dans-Logicmaxx-SAT-AP
↳ Dans-MemoryCore-CoreCurriculum-Small
↳ Dans-Taskmaxx-DataPrepper
↳ Dans-Prosemaxx-Instructwriter-Long
↳ Dans-Prosemaxx-InstructWriter-ZeroShot-2
↳ Dans-Prosemaxx-InstructWriter-ZeroShot-3
↳ Dans-Prosemaxx-InstructWriter-Continue-2
↳ Dans-Systemmaxx

✧ Credits

Furry Governor
↳ @Mawnipulator
Government Bodies
↳ @ArtusDev
↳ @SaisExperiments
↳ ALLURA-ORG
Additional Credits
↳ @Fizzarolli
↳ @Delta-Vector

License: CC BY-NC 4.0

Services such as Arli AI, PygmalionAI, and Featherless AI are granted a CC BY-ND 4.0 license for use of this model.