Not-For-All-Audiences

Instructions to use BeaverLegacy/Smegmma-Deluxe-9B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeaverLegacy/Smegmma-Deluxe-9B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="BeaverLegacy/Smegmma-Deluxe-9B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BeaverLegacy/Smegmma-Deluxe-9B-v1")
model = AutoModelForCausalLM.from_pretrained("BeaverLegacy/Smegmma-Deluxe-9B-v1", 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 BeaverLegacy/Smegmma-Deluxe-9B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeaverLegacy/Smegmma-Deluxe-9B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BeaverLegacy/Smegmma-Deluxe-9B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BeaverLegacy/Smegmma-Deluxe-9B-v1

SGLang

How to use BeaverLegacy/Smegmma-Deluxe-9B-v1 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 "BeaverLegacy/Smegmma-Deluxe-9B-v1" \
    --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": "BeaverLegacy/Smegmma-Deluxe-9B-v1",
		"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 "BeaverLegacy/Smegmma-Deluxe-9B-v1" \
        --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": "BeaverLegacy/Smegmma-Deluxe-9B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BeaverLegacy/Smegmma-Deluxe-9B-v1 with Docker Model Runner:
```
docker model run hf.co/BeaverLegacy/Smegmma-Deluxe-9B-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Smegmma-9B-v1

Join our Discord! https://discord.gg/Nbv9pQ88Xb

BeaverAI team proudly presents

Smegmma Deluxe 9B v1 🧀

The sweet moist of Gemma 2, unhinged.

smeg - ghem - mah

An eRP model that will blast you with creamy moist. Finetuned by yours truly.

The first Gemma 2 9B RP finetune attempt!

What's New?

Engaging roleplay
- Less refusals / censorship
- Less commentaries / summaries
- More willing AI
- Better formatting
- Better creativity
Moist alignment

Notes

Refusals still exist, but a couple of re-gens may yield the result you want
Formatting and logic may be weaker at the start
- Make sure to start strong
May be weaker with certain cards, YMMV and adjust accordingly!
Want SmeGmma 27B now? Send me your credit card.

Sarah: You notice a girl staring at you as you walk to the bus stop on a warm breezy day. She is standing with her phone out, loitering in a shady patch under a tree off the path. She senses your attention and subtly beckons you over to her. As you approach her, the short girl stares directly in your eyes intently. Her tight clothes suggest a slim, athletic figure which is pleasing to look at. She grins as she sees your eyes wandering over her body. In a quiet but surprisingly deep and cool voice, she asks, "Do you like ###?"

User: "Uh, sure?"

Sarah: "Oh really? Because I bet you don't know how to do it right! Or else you wouldn't be just standing here awkwardly instead of ####ing me already!" She continues smiling, clearly not embarrassed. Then without waiting for any response she takes out a dil## the same size and shape as a ####. With confidence she positions it between her legs and slams the fake #### up against herself. She looks at you again while positioning the dil## like it was a real one. "So, what do you think of my skill level?"

BeaverAI/Smegmma-9B-v1h

Downloads last month: 42

Safetensors

Model size

10B params

Tensor type

BF16

Model tree for BeaverLegacy/Smegmma-Deluxe-9B-v1

Merges

4 models

Quantizations

3 models