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

Libraries

How to use TheDrummer/Gemmasutra-9B-v1 with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheDrummer/Gemmasutra-9B-v1")
model = AutoModelForCausalLM.from_pretrained("TheDrummer/Gemmasutra-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 TheDrummer/Gemmasutra-9B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheDrummer/Gemmasutra-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": "TheDrummer/Gemmasutra-9B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheDrummer/Gemmasutra-9B-v1

SGLang

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

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

Nbv9pQ88Xb

BeaverAI team proudly presents

Gemmasutra 9B v1 🧘

Gemma's been training for you

An RP model with impressive flexibility. Finetuned by yours truly.

Usage

Use Kobold: https://github.com/LostRuins/koboldcpp/releases

What's Different?

Engaging Roleplay
- Asterisks-capable
- Long responses
- Barely any mention of (You)
- Creative!
Enhanced Moist
- Less slop, more dirt, more details, more dwelling on moist moments.
Important: This is an RP-enhanced model with some degree of censorship.
- WHY: Refusals allow the AI to roleplay certain behaviors like avoidance, rejection, etc.
- Use Tiger Gemma if you want zero refusals as an Assistant / during Instruct mode.