Instructions to use Steelskull/MSM-MS-Cydrion-22B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Steelskull/MSM-MS-Cydrion-22B with Transformers:

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

pipe = pipeline("text-generation", model="Steelskull/MSM-MS-Cydrion-22B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Steelskull/MSM-MS-Cydrion-22B")
model = AutoModelForCausalLM.from_pretrained("Steelskull/MSM-MS-Cydrion-22B")
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 Steelskull/MSM-MS-Cydrion-22B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Steelskull/MSM-MS-Cydrion-22B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Steelskull/MSM-MS-Cydrion-22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Steelskull/MSM-MS-Cydrion-22B

SGLang

How to use Steelskull/MSM-MS-Cydrion-22B 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 "Steelskull/MSM-MS-Cydrion-22B" \
    --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": "Steelskull/MSM-MS-Cydrion-22B",
		"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 "Steelskull/MSM-MS-Cydrion-22B" \
        --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": "Steelskull/MSM-MS-Cydrion-22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Steelskull/MSM-MS-Cydrion-22B with Docker Model Runner:
```
docker model run hf.co/Steelskull/MSM-MS-Cydrion-22B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Meet Cydrion, the attempt of fusion for creativity and intelligence.

Creator: SteelSkull

About Cydrion-22B:

Name Legend:
MSM = Mistral-Small
MS = Model Stock
22b = its 22b

This model merges the robust storytelling of Cydonia with the creative edge of Acolyte, ArliAI-RPMax, and Gutenberg with some special sauce.

Use Mistral Format

Quants:

My Quants:MSM-MS-Cydrion-22B-Q6_K-GGUF

Config:

MODEL_NAME = "MSM-MS-Cydrion-22B"
yaml_config = """
base_model: Steelskull/Merged-v2
merge_method: model_stock
dtype: bfloat16
models:
  - model: TheDrummer/Cydonia-22B-v1.1
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
  - model: nbeerbower/Mistral-Small-Gutenberg-Doppel-22B
  - model: rAIfle/Acolyte-22B
"""

If you wish to support: