Instructions to use Vortex5/Velvet-Orchid-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vortex5/Velvet-Orchid-12B with Transformers:

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

pipe = pipeline("text-generation", model="Vortex5/Velvet-Orchid-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vortex5/Velvet-Orchid-12B")
model = AutoModelForCausalLM.from_pretrained("Vortex5/Velvet-Orchid-12B")
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 Vortex5/Velvet-Orchid-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vortex5/Velvet-Orchid-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/Velvet-Orchid-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vortex5/Velvet-Orchid-12B

SGLang

How to use Vortex5/Velvet-Orchid-12B 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 "Vortex5/Velvet-Orchid-12B" \
    --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": "Vortex5/Velvet-Orchid-12B",
		"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 "Vortex5/Velvet-Orchid-12B" \
        --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": "Vortex5/Velvet-Orchid-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vortex5/Velvet-Orchid-12B with Docker Model Runner:
```
docker model run hf.co/Vortex5/Velvet-Orchid-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Velvet-Orchid-12B

This is a multi-stage merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using Vortex5/MegaMoon-Karcher-12B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

Merge Config (click to expand)

name: First  
models:
- model: Vortex5/Harmonic-Moon-12B
- model: Vortex5/Scarlet-Ink-12B
merge_method: karcher
dtype: bfloat16
parameters:
tol: 1e-10
max_iter: 1200
tokenizer:
source: union

base_model: Vortex5/MegaMoon-Karcher-12B
dtype: bfloat16
merge_method: della_linear
modules:
default:
  slices:
  - sources:
    - layer_range: [0, 40]
      model: ./intermediates/First
      parameters:
        density: 0.5
        epsilon: 0.4
        weight: [0.9, 0.2, 0.2, 0.2, 0.95, 0.8, 0.4, 0.2]
    - layer_range: [0, 40]
      model: taozi555/MN-12B-Mag-Mell-R1-KTO
      parameters:
        density: 0.5
        epsilon: 0.4
        weight: [0.1, 0.9, 1.0, 0.95, 0.4, 0.4, 0.5, 0.3]
    - layer_range: [0, 40]
      model: Vortex5/MegaMoon-Karcher-12B
parameters:
lambda: 1.0
normalize: 1.0
tokenizer: {}