Instructions to use libraos/MN-Violet-Lotus-12B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use libraos/MN-Violet-Lotus-12B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="libraos/MN-Violet-Lotus-12B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("libraos/MN-Violet-Lotus-12B-AWQ")
model = AutoModelForCausalLM.from_pretrained("libraos/MN-Violet-Lotus-12B-AWQ", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use libraos/MN-Violet-Lotus-12B-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/libraos/MN-Violet-Lotus-12B-AWQ

SGLang

How to use libraos/MN-Violet-Lotus-12B-AWQ 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 "libraos/MN-Violet-Lotus-12B-AWQ" \
    --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": "libraos/MN-Violet-Lotus-12B-AWQ",
		"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 "libraos/MN-Violet-Lotus-12B-AWQ" \
        --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": "libraos/MN-Violet-Lotus-12B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use libraos/MN-Violet-Lotus-12B-AWQ with Docker Model Runner:
```
docker model run hf.co/libraos/MN-Violet-Lotus-12B-AWQ
```

MN-Violet-Lotus-12B-AWQ

Provenance

Quantized by Meganova AI from the base model named above. No upstream quantized repo was used.

AWQ 4-bit quantized version of FallenMerick/MN-Violet-Lotus-12B — a Mistral-based 12B finetune for creative writing and emotionally rich roleplay.

Spec	Value
Architecture	Mistral 12B
Parameters	12.2B (not 3B — HF misreads AWQ compressed size)
Quantization	AWQ W4A16 (4-bit weights, 16-bit activations)
Format	compressed-tensors / safetensors
Base model	FallenMerick/MN-Violet-Lotus-12B
VRAM required	~8GB (fits on 1× RTX 3080)

Serving with vLLM

pip install vllm compressed-tensors

python3 -m vllm.entrypoints.openai.api_server \
    --model meganovaai/MN-Violet-Lotus-12B-AWQ \
    --served-model-name MN-Violet-Lotus-12B \
    --gpu-memory-utilization 0.8 \
    --dtype half \
    --quantization compressed-tensors \
    --port 8000

Quantization

Applied via llmcompressor with AWQ W4A16 scheme, calibrated on 64 samples from ultrachat_200k. lm_head excluded from quantization.

Credits

Original model: FallenMerick/MN-Violet-Lotus-12B
Quantized by: Meganova AI

Downloads last month: 187

Safetensors

Model size

3B params

Tensor type

I32

BF16

Model tree for libraos/MN-Violet-Lotus-12B-AWQ

Base model

FallenMerick/MN-Violet-Lotus-12B

Quantized

(10)

this model