Instructions to use Undi95/Lumimaid-Magnum-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Lumimaid-Magnum-12B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Lumimaid-Magnum-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Lumimaid-Magnum-12B")
model = AutoModelForCausalLM.from_pretrained("Undi95/Lumimaid-Magnum-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/Lumimaid-Magnum-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Lumimaid-Magnum-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": "Undi95/Lumimaid-Magnum-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Undi95/Lumimaid-Magnum-12B

SGLang

How to use Undi95/Lumimaid-Magnum-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 "Undi95/Lumimaid-Magnum-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": "Undi95/Lumimaid-Magnum-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 "Undi95/Lumimaid-Magnum-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": "Undi95/Lumimaid-Magnum-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Undi95/Lumimaid-Magnum-12B with Docker Model Runner:
```
docker model run hf.co/Undi95/Lumimaid-Magnum-12B
```

Magnum v4

by EloyOn - opened Dec 10, 2024

Discussion

EloyOn

Dec 10, 2024

•

edited Dec 10, 2024

Lumimaid-Magnum has been a favorite of mine for a long time.

Would you consider a new version using the new Magnum v4, since it shares the same Mistral prompt with Lumi? magnum v2 used ChatML.

sirmyrrh

Dec 19, 2024

Not the author, but I believe this was made with Mini-Magnum 12b v1.1, which does use Mistral formatting.

EloyOn

Dec 19, 2024

Not the author, but I believe this was made with Mini-Magnum 12b v1.1, which does use Mistral formatting.

Mini-magnum 12b v1.1 has been out for 5 months and Magnum v4 is 2 months old.

sirmyrrh

Dec 19, 2024

Sure, I'm not saying Undi shouldn't do an alternate version. It would be interesting to compare.

Undi95

Owner Dec 21, 2024

•

edited Dec 21, 2024

I will do that if that interest some people, sure!
It's just a merge.

Undi95

Owner Dec 22, 2024

•

edited Dec 22, 2024

Hello, I'm currently doing the exact same merge, replacing the mini v1.1 with v4.
I will upload the model when done and make some basic GGUF.

Also, I invite you to try out my "Sushi" model, if you have enough power to run it, I would be happy if you do and post feedback.
Have a nice day!

Edit: https://huggingface.co/Undi95/Lumimaid-Magnum-v4-12B

EloyOn

Dec 22, 2024

Thank you!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment