Instructions to use inflatebot/MN-12B-Mag-Mell-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inflatebot/MN-12B-Mag-Mell-R1 with Transformers:

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

pipe = pipeline("text-generation", model="inflatebot/MN-12B-Mag-Mell-R1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inflatebot/MN-12B-Mag-Mell-R1")
model = AutoModelForCausalLM.from_pretrained("inflatebot/MN-12B-Mag-Mell-R1")
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 inflatebot/MN-12B-Mag-Mell-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inflatebot/MN-12B-Mag-Mell-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inflatebot/MN-12B-Mag-Mell-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inflatebot/MN-12B-Mag-Mell-R1

SGLang

How to use inflatebot/MN-12B-Mag-Mell-R1 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 "inflatebot/MN-12B-Mag-Mell-R1" \
    --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": "inflatebot/MN-12B-Mag-Mell-R1",
		"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 "inflatebot/MN-12B-Mag-Mell-R1" \
        --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": "inflatebot/MN-12B-Mag-Mell-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inflatebot/MN-12B-Mag-Mell-R1 with Docker Model Runner:
```
docker model run hf.co/inflatebot/MN-12B-Mag-Mell-R1
```

Could you please release the SillyTavern text completion preset file?

#16

by ruinou - opened Jun 5, 2025

Discussion

ruinou

Jun 5, 2025

It's really too complicated.please

inflatebot

Owner Jun 6, 2025

•

edited Jun 6, 2025

It's not complicated at all.

Step 1: Select the Universal-Light preset.
Step 2: Bump MinP up to 0.2.

You're now at the recommended settings. It's not worth shipping a whole preset file for.
That is the only official recommendation I have ever made. Any complexity past that is complexity you're taking on yourself.
I'm not familiar with the way other people use this model, so if anybody else has suggestions that work better for them then great, implement that, but it's not my responsibility to ship other people's suggestions.

Shinpin

Jun 17, 2025

I'm using sphiratrioth - Roleplay settings from their presets and it works quite well for me. I think it was the ChatML version.. But i did change like one or two settings, increase repetition penalty from 1 to 1.1 for example.

Goodluck. I'm also a noob at this shit, so I can relate, everyone says it's not hard.. But they don't realize a lot of us are relatively new to all of this.

inflatebot

Owner Jun 17, 2025

Goodluck. I'm also a noob at this shit, so I can relate, everyone says it's not hard.. But they don't realize a lot of us are relatively new to all of this.

Let me clarify: I totally empathize with the fact that dialling in LLM settings is difficult! Everyone's expectations/preferences, system prompt, character card, etc... will all make the ideal settings different.
I was only irritated by the implication that I should ship a whole JSON file for what is only 2 settings.
Or, and I'm probably reading into OP's comment with this; the notion that there's an "ideal preset" that I'm somehow hiding. I'm not! Model makers don't know how their stuff will be used! I can only tell you how I like to use it. :)

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