Instructions to use flammenai/Mahou-1.5-mistral-nemo-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flammenai/Mahou-1.5-mistral-nemo-12B with Transformers:

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

pipe = pipeline("text-generation", model="flammenai/Mahou-1.5-mistral-nemo-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flammenai/Mahou-1.5-mistral-nemo-12B")
model = AutoModelForCausalLM.from_pretrained("flammenai/Mahou-1.5-mistral-nemo-12B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flammenai/Mahou-1.5-mistral-nemo-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flammenai/Mahou-1.5-mistral-nemo-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": "flammenai/Mahou-1.5-mistral-nemo-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flammenai/Mahou-1.5-mistral-nemo-12B

SGLang

How to use flammenai/Mahou-1.5-mistral-nemo-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 "flammenai/Mahou-1.5-mistral-nemo-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": "flammenai/Mahou-1.5-mistral-nemo-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 "flammenai/Mahou-1.5-mistral-nemo-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": "flammenai/Mahou-1.5-mistral-nemo-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flammenai/Mahou-1.5-mistral-nemo-12B with Docker Model Runner:
```
docker model run hf.co/flammenai/Mahou-1.5-mistral-nemo-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mahou-1.5-mistral-nemo-12B

Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.

Chat Format

This model has been trained to use ChatML format.

<|im_start|>system
{{system}}<|im_end|>
<|im_start|>{{char}}
{{message}}<|im_end|>
<|im_start|>{{user}}
{{message}}<|im_end|>

Roleplay Format

Speech without quotes.
Actions in *asterisks*

*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.

SillyTavern Settings

Use ChatML for the Context Template.
Enable Instruct Mode.
Use the Mahou ChatML Instruct preset.
Use the Mahou Sampler preset.

Method

ORPO finetuned with 4x H100 for 3 epochs.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.28
IFEval (0-Shot)	67.51
BBH (3-Shot)	36.26
MATH Lvl 5 (4-Shot)	5.06
GPQA (0-shot)	3.47
MuSR (0-shot)	16.47
MMLU-PRO (5-shot)	28.91

Downloads last month: 79

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for flammenai/Mahou-1.5-mistral-nemo-12B

Base model

winglian/m12b-20240721-test010

Finetuned

axolotl-ai-co/romulus-mistral-nemo-12b-simpo

Finetuned

nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2

Finetuned

flammenai/Flammades-Mistral-Nemo-12B

Finetuned

(2)

this model

Finetunes

1 model

Merges

13 models

Quantizations

7 models

Dataset used to train flammenai/Mahou-1.5-mistral-nemo-12B

Spaces using flammenai/Mahou-1.5-mistral-nemo-12B 6

Collections including flammenai/Mahou-1.5-mistral-nemo-12B

Mahou

Collection

flammen.ai's production model for casual conversation and character roleplay • 25 items • Updated Mar 16, 2025 • 4

Mahou (Recommended)

Collection

Use this model for best performance and permissive licensing. • 2 items • Updated Mar 2 • 1

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

67.510
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

36.260
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

5.060
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

3.470
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

16.470
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

28.910