Instructions to use DoppelReflEx/MN-12B-FoxFrame-Yukina with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/MN-12B-FoxFrame-Yukina with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/MN-12B-FoxFrame-Yukina")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MN-12B-FoxFrame-Yukina")
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 DoppelReflEx/MN-12B-FoxFrame-Yukina with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DoppelReflEx/MN-12B-FoxFrame-Yukina

SGLang

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

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

Version: Miyuri - Yukina - Shinori

What is this?

A very nice merge series, to be real. I have test this and got the good result so far.

In my test character card, it's give me an light tsundere and yandere girl, LOL. You should try it too, or try any version you like most.

Good for RP,ERP.

PS: Sometimes, it have cgato/Nemo-12b-Humanize-KTO-Experimental-Latest but that <|im_end|> token will appear and you must write some word or reroll the message.

Template? ChatML, of course!

Merge Detail

### Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
 - model: cgato/Nemo-12b-Humanize-KTO-Experimental-Latest
   parameters:
     density: 0.9
     weight: 1
 - model: DoppelReflEx/MN-12B-Mimicore-GreenSnake
   parameters:
     density: 0.5
     weight: 0.7
 - model: Epiculous/Violet_Twilight-v0.2
   parameters:
     density: 0.7
     weight: 0.5
merge_method: dare_ties
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
tokenizer_source: base