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

Libraries

How to use DoppelReflEx/MN-12B-WolFrame-Ver.B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/MN-12B-WolFrame-Ver.B")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MN-12B-WolFrame-Ver.B", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DoppelReflEx/MN-12B-WolFrame-Ver.B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DoppelReflEx/MN-12B-WolFrame-Ver.B

SGLang

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

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

What is this?

Defective version of WolFrame, it's confuse between {{user}} and {{char}} sometimes, cause me a lots of trouble.

Why this model have a far better eval scores than original WolFrame???

GGUF? https://huggingface.co/mradermacher/MN-12B-LilithFrame-Experiment-4-GGUF was previous name of this model

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: DoppelReflEx/MN-12B-Mimicore-WhiteSnake
  - model: crestf411/MN-Slush
merge_method: slerp
base_model: DoppelReflEx/MN-12B-Mimicore-WhiteSnake
parameters:
  t: [0.1, 0.2, 0.4, 0.6, 0.6, 0.4, 0.2, 0.1]
dtype: bfloat16
tokenizer_source: base