Instructions to use yamatazen/FusionEngine-12B-Lorablated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yamatazen/FusionEngine-12B-Lorablated with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yamatazen/FusionEngine-12B-Lorablated")
model = AutoModelForCausalLM.from_pretrained("yamatazen/FusionEngine-12B-Lorablated", 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 yamatazen/FusionEngine-12B-Lorablated with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yamatazen/FusionEngine-12B-Lorablated

SGLang

How to use yamatazen/FusionEngine-12B-Lorablated 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 "yamatazen/FusionEngine-12B-Lorablated" \
    --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": "yamatazen/FusionEngine-12B-Lorablated",
		"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 "yamatazen/FusionEngine-12B-Lorablated" \
        --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": "yamatazen/FusionEngine-12B-Lorablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yamatazen/FusionEngine-12B-Lorablated with Docker Model Runner:
```
docker model run hf.co/yamatazen/FusionEngine-12B-Lorablated
```

Really good model in general but Please can you merge FusionEngine 12B + NeonMaid-12B-v2 ?

by Noire1 - opened Oct 6, 2025

Discussion

Noire1

Oct 6, 2025

FusionEngine 12B is surprisingly open-minded, talks about everything without hesitation and doesn't show disapproval or deviations during conversation... but general knowledge isn't as good as NeonMaid.
NeonMaid is very knowledgeable and writes well but unfortunately suffers from "obedience." It avoids and refuses many topics. When in conversation, it always finds a way to divert the subject to something more SFW.

I never merged any model and I do not have the Hardware to do that, I searched a little and maybe this settings is good:

Using FusionEngine as Base at 0.65 to keep it open minded and the willing to answer everything and avoid refusing to answer something as well as "obedience" in following the Prompt as it is and NeonMaidV2 at 0.35 to maintain the knowledge and excellent writing.

"yamatazen/FusionEngine-12B-Lorablated"
parameters:
weight: 0.65

model: "yamatazen/NeonMaid-12B-v2"
parameters:
weight: 0.35

yamatazen changed discussion status to closed Dec 19, 2025

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