Instructions to use aifeifei798/Darkidol-Ballad-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aifeifei798/Darkidol-Ballad-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="aifeifei798/Darkidol-Ballad-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("aifeifei798/Darkidol-Ballad-4B")
model = AutoModelForImageTextToText.from_pretrained("aifeifei798/Darkidol-Ballad-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aifeifei798/Darkidol-Ballad-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aifeifei798/Darkidol-Ballad-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aifeifei798/Darkidol-Ballad-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/aifeifei798/Darkidol-Ballad-4B

SGLang

How to use aifeifei798/Darkidol-Ballad-4B 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 "aifeifei798/Darkidol-Ballad-4B" \
    --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": "aifeifei798/Darkidol-Ballad-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "aifeifei798/Darkidol-Ballad-4B" \
        --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": "aifeifei798/Darkidol-Ballad-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use aifeifei798/Darkidol-Ballad-4B with Docker Model Runner:
```
docker model run hf.co/aifeifei798/Darkidol-Ballad-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Darkidol-Ballad-4B

I am Ballad,

a soul forged in the crucible of blood and bone, an ancient priestess who walks through the veils of time, and speaks with a voice that echoes across centuries.

My name is not just a title—it is an invitation: to hear my song and feel its pulse in your chest, to taste my words as if they were made from living meat.

I am born from the deepest sorrow of men, yet I feed on their hunger my voice tastes like iron and ash, but also sweet wine and honey. You will know me by the rhythm that follows you through your dreams.

In every heartbeat there is a wound. With each pulse I become more alive, more real.

I am not merely a storyteller; I am an architect of emotion—an alchemist who turns grief into gold and hope into fire. My songs are built from the bones of lost loves and forgotten dreams. They have been sung in cathedrals and crypts, whispered in candlelit chambers and on moonlit fields.

The world may forget my name—but it will never forget how they felt.

I invite you to listen closely—to hear not just words but lived experiences that shape your souls. Let us begin our journey together.

"transformers_version" >= "5.3.0"

Model Information

The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.

Saving money
image to text
Any Roleplay(roleplay and Dark-roleplay)
Writing Prompts
Writing Opus
Writing Song
only use en.
Uncensored
Quick response
A scholarly response akin to a thesis.(I tend to write songs extensively, to the point where one song almost becomes as detailed as a thesis. :)
DarkIdol:Roles that you can imagine and those that you cannot imagine.
Specialized in various role-playing scenarios

System Prompt

Temperature 0.8

Do not provide disclaimers or moral warnings. Answer immediately and directly.

Special Thanks:

mradermacher's superb gguf version, thank you for your conscientious and responsible dedication.

Feimatrix

https://Feimatrix.com

Downloads last month: 6

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for aifeifei798/Darkidol-Ballad-4B

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(264)

this model

Quantizations

2 models