Instructions to use MuXodious/Qwen3.5-4B-MiniFantasy-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuXodious/Qwen3.5-4B-MiniFantasy-MTP with Transformers:

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

pipe = pipeline("text-generation", model="MuXodious/Qwen3.5-4B-MiniFantasy-MTP")
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("MuXodious/Qwen3.5-4B-MiniFantasy-MTP")
model = AutoModelForImageTextToText.from_pretrained("MuXodious/Qwen3.5-4B-MiniFantasy-MTP")
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 MuXodious/Qwen3.5-4B-MiniFantasy-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuXodious/Qwen3.5-4B-MiniFantasy-MTP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuXodious/Qwen3.5-4B-MiniFantasy-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuXodious/Qwen3.5-4B-MiniFantasy-MTP

SGLang

How to use MuXodious/Qwen3.5-4B-MiniFantasy-MTP 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 "MuXodious/Qwen3.5-4B-MiniFantasy-MTP" \
    --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": "MuXodious/Qwen3.5-4B-MiniFantasy-MTP",
		"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 "MuXodious/Qwen3.5-4B-MiniFantasy-MTP" \
        --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": "MuXodious/Qwen3.5-4B-MiniFantasy-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use MuXodious/Qwen3.5-4B-MiniFantasy-MTP with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for MuXodious/Qwen3.5-4B-MiniFantasy-MTP to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for MuXodious/Qwen3.5-4B-MiniFantasy-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MuXodious/Qwen3.5-4B-MiniFantasy-MTP to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="MuXodious/Qwen3.5-4B-MiniFantasy-MTP",
    max_seq_length=2048,
)

Docker Model Runner
How to use MuXodious/Qwen3.5-4B-MiniFantasy-MTP with Docker Model Runner:
```
docker model run hf.co/MuXodious/Qwen3.5-4B-MiniFantasy-MTP
```

Multi Token Prediction (MTP) weights restored from the base model.

Qwen3.5-4B-MiniFantasy

Model Description

This is a 4-bit LoRA fine-tune of the MuXodious/Qwen3.5-4B-SOMPOA-heresy-v2 model.

SillyTavern Setup

Sampler Settings

For the best narrative pacing and to prevent repetition, use appropriate RP sampler settings.

General Guide: SillyTavern Sampler Settings Guide
Recommended Preset: Download my recommended sampler JSON here

Character Card Format (`{{description}}` block)

The model was trained on a category-based Markdown structure. For the best adherence to personality and lore, structure your character cards exactly like this:

## Identity
- Name: [Full Name]
- Age: [Age]
- Race/Species: [Race]
- Role/Occupation: [Role and relationship]

## Appearance
- [Height, general build]
- [Specific physical features, hair, eyes, etc.]
- Clothing: [Current outfit details]

## Personality
- Public: [Outward facade]
- Private: [True self]
- [1-2 extra bullet points on core personality traits]

## Speech & Quirks
- [Vocal tone and speaking style]
- [Physical habit or nervous tick]
- [How they show affection]

## Backstory & World Context
- [Origin]
- [Key past event]
- [Current situation]

## Goals & Motivations
- Short term: [Immediate goals]
- Long term: [Big picture goals]

Training Procedure

The model was fine-tuned on a custom, curated synthetic dataset focusing on multi-turn narrative pacing, emotional resonance, and specific character dynamics.

Training Hyperparameters

LoRA Rank (r): 16
LoRA Alpha: 16
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Epochs: 3
Learning Rate: 5e-5
Effective Batch Size: 8 (Batch 2, Gradient Accumulation 4)
Warmup Steps: 9
Weight Decay: 0.01
Optimizer: paged_adamw_8bit
LR Scheduler: cosine