Instructions to use zerofata/MS3.2-PaintedFantasy-Visage-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zerofata/MS3.2-PaintedFantasy-Visage-33B with Transformers:

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

pipe = pipeline("text-generation", model="zerofata/MS3.2-PaintedFantasy-Visage-33B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zerofata/MS3.2-PaintedFantasy-Visage-33B")
model = AutoModelForCausalLM.from_pretrained("zerofata/MS3.2-PaintedFantasy-Visage-33B")
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 zerofata/MS3.2-PaintedFantasy-Visage-33B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zerofata/MS3.2-PaintedFantasy-Visage-33B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zerofata/MS3.2-PaintedFantasy-Visage-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zerofata/MS3.2-PaintedFantasy-Visage-33B

SGLang

How to use zerofata/MS3.2-PaintedFantasy-Visage-33B 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 "zerofata/MS3.2-PaintedFantasy-Visage-33B" \
    --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": "zerofata/MS3.2-PaintedFantasy-Visage-33B",
		"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 "zerofata/MS3.2-PaintedFantasy-Visage-33B" \
        --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": "zerofata/MS3.2-PaintedFantasy-Visage-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zerofata/MS3.2-PaintedFantasy-Visage-33B with Docker Model Runner:
```
docker model run hf.co/zerofata/MS3.2-PaintedFantasy-Visage-33B
```

DRY parameters?

by deleted - opened Jul 9, 2025

Discussion

deleted

Jul 9, 2025

Could you be a bit clearer about the DRY parameters?

Is the "0.8 1.75 4" supposed to be these, or something else? llama.cpp also allows a --dry-penalty-last-n

DRY multiplier: 0.8
DRY allowed length: 1.75
DRY base: 4.0

zerofata

Owner Jul 9, 2025

Sure,

Dry multiplier: 0.8
Dry base: 1.75
Dry allowed length: 4

This dry setting is pretty light, as it will only penalize chunks of text where there's four or more repeated tokens.

Dry penalty last-n I assume is referring to range, which can be left blank. That value lets you specify how far back through your context it should look for repetitions. By default I believe it looks over the entire context for repetitions but if you specify a context range, it will only penalize repetitions within that context. To increase the potency of dry, I'd recommend increasing the multiplier.

If struggling with repetition, I'd also recommend adding in repetition penalty between 1.05 - 1.1 and messing around with the temp / minp & topp samplers or even XTC / smooth sampling.

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