Instructions to use Naphula/Goetia-31B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Goetia-31B-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Naphula/Goetia-31B-v1")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Naphula/Goetia-31B-v1")
model = AutoModelForMultimodalLM.from_pretrained("Naphula/Goetia-31B-v1", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula/Goetia-31B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Goetia-31B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Goetia-31B-v1",
		"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/Naphula/Goetia-31B-v1

SGLang

How to use Naphula/Goetia-31B-v1 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 "Naphula/Goetia-31B-v1" \
    --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": "Naphula/Goetia-31B-v1",
		"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 "Naphula/Goetia-31B-v1" \
        --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": "Naphula/Goetia-31B-v1",
		"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 Naphula/Goetia-31B-v1 with Docker Model Runner:
```
docker model run hf.co/Naphula/Goetia-31B-v1
```

That pagefile tho...

by Naphula - opened May 23

Discussion

Naphula

Owner May 23

Naphula

Owner May 23

•

edited May 23

Goetia 31B audit

Naphula

Owner May 23

•

edited May 23

This was for v1a, which has lobotomized, short outputs

v1b is next with all merges removed (finetunes only)

Naphula changed discussion status to closed May 23

Naphula

Owner Jun 3

•

edited Jun 3

Qliphoth 31B merges were shit, tons of slop and so far I don't like Gemma 31B much at all.

In fact there are a bunch of G4 finetunes/merges I likely won't get around to testing because i just cant stand the way gemma 4 writes (and it is too slow on my pc). Here is a list of them

# Base
google/gemma-4-31B-it

# Finetunes
ApocalypseParty/G4-31B-Exp-3
ApocalypseParty/G4-31B-SFT-v3-1-1ep
AuriAetherwiing/G4-31B-Musica-v1
ConicCat/Gemma4-GarnetV2-31B
Darkhn/Gemma-4-31B-Animus-V14.0
Jackrong/Gemopus-4-31B-it
p-e-r-e-g-r-i-n-e/Sprinkle-Gemma-4-31B
BeaverAI/Artemis-31B-v1h-GGUF
llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic
DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-Grand-Horror-X-INTENSE-HERETIC-UNCENSORED-Thinking
Lambent/Fabled-Gemma4-31B
LatitudeGames/Equinox-31B
MRockatansky/Gemma-4-31B-storymaxxed

# Merges
Blazed-Forge/Gemma-4-Gemsicle-31B
Nimbz/Gemma-4-Gembrain-31B
zerofata/G4-MeroMero-31B
sophosympatheia/Mero-Artemis-31B-v0.3.1
kabachuha/Gemma-4-The-Deckards-Brain-31B
virtuous7373/Gemma-4-Harmonia-31B
sophosympatheia/Glimmer-31B-v1.0
Nimbz/Gemma-4-Giftige-Blume-31B-v2
Blazed-Forge/Gemma-4-Giftige-Blume-31B-v1
Blazed-Forge/Gemma-4-Sphinsikus-Chronist-31B

Naphula

Owner Jun 3

This comment has been hidden (marked as Resolved)

Naphula

Owner Jun 3

The merge is not that good, 26B seems better. Outputs are too short. uploading for archival and testing purpose

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