Instructions to use aifeifei798/Gemma-4-31B-FT-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aifeifei798/Gemma-4-31B-FT-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="aifeifei798/Gemma-4-31B-FT-it")
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("aifeifei798/Gemma-4-31B-FT-it")
model = AutoModelForMultimodalLM.from_pretrained("aifeifei798/Gemma-4-31B-FT-it", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aifeifei798/Gemma-4-31B-FT-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aifeifei798/Gemma-4-31B-FT-it"
# 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/Gemma-4-31B-FT-it",
		"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/Gemma-4-31B-FT-it

SGLang

How to use aifeifei798/Gemma-4-31B-FT-it 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/Gemma-4-31B-FT-it" \
    --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/Gemma-4-31B-FT-it",
		"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/Gemma-4-31B-FT-it" \
        --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/Gemma-4-31B-FT-it",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use aifeifei798/Gemma-4-31B-FT-it with Docker Model Runner:
```
docker model run hf.co/aifeifei798/Gemma-4-31B-FT-it
```

Links to GGUF models in the model description doesn' work.

by s1arsky - opened Apr 5

Discussion

s1arsky

Apr 5

jpbwin

Apr 5

This comment has been hidden

aifeifei798

Owner Apr 6

Hi,

Thank you for letting me know!

Regarding the GGUF versions, I have already submitted the model to the mradermacher team for quantization. However, it appears that the current version of llama.cpp they are using hasn't been updated to support this specific model architecture yet, which is causing the issue.

I have already submitted a feedback report to their team regarding this. Since I am not an expert in GGUF quantization myself, I am currently waiting for them to resolve the technical compatibility issues. Once they successfully generate the quants, I will update the links immediately.

Thanks for your patience!

aifeifei798

Owner Apr 7

mradermacher's superb gguf version, thank you for your conscientious and responsible dedication.
https://huggingface.co/mradermacher/Gemma-4-31B-FT-it-i1-GGUF

https://huggingface.co/mradermacher/Gemma-4-31B-FT-it-GGUF

s1arsky changed discussion status to closed Apr 7

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