Instructions to use mistral-experimental/pixtral-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistral-experimental/pixtral-12b with Transformers:

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

pipe = pipeline("image-text-to-text", model="mistral-experimental/pixtral-12b")
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("mistral-experimental/pixtral-12b")
model = AutoModelForMultimodalLM.from_pretrained("mistral-experimental/pixtral-12b")
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 mistral-experimental/pixtral-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mistral-experimental/pixtral-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-experimental/pixtral-12b",
		"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/mistral-experimental/pixtral-12b

SGLang

How to use mistral-experimental/pixtral-12b 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 "mistral-experimental/pixtral-12b" \
    --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": "mistral-experimental/pixtral-12b",
		"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 "mistral-experimental/pixtral-12b" \
        --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": "mistral-experimental/pixtral-12b",
		"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 mistral-experimental/pixtral-12b with Docker Model Runner:
```
docker model run hf.co/mistral-experimental/pixtral-12b
```

Fastest way for inference?

#28

by psycy - opened Feb 6, 2025

Discussion

psycy

Feb 6, 2025

•

edited Feb 6, 2025

I have fine tuned this model, however there's no support on vllm to run this model.
What's the best way to use this in prod?

psycy changed discussion title from Fastest way to inference? to Fastest way for inference? Feb 6, 2025

nielsr

Feb 6, 2025

There's support, see https://docs.vllm.ai/en/v0.6.4/getting_started/examples/offline_inference_pixtral.html

psycy

Feb 7, 2025

Not really, so the support is for the non-hf version that is - mistralai/Pixtral-12B-2409
However, the HF implemented Pixtral in Transformers, use a different Llava model structure. https://huggingface.co/mistral-community/pixtral-12b which isn't supported on vLLM due to

However, I found a script that seems to be working in another thread.

https://github.com/vllm-project/vllm/issues/8685

Thanks

ArthurZ

Feb 7, 2025

Yeah I think vllm team is working to make sure both are compatible!

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