Instructions to use microsoft/maira-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/maira-2 with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/maira-2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/maira-2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/maira-2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/microsoft/maira-2

SGLang

How to use microsoft/maira-2 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 "microsoft/maira-2" \
    --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": "microsoft/maira-2",
		"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 "microsoft/maira-2" \
        --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": "microsoft/maira-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/maira-2 with Docker Model Runner:
```
docker model run hf.co/microsoft/maira-2
```

The current demos are incompatible with transformers library Version: 4.49.0.

#14

by ZhangNy - opened Mar 6, 2025

Discussion

ZhangNy

Mar 6, 2025

The version of the transformers library is Version: 4.49.0. When running cases 1 and 2: Findings generation with or without grounding, an error occurs at the model.generate() location:
lib/python3.11/site-packages/transformers/models/llava/modeling_llava.py", line 415, in forward
image_features = self.get_image_features(
^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Maira2ForConditionalGeneration.get_image_features() got an unexpected keyword argument 'image_sizes'

kimmazel

Apr 17, 2025

Hello, did you end up figuring out what version of Transformers works for the model? When I use the recommended version in the model card, the shards cannot be loaded. The more recent versions of Transformers allows the shards to be loaded but I get the same error with you for the image_sizes.

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