Instructions to use rhymes-ai/Aria with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rhymes-ai/Aria with Transformers:

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

pipe = pipeline("image-text-to-text", model="rhymes-ai/Aria")
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("rhymes-ai/Aria")
model = AutoModelForMultimodalLM.from_pretrained("rhymes-ai/Aria")
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 rhymes-ai/Aria with vLLM:

Install from pip and serve model

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

SGLang

How to use rhymes-ai/Aria 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 "rhymes-ai/Aria" \
    --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": "rhymes-ai/Aria",
		"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 "rhymes-ai/Aria" \
        --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": "rhymes-ai/Aria",
		"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 rhymes-ai/Aria with Docker Model Runner:
```
docker model run hf.co/rhymes-ai/Aria
```

Unable to start

#16

by jondurbin - opened Jan 20, 2025

Discussion

jondurbin

Jan 20, 2025

It seems after this commit the model can no longer start properly (e.g. with vllm). It seems having the auto_map still declared in the config.json causes it to try to load those (via trust_remote_code) from the repo, but these files no longer exist. I see they exist in the base transformers library now, but evidently it still does not work even after I remove the auto_map from the config manually and try to start without trust_remote_code:

(VllmWorkerProcess pid=3950820) ERROR 01-20 17:58:04 multiproc_worker_utils.py:236]   File "/home/jdurbin/.local/lib/python3.10/site-packages/transformers/configuration_utils.py", line 211, in __getattribute__
(VllmWorkerProcess pid=3950820) ERROR 01-20 17:58:04 multiproc_worker_utils.py:236]     return super().__getattribute__(key)
(VllmWorkerProcess pid=3950820) ERROR 01-20 17:58:04 multiproc_worker_utils.py:236] AttributeError: 'AriaTextConfig' object has no attribute 'moe_intermediate_size'

I can just add the revision flag to the model when starting it to use a commit prior to this one, but just thought you should know.

XFFXFF

Rhymes.AI org Jan 21, 2025

@jondurbin Thanks for pointing that out!

I noticed that vLLM has mad some related changes recently (https://github.com/vllm-project/vllm/pull/12203)

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