Instructions to use dots-studio/dots3-note-prev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dots-studio/dots3-note-prev with Transformers:

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

pipe = pipeline("image-text-to-text", model="dots-studio/dots3-note-prev")
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dots-studio/dots3-note-prev", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dots-studio/dots3-note-prev with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dots-studio/dots3-note-prev"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dots-studio/dots3-note-prev",
		"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/dots-studio/dots3-note-prev

SGLang

How to use dots-studio/dots3-note-prev 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 "dots-studio/dots3-note-prev" \
    --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": "dots-studio/dots3-note-prev",
		"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 "dots-studio/dots3-note-prev" \
        --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": "dots-studio/dots3-note-prev",
		"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 dots-studio/dots3-note-prev with Docker Model Runner:
```
docker model run hf.co/dots-studio/dots3-note-prev
```

Plans for OpenRouter integration?

by NodeLinker - opened about 4 hours ago

Discussion

NodeLinker

about 4 hours ago

•

edited about 4 hours ago

Hi! Do you have plans to bring this model to OpenRouter? Having it there would make it much easier to test and use. Thanks!
Even a quantized or smaller version would be great if the full BF16 is too heavy to host.

MegatronPrimer

dots studio org about 4 hours ago

•

edited about 3 hours ago

Hi, we have fp8 precision checkpoint at https://huggingface.co/dots-studio/dots3-note-prev-fp8

miraclezqc

dots studio org about 4 hours ago

Thanks for your interest! Dots3-Note Preview is rolling out on OpenRouter with free access: https://openrouter.ai/dots-studio/dots-3-note-preview:free
An FP8 checkpoint is also available for self-hosting: https://huggingface.co/dots-studio/dots3-note-prev-fp8
We’d love to hear your feedback!

NodeLinker

about 4 hours ago

Hi, we have fp8 precision checkpoint at https://huggingface.co/dots-studio/dots3-note-prev-fp8
Meanwhile, our model is available for free on OpenRouter: https://openrouter.ai/dots-studio/dots-3-note-preview:free

Thanks for your interest! Dots3-Note Preview is rolling out on OpenRouter with free access: https://openrouter.ai/dots-studio/dots-3-note-preview:free
An FP8 checkpoint is also available for self-hosting: https://huggingface.co/dots-studio/dots3-note-prev-fp8
We’d love to hear your feedback!

Wow, thank you for the incredibly fast response from both of you! I didn't realize there was already an official deployment on OpenRouter.

However, I'm currently having trouble accessing it:

There is no "Chat" button on the OpenRouter page, and the model doesn't seem to show up in the search or the "New" models list.
When trying to query it via the API, I get the following error: Access denied by security policy (even though I have the first three data training privacy toggles enabled in my OpenRouter settings).

Is there any regional lock, provider restriction, or specific policy on this endpoint?

miraclezqc

dots studio org about 3 hours ago

Hi, we have fp8 precision checkpoint at https://huggingface.co/dots-studio/dots3-note-prev-fp8
Meanwhile, our model is available for free on OpenRouter: https://openrouter.ai/dots-studio/dots-3-note-preview:free

Thanks for your interest! Dots3-Note Preview is rolling out on OpenRouter with free access: https://openrouter.ai/dots-studio/dots-3-note-preview:free
An FP8 checkpoint is also available for self-hosting: https://huggingface.co/dots-studio/dots3-note-prev-fp8
We’d love to hear your feedback!

Wow, thank you for the incredibly fast response from both of you! I didn't realize there was already an official deployment on OpenRouter.

However, I'm currently having trouble accessing it:

There is no "Chat" button on the OpenRouter page, and the model doesn't seem to show up in the search or the "New" models list.

When trying to query it via the API, I get the following error: Access denied by security policy (even though I have the first three data training privacy toggles enabled in my OpenRouter settings).

Is there any regional lock, provider restriction, or specific policy on this endpoint?

Sorry for the confusion! We’ve just confirmed that our team is still optimizing the deployment to improve performance and stability. We’ll let you know as soon as it’s ready. Thanks for your patience! @NodeLinker

NodeLinker changed discussion status to closed 36 minutes ago

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