Instructions to use ATH-MaaS/Ovis1.6-Gemma2-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ATH-MaaS/Ovis1.6-Gemma2-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ATH-MaaS/Ovis1.6-Gemma2-9B", trust_remote_code=True)
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("ATH-MaaS/Ovis1.6-Gemma2-9B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ATH-MaaS/Ovis1.6-Gemma2-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ATH-MaaS/Ovis1.6-Gemma2-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ATH-MaaS/Ovis1.6-Gemma2-9B",
		"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/ATH-MaaS/Ovis1.6-Gemma2-9B

SGLang

How to use ATH-MaaS/Ovis1.6-Gemma2-9B 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 "ATH-MaaS/Ovis1.6-Gemma2-9B" \
    --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": "ATH-MaaS/Ovis1.6-Gemma2-9B",
		"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 "ATH-MaaS/Ovis1.6-Gemma2-9B" \
        --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": "ATH-MaaS/Ovis1.6-Gemma2-9B",
		"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 ATH-MaaS/Ovis1.6-Gemma2-9B with Docker Model Runner:
```
docker model run hf.co/ATH-MaaS/Ovis1.6-Gemma2-9B
```

Any Plan on doing something similar for gemma 2 27b?

by backendmagier - opened Sep 26, 2024

Discussion

backendmagier

Sep 26, 2024

Any Plan on doing something similar for gemma 2 27b? would love it

runninglsy

ATH-MaaS org Sep 27, 2024

Thank you for your interest in Ovis. The 27B version is currently in the training phase. Barring any unforeseen circumstances, we anticipate its release later next month.

backendmagier

Sep 27, 2024

very nice looking forward to that!

Sadmank

Sep 27, 2024

@runninglsy Thanks for it. Can we get one for Qwen 2.5 14B? Strong chat model, so with vision, it will be very good for local use. I tried the Ovis 1.6 9B model; very strong for this size. I like it, but the only thing it slightly underperforms in is OCR/text-related tasks compared to Qwen 2 VL 7B.

barleyspectacular

Oct 17, 2024

@runninglsy you nailed it with this model, I'm blown away. Excited for 27B!

thesby

Nov 12, 2024

期待 27B

runninglsy

ATH-MaaS org Nov 26, 2024

We have just released Ovis1.6-Gemma2-27B. Feel free to try them out and share your feedback!

thesby

Nov 28, 2024

Great!!!

runninglsy

ATH-MaaS org Nov 29, 2024

@runninglsy Thanks for it. Can we get one for Qwen 2.5 14B? Strong chat model, so with vision, it will be very good for local use. I tried the Ovis 1.6 9B model; very strong for this size. I like it, but the only thing it slightly underperforms in is OCR/text-related tasks compared to Qwen 2 VL 7B.

@Sadmank We are working on it. Stay tuned!

runninglsy

ATH-MaaS org Feb 12, 2025

@runninglsy Thanks for it. Can we get one for Qwen 2.5 14B? Strong chat model, so with vision, it will be very good for local use. I tried the Ovis 1.6 9B model; very strong for this size. I like it, but the only thing it slightly underperforms in is OCR/text-related tasks compared to Qwen 2 VL 7B.

@Sadmank We have just released the Ovis2 series models based on Qwen2.5, which come in various sizes including 1B, 2B, 4B, 8B, 16B (based on Qwen2.5-14B-Instruct), and 34B. Feel free to try them out!

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