Instructions to use ATH-MaaS/Ovis2-34B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ATH-MaaS/Ovis2-34B-GPTQ-Int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ATH-MaaS/Ovis2-34B-GPTQ-Int4", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ATH-MaaS/Ovis2-34B-GPTQ-Int4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ATH-MaaS/Ovis2-34B-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ATH-MaaS/Ovis2-34B-GPTQ-Int4"
# 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/Ovis2-34B-GPTQ-Int4",
		"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/Ovis2-34B-GPTQ-Int4

SGLang

How to use ATH-MaaS/Ovis2-34B-GPTQ-Int4 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/Ovis2-34B-GPTQ-Int4" \
    --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/Ovis2-34B-GPTQ-Int4",
		"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/Ovis2-34B-GPTQ-Int4" \
        --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/Ovis2-34B-GPTQ-Int4",
		"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/Ovis2-34B-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/ATH-MaaS/Ovis2-34B-GPTQ-Int4
```

TryingHard commited on Mar 28, 2025

Commit

d16bdfe

verified ·

1 Parent(s): 9ca4051

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -209,6 +209,9 @@ We report the performance of the quantized Ovis2 series. OpenCompass results are
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/645cb4b4a03f3ebb0bde20e0/HZqgbFU-RkuqvWhmo1HpM.png)
 ## Citation

 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/645cb4b4a03f3ebb0bde20e0/HZqgbFU-RkuqvWhmo1HpM.png)
+GPU peak memory consumption, tested by inferencing on 500 ChartQA samples:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645cb4b4a03f3ebb0bde20e0/7LgC6_FoVQMjGLRINvwMj.png)
 ## Citation