Instructions to use qvac/VisionPsy-Nano-460M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qvac/VisionPsy-Nano-460M with Transformers:

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

pipe = pipeline("image-text-to-text", model="qvac/VisionPsy-Nano-460M", 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 AutoModel
model = AutoModel.from_pretrained("qvac/VisionPsy-Nano-460M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qvac/VisionPsy-Nano-460M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qvac/VisionPsy-Nano-460M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qvac/VisionPsy-Nano-460M",
		"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/qvac/VisionPsy-Nano-460M

SGLang

How to use qvac/VisionPsy-Nano-460M 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 "qvac/VisionPsy-Nano-460M" \
    --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": "qvac/VisionPsy-Nano-460M",
		"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 "qvac/VisionPsy-Nano-460M" \
        --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": "qvac/VisionPsy-Nano-460M",
		"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 qvac/VisionPsy-Nano-460M with Docker Model Runner:
```
docker model run hf.co/qvac/VisionPsy-Nano-460M
```

cdpark commited on 2 days ago

Commit

584a3a6

verified ·

1 Parent(s): b1a0c62

Update README.md

Browse files

Add VLMEvalKit PR Link

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -83,6 +83,16 @@ accuracy for most, POPE = F1, MMVet = partial credit, MM-IFEval = instruction-fo
 **MME = Perception + Reasoning score**, **OCRBench = Final Score (out of 1000)**. Each model is
 evaluated on its own full sample set. **All LLM-as-judge scoring uses Qwen3.6-27B** as the judge.
 ### Similar-size models (~0.45-0.5B)
 Bold = best score in the row across the similar-size cohort. Sorted by VisionPsy-Nano's lead. Scores are

 **MME = Perception + Reasoning score**, **OCRBench = Final Score (out of 1000)**. Each model is
 evaluated on its own full sample set. **All LLM-as-judge scoring uses Qwen3.6-27B** as the judge.
+The changes used for these numbers are currently under review in VLMEvalKit:
+- **VisionPsy model support**: [PR #1613](https://github.com/open-compass/VLMEvalKit/pull/1613)
+- **Opt-in LLM-judge rescoring for open-ended VQA benchmarks**: [PR #1602](https://github.com/open-compass/VLMEvalKit/pull/1602)
+- **MM-IFEval bug fix**: [PR #1601](https://github.com/open-compass/VLMEvalKit/pull/1601)
+- **LLM-judge bug fix**: [PR #1611](https://github.com/open-compass/VLMEvalKit/pull/1611)
+Until they are merged, you can reproduce the benchmarks by applying these PRs on top of
+[VLMEvalKit](https://github.com/open-compass/VLMEvalKit).
 ### Similar-size models (~0.45-0.5B)
 Bold = best score in the row across the similar-size cohort. Sorted by VisionPsy-Nano's lead. Scores are