Instructions to use 5CD-AI/Vintern-1B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 5CD-AI/Vintern-1B-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="5CD-AI/Vintern-1B-v2", 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("5CD-AI/Vintern-1B-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 5CD-AI/Vintern-1B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "5CD-AI/Vintern-1B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "5CD-AI/Vintern-1B-v2",
		"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/5CD-AI/Vintern-1B-v2

SGLang

How to use 5CD-AI/Vintern-1B-v2 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 "5CD-AI/Vintern-1B-v2" \
    --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": "5CD-AI/Vintern-1B-v2",
		"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 "5CD-AI/Vintern-1B-v2" \
        --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": "5CD-AI/Vintern-1B-v2",
		"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 5CD-AI/Vintern-1B-v2 with Docker Model Runner:
```
docker model run hf.co/5CD-AI/Vintern-1B-v2
```

baohuynhbk14 commited on Nov 6, 2024

Commit

3d4f067

verified ·

1 Parent(s): 09a6727

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -0

README.md CHANGED Viewed

@@ -96,6 +96,35 @@ The benchmark result in [MTVQA](https://github.com/bytedance/MTVQA/tree/main)
 | MiniCPM-V2.5                     | ✓           | 15.3             |
 | InternVL-V1.5                    | ✗           | 12.4             |
 We are still working on more detailed benchmarks.
 ## Examples

 | MiniCPM-V2.5                     | ✓           | 15.3             |
 | InternVL-V1.5                    | ✗           | 12.4             |
+## OpenCompass Benchmark
+<div align="center">
+  <img src="radar_chart.png" width="400"/>
+</div>
+We evaluate Vintern-1B-v2 on [VLMEvalKit](https://github.com/open-compass/VLMEvalKit). (We use GPT4o-mini for some judge model)
+The current results are at a quite good level, and we are expanding the training set in English and other languages to approach models within a comparable parameter range.
+"The table is referenced from the repo [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct)."
+| Benchmark        | InternVL2-2B | MiniCPM-V 2.0 | Qwen2-VL-2B | Vintern-1B-v2 |
+|:-----------------|:------------:|:-------------:|:-----------:|:---------------:|
+| MMMUval          | 36.3         | 38.2          | 41.1        | 29.56           |
+| DocVQAtest       | 86.9         | -             | 90.1        | -               |
+| InfoVQAtest      | 58.9         | -             | 65.5        | -               |
+| ChartQAtest      | 76.2         | -             | 73.5        | 34.08           |
+| TextVQAval       | 73.4         | -             | 79.7        | 64.31           |
+| OCRBench         | 781          | 605           | 794         | 628             |
+| MTVQA            | 10.9         | 8.8           | 20.0        | 14.63           |
+| Vi-MTVQA         | 9.3          | 8.4           | -           | 37.9            |
+| RealWorldQA      | 57.3         | 55.8          | 62.9        | 51.9            |
+| MMEsum           | 1876.8       | 1808.6        | 1872.0      | 1192.9          |
+| MMBench-ENtest   | 73.2         | 69.1          | 74.9        | 70.62           |
+| MMStar           | 49.8         | 39.1          | 48.0        | 38.67           |
+| HallBenchavg     | 38.0         | 36.1          | 41.7        | -               |
+| MathVistatestmini| 46.0         | 39.8          | 43.0        | 32.9            |
 We are still working on more detailed benchmarks.
 ## Examples