Instructions to use seshing/openfacades-internvl3-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seshing/openfacades-internvl3-2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="seshing/openfacades-internvl3-2b", 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("seshing/openfacades-internvl3-2b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use seshing/openfacades-internvl3-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seshing/openfacades-internvl3-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "seshing/openfacades-internvl3-2b",
		"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/seshing/openfacades-internvl3-2b

SGLang

How to use seshing/openfacades-internvl3-2b 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 "seshing/openfacades-internvl3-2b" \
    --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": "seshing/openfacades-internvl3-2b",
		"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 "seshing/openfacades-internvl3-2b" \
        --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": "seshing/openfacades-internvl3-2b",
		"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 seshing/openfacades-internvl3-2b with Docker Model Runner:
```
docker model run hf.co/seshing/openfacades-internvl3-2b
```

OpenFACADES-InternVL3-2B

A vision-language model fine-tuned on building facade analysis tasks, based on InternVL3-2B architecture.

Model Description

This model is designed for analyzing building facades and architectural features. It combines computer vision and natural language processing capabilities to understand and describe architectural elements in images.

Usage

from transformers import AutoModel, AutoTokenizer

# Load model and tokenizer
model = AutoModel.from_pretrained("seshing/openfacades-internvl3-2b", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("seshing/openfacades-internvl3-2b", trust_remote_code=True)

License

This project is released under the Apache-2.0 License. This project uses the pre-trained InternVL, which is licensed under the Apache-2.0 License.

Acknowledgments

Built upon the InternVL3-2B model architecture and trained on building facade datasets.

Downloads last month: 55

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for seshing/openfacades-internvl3-2b

Base model

OpenGVLab/InternVL2_5-2B

Finetuned

(11)

this model

Collection including seshing/openfacades-internvl3-2b

openfacades-models-dataset

Collection

finetuned InternVL models for building annotations • 4 items • Updated Jan 28