Instructions to use yyyllll/VecLang-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yyyllll/VecLang-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="yyyllll/VecLang-4B")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yyyllll/VecLang-4B")
model = AutoModelForMultimodalLM.from_pretrained("yyyllll/VecLang-4B", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yyyllll/VecLang-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yyyllll/VecLang-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yyyllll/VecLang-4B",
		"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/yyyllll/VecLang-4B

SGLang

How to use yyyllll/VecLang-4B 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 "yyyllll/VecLang-4B" \
    --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": "yyyllll/VecLang-4B",
		"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 "yyyllll/VecLang-4B" \
        --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": "yyyllll/VecLang-4B",
		"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 yyyllll/VecLang-4B with Docker Model Runner:
```
docker model run hf.co/yyyllll/VecLang-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VecLang-4B

VecLang-4B 是基于 Qwen3-VL-4B-Instruct 微调的遥感视觉语言模型，面向以下任务：

遥感图像目标检测；
建筑 Polygon 矢量属性推理；
道路 MultiLineString 矢量属性推理。

权重使用 BF16 保存，共包含两个 safetensors 分片。建议使用项目提供的 qwen3_vl_nothink 模板和推理配置。

Code

推理脚本、配置与评估工具：https://github.com/yyyyll0ss/VecLang

Limitations

模型主要针对遥感影像及对应的结构化输出进行训练和测试。迁移到不同传感器、不同空间分辨率、不同地区或开放域图像时，输出质量可能下降。检测框和矢量结果应在实际应用前进行格式校验与人工抽查。

License and data notice

对外使用前，请分别核对 Qwen3-VL 基座模型、微调数据集及派生权重适用的许可条款。本模型卡未对训练数据或派生权重声明额外许可。

Downloads last month: 60

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for yyyllll/VecLang-4B

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(413)

this model

Quantizations

1 model