Instructions to use HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA with Transformers:

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

pipe = pipeline("image-text-to-text", model="HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA")
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("HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA")
model = AutoModelForMultimodalLM.from_pretrained("HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA", 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 HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA",
		"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/HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA

SGLang

How to use HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA 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 "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA" \
    --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": "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA",
		"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 "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA" \
        --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": "HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA",
		"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 HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA with Docker Model Runner:
```
docker model run hf.co/HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA
```

Qwen3-VL-2B — nuScenes Driving QA + Counterfactual (LoRA, merged)

LoRA adaptation of Qwen3-VL-2B-Instruct for front-camera driving visual question answering on nuScenes, combining NuScenes-QA (perception: existence / count / status / position) and OmniDrive reasoning + counterfactual QA ("if you follow trajectory X, what happens?"). Vision encoder frozen; LoRA on the LLM + aligner, then merged into a standalone checkpoint. Trained on driving data only (no general-domain replay).

Results (front camera, greedy decoding, vs stock Qwen3-VL-2B)

Task	Stock 2B	This model	Δ
NuScenes-QA (exact-match, n=2000)	27.55%	52.10%	+24.5
Counterfactual (reason-hit)	50.3%	58.7%	+8.4

General-ability retention: MMStar 43.2→44.8, AI2D 72.2→73.2, ScienceQA 74.4→80.0, ChartQA 80.4→76.8, RealWorldQA 68.2→63.2 (largely preserved; several improve).

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor
m = AutoModelForImageTextToText.from_pretrained("HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA", torch_dtype="auto", device_map="auto")
p = AutoProcessor.from_pretrained("HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA")

Training: Qwen3-VL-2B-Instruct · ViT frozen · LoRA r64/α128 (all-linear) · bf16 · 3×A100 · ms-swift · 50k samples (NuScenes-QA 28k + OmniDrive 22k) · 2 epochs. Non-commercial research use (nuScenes / OmniDrive terms).

Downloads last month: 20

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA

Base model

Qwen/Qwen3-VL-2B-Instruct

Adapter

(95)

this model