Downloads · 30 days
17
27% of all-time downloads
Qwen3-VL-2B-NuScenes-DrivingQA
HqH1111/Qwen3-VL-2B-NuScenes-DrivingQA
Qwen3-VL-2B-NuScenes-DrivingQA is a image-text-to-text model from HqH1111. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
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 + counterfactua…
All-time downloads
64
Public
Parameters
2.1B
4.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.3 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_vl
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026
- SHA
- 2688636c
Try a prompt
Base models
Model card
From the Hugging Face model README
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).
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026