Downloads · 30 days
18
38% of all-time downloads
Qwen3-VL-2B-Bench2Drive-FrontView
HqH1111/Qwen3-VL-2B-Bench2Drive-FrontView
Qwen3-VL-2B-Bench2Drive-FrontView 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-view autonomous-driving visual question answering on the Bench2Drive (Chat-B2D) benchmark. The vision encoder is frozen; LoRA is applied to the language model + multim…
All-time downloads
47
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 23, 2026
- Updated
- Jul 23, 2026
- SHA
- a8f07193
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-VL-2B — Bench2Drive Front-View Driving VQA (LoRA, merged)
LoRA adaptation of Qwen3-VL-2B-Instruct for front-view autonomous-driving visual question answering on the Bench2Drive (Chat-B2D) benchmark. The vision encoder is frozen; LoRA is applied to the language model + multimodal aligner, then merged back into a single standalone checkpoint.
Input format: front camera current frame + 3 history frames (oldest→newest), with a driving-agent system prompt. Trained on driving data only (no general-domain replay) — this recipe was found to outperform general-mixed and data-scaled variants on both driving and general benchmarks.
Results (held-out front-view QA, n=2,500, deterministic split, zero clip overlap)
| Model | Recipe | BLEU-4 | ROUGE-L | CIDEr | MMStar |
|---|---|---|---|---|---|
| Qwen3-VL-2B (stock) | — | 3.00 | 14.15 | 0.47 | 43.67 |
| This model (v7) | B2D-only, 56k, 2 epochs | 45.40 | 74.30 | 436.4 | 52.60 |
General-ability retention (same scorers): AI2D 71.6 · ChartQA 77.2 · RealWorldQA 62.9 · ScienceQA 79.4 · MMStar 52.6 (stock MMStar 43.7 — general reasoning is preserved and, on several benchmarks, improved).
Usage
from transformers import AutoModelForImageTextToText, AutoProcessor
m = AutoModelForImageTextToText.from_pretrained("HqH1111/Qwen3-VL-2B-Bench2Drive-FrontView", torch_dtype="auto", device_map="auto")
p = AutoProcessor.from_pretrained("HqH1111/Qwen3-VL-2B-Bench2Drive-FrontView")
Training
Base Qwen3-VL-2B-Instruct · ViT frozen · LoRA r64/α128 on LLM + aligner · bf16 · 3×A100 · ms-swift. Driving metrics via pycocoevalcap (BLEU-4/ROUGE-L/CIDEr). Non-commercial research use.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026