Downloads · 30 days
0
vivqa-beit3-routing-A-clean
ThucPD/vivqa-beit3-routing-A-clean
vivqa-beit3-routing-A-clean is a visual question answering model from ThucPD. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
BEiT-3 base (patch16, 224) finetuned on ViVQA (Vietnamese VQA, 218 answer classes). This is the clean baseline expert (no augmentation) from the question-type routing study.
Access
Public
Updated Jun 27, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 54%
At a glance
- Task
- Visual Question Answering
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- 0ab952a4
Model card
From the Hugging Face model README
ViVQA-BEiT3 — Expert A (clean baseline)
BEiT-3 base (patch16, 224) finetuned on ViVQA (Vietnamese VQA, 218 answer classes). This is the clean baseline expert (no augmentation) from the question-type routing study.
Results (test, 3001 samples)
| Total | what/other | counting | color | location |
|---|---|---|---|---|
| 70.21% | 71.53 | 61.26 | 78.40 | 66.13 |
Training
- Init:
beit3_base_indomain_patch16_224, XLM-R (beit3.spm) tokenization - 30 epochs, lr 5e-5, layer_decay 0.8, batch 64, seed 42,
--clip_grad 1.0,--randaug --augmented none
Files
checkpoint-best.pth— best-val checkpoint (modelkey in state_dict)
Load
from huggingface_hub import hf_hub_download
ckpt = hf_hub_download("ThucPD/vivqa-beit3-routing-A-clean", "checkpoint-best.pth")
# use with BEiT-3 run_beit3_finetuning.py --model beit3_base_patch16_224 --finetune <ckpt>
See the routing study: per-type augmentation effects reproduce but are sub-noise; this clean
baseline is the robust optimum. Paired with the YOLO-augmented expert ThucPD/vivqa-beit3-routing-C-yolo.
- Task
- Visual Question Answering
- Library
- pytorch
- License
- mit
- Languages
- vi
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026