Downloads · 30 days
0
vichartvqa-a1-lstm
Zenng2812/vichartvqa-a1-lstm
vichartvqa-a1-lstm is a visual question answering model from Zenng2812. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository stores the A1 model checkpoint for Vietnamese Chart Visual Question Answering.
Access
Public
Updated May 5, 2026
Repo size
459 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth459 MB · 100%
At a glance
- Task
- Visual Question Answering
- License
- mit
- Access
- Public
- Created
- May 5, 2026
- Updated
- May 5, 2026
- SHA
- 40517607
Model card
From the Hugging Face model README
ViChartVQA A1 - LSTM Decoder
This repository stores the A1 model checkpoint for Vietnamese Chart Visual Question Answering.
Model
A1 uses a custom architecture with an image encoder, text encoder, co-attention fusion, and an LSTM answer decoder.
File
best_model_a1.pth
Note
This repository only stores the PyTorch checkpoint.
The custom model architecture code is required to load this checkpoint.
- Task
- Visual Question Answering
- License
- mit
- Languages
- vi
- Created
- May 5, 2026
- Updated
- May 5, 2026