dinhanhx/VisualRoBERTa

The first public Vietnamese visual linguistic foundation model(s)

Stars: 3
Forks: 2
Open beginner issues: 0
Indexed issues: 7

Dominant language: Python
License: MIT
Last GitHub push: Oct 29, 2023
Latest indexed: Sep 15, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

7 open issues indexed

Where the weights? Open

dinhanhx/VisualRoBERTa#2 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🐛 Bug: Typo 'econder' instead of 'encoder' in ImageTextModel Open

dinhanhx/VisualRoBERTa#3 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🏗️ Tech Debt: Deprecated transformers imports and copied generation code Open

dinhanhx/VisualRoBERTa#4 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🐛 Bug: Typo 'econder' instead of 'encoder' + hardcoded magic number 4042 for question mark token Open

dinhanhx/VisualRoBERTa#5 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🏗️ Tech Debt: Deprecated transformers imports + duplicated code across Collators Open

dinhanhx/VisualRoBERTa#6 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🐛 Bug: ResNetMSA._init_params sets weight to 0 instead of bias + method never called Open

dinhanhx/VisualRoBERTa#7 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
🏗️ Tech Debt: Deprecated transformers imports + unclosed file handle + hardcoded dataset paths Open

dinhanhx/VisualRoBERTa#8 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

A short digest of beginner-friendly GitHub issues.