ModelListadosExterno

Bbox Indicator Visual Baseline Vi

This repository contains the visual-only baseline using the target-region bbox indicator input path.

Fontehuggingface.co/AnhDau/bbox-indicator-visual-baseline-vi/tree/939110041b566298d80e39abb16b98e59c4fcc23

TipoOtherVersãoModel stateBnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 3,49 GB
Versão: vModel state
Atualizado: 10 de out. de 2026
Fonte: Hugging Face

Descrição da fonte

BBox-Indicator Visual Baseline (Vietnamese)

This repository contains the visual-only baseline using the target-region bbox indicator input path.

Architecture

full image + target region bbox [cx, cy, w, h] / 1000
  -> SigLIP2 patch tokens
  -> Linear(4, 1024) bbox indicator token
  -> prepend bbox indicator before patch tokens
  -> semantic projector
  -> mBART decoder with LoRA
  -> Vietnamese region caption

Main files

model_state.pt
model_config.json
tokenizer/
image_processor/
bbox_indicator_baseline/
requirements.txt

Fontes

1 fonte

Hugging FacePrimárioVersão 939110041b566298d80e39abb16b98e59c4fcc23

huggingface.co/AnhDau/bbox-indicator-visual-baseline-vi/tree/939110041b566298d80e39abb16b98e59c4fcc23

Verificado 10 de out.

Artefatos de modelo

1 artefato

model_state.pt

pt · 3,49 GB · SHA-256 44fe9ea90b49…3b23 · Hugging Face

Download file

Trechos de fonte

2 trechos

Readme1 de ago.huggingface.co/AnhDau/bbox-indicator-visual-baseline-vi

--- language: - vi pipeline_tag: image-to-text tags: - image-captioning - siglip2 - mbart - lora - bbox-indicator - visual-genome license: mit --- # BBox-Indicator Visual Baseline (Vietnamese) This repository contains the visual-only baseline using the target-region bbox indicator input path. ## Architecture ```text full image + target region bbox [cx, cy, w, h] / 1000 -> SigLIP2 patch tokens -> Linear(4, 1024) bbox indicator token -> prepend bbox indicator before patch tokens -> semantic projector -> mBART decoder with LoRA -> Vietnamese region caption ``` ## Main files ```text model_state.pt model_config.json tokenizer/ image_processor/ bbox_indicator_baseline/ requirements.txt ```

Note1 de ago.huggingface.co/AnhDau/bbox-indicator-visual-baseline-vi

Source context: 0 downloads · 0 likes · Pipeline image-to-text · Repo AnhDau/bbox-indicator-visual-baseline-vi