Hugging Face's logo

lucasoc
/
sci-image-models

Image-to-Text
PEFT
Safetensors
Portuguese
English
vision-language
table-extraction
scientific-figures
markdown-table
lightonocr
qwen2.5-vl
qwen3-vl
lora
icdar-metric-loss
Model card Files
xet
 Community
sci-image-models / README.md

Commit History

12 days ago

  1. Update README with LightOnOCR-3-4B (0.5232) and Qwen3-VL-8B (0.4872) benchmark results

    lucasoc
    Verified signature
    6ecfe6c

  1. docs: remove metrics below ICDAR Score Composto from test benchmark table

    lucasoc
    Verified signature
    95a5e7a

  2. docs: add Qwen2.5-VL-7B SOTA results column and ICDAR leaderboard ranking to model card

    lucasoc
    Verified signature
    c79c3ac

  1. docs: atualiza metricas finais oficiais do conjunto de teste (373 figuras) e tempo de treino

    lucasoc
    Verified signature
    015366f

  2. feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card

    lucasoc
    Verified signature
    840ea91

  3. docs: adiciona tempo de treinamento e hardware a tabela comparativa

    lucasoc
    Verified signature
    da2a347

  4. docs: atualiza explicacao detalhada da loss icdar vs padrao e remove emojis

    lucasoc
    Verified signature
    2aecc4b

  5. docs: update pt-br readme with detailed loss explanation, lora mechanics and +pp metrics

    lucasoc
    Verified signature
    e0efc06

  6. feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase

    lucasoc
    Verified signature
    be90b31