docs: add comprehensive failure analysis and error diagnostics for 7B model

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

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

feat(config): upload configs/models/qwen2_5_vl_7b.yaml

feat(config): upload configs/training/train_7b_icdar_loss.yaml

docs(eval): add 7B evaluation metrics inside subfolder

docs(eval): add 7B evaluation metrics report (eval_report_7b.json)

feat(7b): upload Qwen2.5-VL-7B fine-tuned adapter weights and processor config

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

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

docs: adiciona tempo de treinamento e hardware a tabela comparativa

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

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

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

initial commit