allenai/vila

Issues

• In fact, the VILA model only use the 'token' and 'box' to predict, the block is useless

  #38 opened 3 months ago by xsank
  0

• AssertionError: These char IDs get dropped in huggingface

  #37 opened a year ago by rdmpage
  2

• Can we train on Companies PDF documents

  #35 opened 2 years ago by skprasadu
  1

• Can I get the rectangle of figures and tables I read the XML, it seems like it can only be text

  #36 opened 2 years ago by xiaoguaishoubaobao
  1

• Cannot download all files for s2-vl

  #32 opened 2 years ago by ismasensei
  2

• end2end-sci-pdf-parsing doesn't work

  #31 opened 2 years ago by dennissoftman
  5

• Change PDF loader to lp version

  #22 opened 2 years ago by lolipopshock
  0

• Issue in using allenai/hvila-block-layoutlm-finetuned-grotoap2 as predictor weights

  #17 opened 3 years ago by NicholasMcElroy
  1

• module layoutparser has no attribute EfficientDetLayoutModel

  #18 opened 3 years ago by wbb123
  2

• Parsing non-standard sized documents

  #14 opened 3 years ago by NicholasMcElroy
  3

• missing annotation_table.csv

  #15 opened 3 years ago by billy322
  1

• We will provide the download links to the datasets very soon.

  #7 opened 3 years ago by vansin
  2