Issues
- 0
In fact, the VILA model only use the 'token' and 'box' to predict, the block is useless
#38 opened by xsank - 2
- 1
Can we train on Companies PDF documents
#35 opened 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 by xiaoguaishoubaobao - 2
Cannot download all files for s2-vl
#32 opened by ismasensei - 5
end2end-sci-pdf-parsing doesn't work
#31 opened by dennissoftman - 0
Change PDF loader to lp version
#22 opened by lolipopshock - 1
Issue in using allenai/hvila-block-layoutlm-finetuned-grotoap2 as predictor weights
#17 opened by NicholasMcElroy - 2
- 3
Parsing non-standard sized documents
#14 opened by NicholasMcElroy - 1
missing annotation_table.csv
#15 opened by billy322 - 2