Molbap (Pablo Montalvo) – Community Activity

New activity in google/paligemma-3b-mix-448 1 day ago

Torch detection bbox differs from JAX models?

13

#6 opened 15 days ago by

tlpss

New activity in pixparse/pdfa-eng-wds 12 days ago

How were the PDF annotations generated?

1

#3 opened 18 days ago by

nfliu

New activity in PleIAs/Post-OCR-Correction about 2 months ago

Image sources - additional data?

#4 opened about 2 months ago by

Molbap

New activity in pixparse/pdfa-eng-wds 2 months ago

Where do I see the list of textbooks about mathematics?

1

#2 opened 2 months ago by

brando

New activity in pixparse/idl-wds 3 months ago

ValueError raised upon loading dataset

2

#2 opened 3 months ago by

rufimelo

New activity in adept/fuyu-8b 7 months ago

Are there special tokens that are ignored during loss computation?

9

#62 opened 7 months ago by

Nyandwi

Tips on resolving this typing.Optional error seemingly related to PIL.Image?

3

#56 opened 7 months ago by

justinwickett

demo of PDF vqa

1

#55 opened 7 months ago by

verigle

New activity in google/pix2struct-base 8 months ago

How to use this model to extract html structure from image?

8

#7 opened 8 months ago by

Alexziyu

New activity in adept/fuyu-8b 8 months ago

fine-tuning using FSDP and non 80GB cards?

8

#43 opened 8 months ago by

besiktas

For the vqav2 data set example "fish and carrot", why does the model output a sentence instead of a phrase?

8

#44 opened 8 months ago by

changgeli

Colab

1

#39 opened 8 months ago by

nengelmann

How does the Fuyu model Get images?

3

#45 opened 8 months ago by

VatsaDev

Questions about the examples in the blog

2

#32 opened 8 months ago by

AudreyLin

whether special instruction is need to trigger OCR location function?

3

#38 opened 8 months ago by

liupei0408

Performance Sharing

2

#10 opened 8 months ago by

Starlento

issue with inference

5

#22 opened 8 months ago by

zhangchaosunshine

The 8b model could get correct results for case showed on the offical blog

2

#28 opened 8 months ago by

YuntaoChen

Warning output

4

#15 opened 8 months ago by

dashesy

Released capabilities

6

#42 opened 8 months ago by

ludeksvoboda

fine tune model Posible?

4

#9 opened 8 months ago by

NickyNicky

Loading the model on multi-gpu setup?

1

#23 opened 8 months ago by

Techie5879

long response times

1

#27 opened 8 months ago by

FantasticMrCat42

A working demo.py for your reference

1

#25 opened 8 months ago by

Colderthanice

Using this model as a QA-tool/OCR on a text heavy document?

2

#24 opened 8 months ago by