Pablo Montalvo PRO
Molbap
AI & ML interests
None yet
Organizations
Molbap's activity
Torch detection bbox differs from JAX models?
13
#6 opened 15 days ago
by
tlpss
How were the PDF annotations generated?
1
#3 opened 18 days ago
by
nfliu
Image sources - additional data?
#4 opened about 2 months ago
by
Molbap
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64789feb79f2d49511ed7db4/IzaIwiVgnkTZHrcLDQk0C.jpeg)
Where do I see the list of textbooks about mathematics?
1
#2 opened 2 months ago
by
brando
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1626104876019-noauth.png)
ValueError raised upon loading dataset
2
#2 opened 3 months ago
by
rufimelo
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1666860016110-622f26eb163b4ef6fd7a5361.jpeg)
Are there special tokens that are ignored during loss computation?
9
#62 opened 7 months ago
by
Nyandwi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1654168730944-noauth.png)
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
How to use this model to extract html structure from image?
8
#7 opened 8 months ago
by
Alexziyu
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
![](https://cdn-avatars.huggingface.co/v1/production/uploads/648a66c628e95179adc68d49/WXTipJgemlrxXouBOGl96.png)
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
![](https://cdn-avatars.huggingface.co/v1/production/uploads/631c7a0fe65cd7f686d52856/01bjIoVpJYtP2Ngx8MliP.png)
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
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641b435ba5f876fe30c5ae0a/OknUuweWxX3IzUZIKZ6CF.png)
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
Techie5879
issue with running the model
5
#21 opened 8 months ago
by
slay
Added detailed captioning, increase `max_new_tokens` and fix escape character
5
#8 opened 8 months ago
by
merve
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1648113222875-6141a88b3a0ec78603c9e784.png)
Upload processor
#4 opened 8 months ago
by
Molbap
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64789feb79f2d49511ed7db4/IzaIwiVgnkTZHrcLDQk0C.jpeg)