Lucas Beyer's picture

16 1 2

Lucas Beyer

giffmana

·

http://lucasb.eyer.be

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

google/siglip-so400m-patch14-384:Is SiglipImageProcessor configured correctly?

new activity 4 days ago

google/siglip2-so400m-patch14-384:Question About SigLIP 2’s Performance with Newline-Separated Labels

commented on an article 16 days ago

SigLIP 2: A better multilingual vision language encoder

View all activity

Organizations

giffmana's activity

New activity in google/siglip-so400m-patch14-384 4 days ago

Is SiglipImageProcessor configured correctly?

#9 opened 4 months ago by

New activity in google/siglip2-so400m-patch14-384 4 days ago

Question About SigLIP 2’s Performance with Newline-Separated Labels

#2 opened 20 days ago by

New activity in google/siglip-so400m-patch14-384 5 months ago

Why is the image size designed to be 384, whereas the patch size is designed to be 14, when 384 is not divisible by 14?

#4 opened 12 months ago by

New activity in google/siglip-large-patch16-384 6 months ago

upload fast tokenizer.json

#1 opened 6 months ago by

New activity in google/siglip-large-patch16-256 6 months ago

Upload tokenizer.json

#2 opened 6 months ago by

New activity in google/siglip-base-patch16-256 6 months ago

Upload tokenizer.json

#1 opened 6 months ago by

New activity in google/siglip-base-patch16-384 6 months ago

Upload tokenizer.json

#1 opened 6 months ago by

New activity in google/siglip-base-patch16-512 6 months ago

upload fast tokenizer.json

#2 opened 6 months ago by

New activity in google/siglip-base-patch16-256-multilingual 6 months ago

upload fast tokenizer.json

#4 opened 6 months ago by

New activity in google/siglip-so400m-patch14-384 6 months ago

upload fast tokenizer.json

#7 opened 6 months ago by

New activity in google/siglip-base-patch16-224 6 months ago

Upload tokenizer.json for fast tokenizer support

#4 opened 6 months ago by

New activity in google/siglip-so400m-patch14-384 12 months ago

hidden sizes

#3 opened about 1 year ago by

Model performance is not adequate.

#1 opened about 1 year ago by

New activity in timm/ViT-SO400M-14-SigLIP-384 12 months ago

Very flat output? "Probabilities" all close to zero.

#3 opened over 1 year ago by

New activity in google/siglip-so400m-patch14-384 12 months ago

hidden sizes

#3 opened about 1 year ago by