Hugging Face's logo
Pavel Iakubovskii's picture
68 57 108

Pavel Iakubovskii

qubvel-hf
Taranjeet94's profile picture not-lain's profile picture mrdjtek's profile picture
Β·

AI & ML interests

Computer Vision models

Recent Activity

liked a model 5 days ago
xingyang1/Distill-Any-Depth
upvoted a paper 6 days ago
Unified Video Action Model
upvoted an article 6 days ago
SmolVLM2: Bringing Video Understanding to Every Device
View all activity

Organizations

Hugging Face's profile picture PyTorch Image Models's profile picture Peking University's profile picture Hugging Face Internal Testing Organization's profile picture Huggingface Projects's profile picture Hugging Face OSS Metrics's profile picture Hugging Face for Computer Vision's profile picture kotol's profile picture yorg's profile picture CVPR2024's profile picture Hugging Face Discord Community's profile picture nltpt's profile picture s0409's profile picture Segmentation Models Pytorch's profile picture smp-test's profile picture University of Sydney's profile picture s0225's profile picture ETH Zurich - Computer Vision and Geometry Lab's profile picture

qubvel-hf's activity

liked a model 5 days ago
upvoted a paper 6 days ago
upvoted an article 6 days ago
view article
Article

SmolVLM2: Bringing Video Understanding to Every Device

β€’ 202
reacted to clem's post with πŸ”₯ 6 days ago
liked a Space 6 days ago
liked a Space 7 days ago
updated a model 8 days ago
New activity in facebook/sam-vit-large 8 days ago

Update code snippet
#6 opened 8 days ago by
qubvel-hf
updated a model 8 days ago
New activity in facebook/sam-vit-huge 8 days ago

Update code snippet
#11 opened 8 days ago by
qubvel-hf
updated a model 8 days ago
New activity in facebook/sam-vit-base 8 days ago

Update code snippet
#8 opened 8 days ago by
qubvel-hf
upvoted an article 10 days ago
upvoted a paper 11 days ago
New activity in google/siglip2-base-patch16-224 11 days ago

SigLip2 Does Not Reproduce Expected Results

3
#7 opened 14 days ago by
dogukan-bg
commented on SigLIP 2: A better multilingual vision language encoder 13 days ago
view reply

btw, also observed "." and capitalized template influences the confidence quite a bit
commented on SigLIP 2: A better multilingual vision language encoder 13 days ago
view reply

Not sure what's up as I'm not familiar with this codebase (and no time to dig in), but for siglip what you're supposed to do is do sigmoid(zimg @ ztxt * temperature + bias)

from what you describe, I would bet the bias and/or temperature are missing?
The ground-truth reference code is https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP2_demo.ipynb

Hey @giffmana , temperature and bias are applied under the hood, see

Siglip
https://github.com/huggingface/transformers/blob/17792556b21b4da0dbb9e4b59b39fb34aae4047c/src/transformers/models/siglip/modeling_siglip.py#L1411-L1417

Siglip2
https://github.com/huggingface/transformers/blob/17792556b21b4da0dbb9e4b59b39fb34aae4047c/src/transformers/models/siglip2/modeling_siglip2.py#L1459-L1465
liked a Space 13 days ago
New activity in google/siglip2-base-patch16-224 14 days ago

Error while loading processor: TypeError: expected str, bytes or os.PathLike object, not NoneType

8
#2 opened 19 days ago by
armamut

question about 'model_type' in config.json

2
#5 opened 15 days ago by
XA-hyy