Orr Zohar PRO

orrzohar's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in google/gemma-3-4b-it 3 months ago

SigLIP or SigLIP2 encoder?

6

#37 opened 4 months ago by

orrzohar

commented 2 papers 4 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 196 •

8

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 196 •

8

New activity in google/gemma-3-27b-it 4 months ago

SigLIP or SigLIP2 encoder?

12

#48 opened 4 months ago by

orrzohar

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct 5 months ago

Input Video length constraints

👍 1

8

#6 opened 5 months ago by

NikhilJoson

Several questions on the same video

👍 1

1

#8 opened 5 months ago by

delphijb

checkpoint you are trying to load has model type `smolvlm` but Transformers does not recognize this

1

#7 opened 5 months ago by

JLouisBiz

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (CUDABFloat16Type) should be the same

2

#4 opened 5 months ago by

Neiko2002

Using pre-computed embeddings for images/frames and using as input

5

#2 opened 5 months ago by

maxlun

commented 2 papers 8 months ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 147 •

13

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 147 •

13

New activity in lmms-lab/LLaVA-OneVision-Data 10 months ago

Missing/corrupted images in dataset

#9 opened 11 months ago by

orrzohar

commented a paper 12 months ago

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Paper • 2408.10188 • Published Aug 19, 2024 • 53 •

4

commented 3 papers about 1 year ago

$VILA^2$: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24, 2024 • 42 •

7

$VILA^2$: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24, 2024 • 42 •

7

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

Paper • 2407.06189 • Published Jul 8, 2024 • 27 •

3

New activity in HuggingFaceM4/idefics2-8b about 1 year ago

Idefics2-pretraining

4

#54 opened about 1 year ago by

orrzohar

New activity in meta-llama/Meta-Llama-3-8B-Instruct over 1 year ago

The request to access the repo has been sent for several days, why hasn't it passed yet?

7

#70 opened over 1 year ago by

water-cui