Orr Zohar PRO

orrzohar's activity

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

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct about 7 hours ago

Several questions on the same video

1

#8 opened 4 days ago by

delphijb

upvoted 2 papers about 19 hours ago

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models

Paper • 2502.16033 • Published 4 days ago • 14

Audio-FLAN: A Preliminary Release

Paper • 2502.16584 • Published 2 days ago • 25

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct 1 day ago

Input Video length constraints

3

#6 opened 4 days ago by

NikhilJoson

liked a Space 2 days ago

Running

31

31

Datasets Convertor

👁

Support by Parquet, CSV, Jsonl, XLS

liked a dataset 2 days ago

facebook/natural_reasoning

Viewer • Updated 5 days ago • 1.15M • 2.12k • 201

upvoted a collection 4 days ago

SigLIP2

Collection

36 items • Updated 5 days ago • 46

upvoted a paper 4 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 5 days ago • 115

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct 4 days ago

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

1

#7 opened 4 days ago by

JLouisBiz

updated a model 4 days ago

HuggingFaceTB/SmolVLM2-500M-Video-Instruct

Video-Text-to-Text • Updated 4 days ago • 1.52k • 28

New activity in HuggingFaceTB/SmolVLM2-500M-Video-Instruct 4 days ago

update readme dtype

#8 opened 4 days ago by

orrzohar

updated a model 4 days ago

HuggingFaceTB/SmolVLM2-256M-Video-Instruct

Video-Text-to-Text • Updated 4 days ago • 1.78k • 23

New activity in HuggingFaceTB/SmolVLM2-256M-Video-Instruct 4 days ago

update readme dtype

#5 opened 4 days ago by

orrzohar

updated a model 4 days ago

HuggingFaceTB/SmolVLM2-2.2B-Instruct

Video-Text-to-Text • Updated 2 days ago • 5.19k • 69

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct 4 days ago

Fix dtype processing in README example

#5 opened 4 days ago by

orrzohar

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

2

#4 opened 4 days ago by

Neiko2002

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

3

#2 opened 5 days ago by

maxlun

upvoted a collection 5 days ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

Collection

11 items • Updated about 12 hours ago • 38

liked 2 Spaces 5 days ago

Running on Zero

35

35

SmolVLM

📊

Generate text by analyzing images and videos

Sleeping

13

13

SmolVLM2 XSPFGenerator (VLC prototype)

🎞

Generate video highlights and playlist