Hugo Laurençon

HugoLaurencon's activity

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

commented a paper about 1 month ago

Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models

Paper • 2607.26326 • Published Jul 28 • 3 •

3

New activity in HuggingFaceM4/WebSight over 1 year ago

Error While Loading the Dataset

1

#14 opened over 1 year ago by

SpidY21

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit over 1 year ago

Need details(?)

1

#9 opened over 1 year ago by

akzsh

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

Seems like the user prompt is ignored

7

#80 opened over 1 year ago by

jlmeunier

commented a paper over 1 year ago

CompCap: Improving Multimodal Large Language Models with Composite Captions

Paper • 2412.05243 • Published Dec 6, 2024 • 21 •

4

New activity in HuggingFaceM4/idefics2-8b almost 2 years ago

Can we use idefics2-8b for document classification(Multi Page Document Boundary Classification)?

2

#77 opened almost 2 years ago by

vishal2802

The inconsistency between evaluation and training.

1

#76 opened almost 2 years ago by

Yee111

Format modelcard better

3

#75 opened almost 2 years ago by

mishig

New activity in HuggingFaceM4/Idefics3-8B-Llama3 almost 2 years ago

How to Effectively Run the Idefics 3 Model on AWS SageMaker for Inference

5

#15 opened about 2 years ago by

Mehyaar

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit almost 2 years ago

Performance decrease compared to base Siglip model without Navit.

4

#7 opened about 2 years ago by

Helder5788

commented a paper about 2 years ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22, 2024 • 134 •

6

New activity in HuggingFaceM4/Idefics3-8B-Llama3 about 2 years ago

How to use history prompts on the same image?

3

#12 opened about 2 years ago by

MotiHa

New activity in HuggingFaceM4/idefics2-8b-base about 2 years ago

Some issues regarding training

1

#9 opened about 2 years ago by

zwq2018

New activity in HuggingFaceM4/Idefics3-8B-Llama3 about 2 years ago

Releasing base model and combined SFT dataset

3

#13 opened about 2 years ago by

SS12444

commented a paper about 2 years ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22, 2024 • 134 •

6

New activity in HuggingFaceM4/Idefics3-8B-Llama3 about 2 years ago

Image encoding / rescaling Question

1

#11 opened about 2 years ago by

ayyylemao

Fine tuning fails

6

#10 opened about 2 years ago by

maorcatmyheritage

Update README.md

#9 opened about 2 years ago by

ThatOneCoder

New activity in HuggingFaceM4/idefics3 about 2 years ago

This is amazing!

👍 1

1

#2 opened about 2 years ago by

awacke1

New activity in HuggingFaceM4/Idefics3-8B-Llama3 about 2 years ago

pretraining datasets

1

#8 opened about 2 years ago by

yasserDahou