109 56 76

Hugo Laurençon

HugoLaurencon

HugoLaurencon

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

Qwen2.5 Technical Report

upvoted a paper 1 day ago

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

new activity 1 day ago

HuggingFaceM4/idefics2-8b:Seems like the user prompt is ignored

View all activity

Articles

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 71

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 170

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Mar 15

• 7

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Aug 22, 2023

• 28

Putting ethical principles at the core of research lifecycle

May 19, 2022

Organizations

HugoLaurencon's activity

New activity in HuggingFaceM4/idefics2-8b 1 day ago

Seems like the user prompt is ignored

#80 opened 4 days ago by

jlmeunier

commented a paper 15 days ago

CompCap: Improving Multimodal Large Language Models with Composite Captions

Paper • 2412.05243 • Published 18 days ago • 18 •

New activity in HuggingFaceM4/idefics2-8b 3 months ago

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

#77 opened 3 months ago by

vishal2802

The inconsistency between evaluation and training.

#76 opened 3 months ago by

Yee111

Format modelcard better

#75 opened 3 months ago by

mishig

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

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

#15 opened 4 months ago by

Mehyaar

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 4 months ago

Performance decrease compared to base Siglip model without Navit.

#7 opened 4 months ago by

Helder5788

commented a paper 4 months ago

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

Paper • 2408.12637 • Published Aug 22 • 124 •

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

How to use history prompts on the same image?

#12 opened 4 months ago by

MotiHa

New activity in HuggingFaceM4/idefics2-8b-base 4 months ago

Some issues regarding training

#9 opened 4 months ago by

zwq2018

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

Releasing base model and combined SFT dataset

#13 opened 4 months ago by

SS12444

commented a paper 4 months ago

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

Paper • 2408.12637 • Published Aug 22 • 124 •

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

Image encoding / rescaling Question

#11 opened 4 months ago by

ayyylemao

Fine tuning fails

#10 opened 4 months ago by

maorcatmyheritage

Update README.md

#9 opened 4 months ago by

ThatOneCoder

New activity in HuggingFaceM4/idefics3 4 months ago

This is amazing!

#2 opened 4 months ago by

awacke1

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

pretraining datasets

#8 opened 4 months ago by

yasserTII

New activity in HuggingFaceM4/idefics2-8b-base 4 months ago

Initializing SIGLIP vision model in Idefics2

#8 opened 4 months ago by

johnwicker

Tree

#7 opened 4 months ago by

chinkara

New activity in HuggingFaceM4/Idefics3-8B-Llama3 4 months ago

Transformer Issue ?

#1 opened 5 months ago by

jgsmcmahon