Krisztian Boros

bilibraker's activity

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

liked a model about 1 month ago

naver-clova-ix/donut-base

Image-to-Text • Updated Aug 13, 2022 • 42.7k • 178

liked a model about 2 months ago

ds4sd/docling-models

Updated Oct 1 • 45.4k • 37

upvoted a paper 3 months ago

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

Paper • 2408.12637 • Published Aug 22 • 121

liked a model 4 months ago

HuggingFaceM4/Idefics3-8B-Llama3

Image-Text-to-Text • Updated Sep 18 • 15.9k • 246

New activity in HuggingFaceM4/Docmatix 4 months ago

Problematic examples

3

#4 opened 4 months ago by bilibraker

liked a dataset 4 months ago

HuggingFaceM4/Docmatix

Viewer • Updated Aug 26 • 2.55M • 22.2k • 227

upvoted an article 4 months ago

view article

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 68

New activity in HuggingFaceM4/idefics2-8b 6 months ago

Mixing text-only data into fine-tuning

4

#68 opened 6 months ago by bilibraker

Unable to do inference of finetuned lora model

4

#69 opened 6 months ago by rajuptvs

New activity in HuggingFaceM4/OK-VQA 6 months ago

error while loading

#1 opened 6 months ago by bilibraker

New activity in HuggingFaceM4/idefics2-8b 7 months ago

Bounding boxes in the pre-training data and pre-training tasks

1

#49 opened 7 months ago by bilibraker

GPT-4 Output in Training Data

7

#10 opened 8 months ago by alfredplpl

New activity in HuggingFaceM4/idefics2_playground 7 months ago

Training code

3

#5 opened 7 months ago by shubhamagarwal92

upvoted a collection 7 months ago

Idefics2 🐶

Collection

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 89

New activity in HuggingFaceM4/idefics2-8b 7 months ago

Pre-training code

1

#47 opened 7 months ago by bilibraker

upvoted a paper 7 months ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 100

upvoted an article 7 months ago

view article

Article

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

Apr 15

• 168