ModernVBERT: Towards Smaller Visual Document Retrievers Paper • 2510.01149 • Published 26 days ago • 30
view article Article Introducing ColQwen-Omni: Retrieve in every modality By manu and 4 others • Jul 17 • 75
Should We Still Pretrain Encoders with Masked Language Modeling? Paper • 2507.00994 • Published Jul 1 • 78
ERNIE 4.5 Collection collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 26 items • Updated Sep 24 • 174
view article Article Efficient LLM Pretraining: Packed Sequences and Masked Attention By sirluk • Oct 7, 2024 • 55
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14 • 117
view article Article DeepSearch Using Visual RAG in Agentic Frameworks 🔎 By paultltc and 1 other • Mar 21 • 37
view article Article ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval By manu and 2 others • Mar 18 • 12
view article Article Introducing smolagents: simple agents that write actions in code. Dec 31, 2024 • 1.14k
RegMix: Data Mixture as Regression for Language Model Pre-training Paper • 2407.01492 • Published Jul 1, 2024 • 40
Parallel Sentences Datasets Collection These datasets all have "english" and "non_english" columns for numerous datasets. They can be used to make embedding models multilingual. • 14 items • Updated Feb 25 • 19
view article Article ColPali: Efficient Document Retrieval with Vision Language Models 👀 By manu • Jul 5, 2024 • 297
Meta Llama 3 Collection This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Dec 6, 2024 • 860