Maksym Lysak's picture

7 2

Maksym Lysak

MaxMnemonic

·

AI & ML interests

None yet

Recent Activity

reacted to merve's post with 🔥 about 1 month ago

IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥 > not only a document converter but also can do document question answering, understand multiple languages 🤯 > best part: released with Apache 2.0 license 👏 use it with your commercial projects! > it supports transformers, vLLM and MLX from the get-go! 🤗 > built on SigLIP2 & granite-165M model: https://huggingface.co/ibm-granite/granite-docling-258M demo: https://huggingface.co/spaces/ibm-granite/granite-docling-258m-demo 💗

liked a model about 1 month ago

ibm-granite/granite-docling-258M

new activity 4 months ago

ds4sd/SmolDocling-256M-preview:Trying to Run on Windows, Triton is Required?

View all activity

Organizations

authored 7 papers 7 months ago

Optimized Table Tokenization for Table Structure Recognition

Paper • 2305.03393 • Published May 5, 2023

KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents

Paper • 2405.00505 • Published May 1, 2024

Docling Technical Report

Paper • 2408.09869 • Published Aug 19, 2024 • 2

TableFormer: Table Structure Understanding with Transformers

Paper • 2203.01017 • Published Mar 2, 2022

Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion

Paper • 2501.17887 • Published Jan 27 • 1

Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence

Paper • 2502.09927 • Published Feb 14

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14 • 117