Amit Naik
@suprgeek
👀
DailyPapers@HuggingPapers · Oct 9Tencent just released an omni-modal parsing model on Hugging Face
One 5B model that turns documents, images, charts, geometry figures, audio and video into a single structured JSON.
One 5B model that turns documents, images, charts, geometry figures, audio and video into a single structured JSON.
Open quoted post →
0 0