Wonsuk Yang's picture

2 1 1

Wonsuk Yang

WonsukYangTL

·

AI & ML interests

None yet

Recent Activity

reacted to AdinaY's post with 🔥 21 days ago

Dolphin 🔥 A multimodal document image parsing model from ByteDance , built on an analyze-then-parse paradigm. https://huggingface.co/ByteDance/Dolphin ✨ MIT licensed ✨ Handles text, tables, figures & formulas via: - Reading-order layout analysis - Parallel parsing with smart prompts

new activity about 2 months ago

trillionlabs/Trillion-7B-preview:Add paper link to model card

upvoted a paper about 2 months ago

Trillion 7B Technical Report

View all activity

Organizations

models 1

WonsukYangTL/Qwen-2.5-7B-Simple-RL

datasets 0

None public yet