Tencent releases Youtu-Parsing-Omni multimodal document parsing model
Tencent published Youtu-Parsing-Omni, an image-text-to-text model for document parsing and OCR, on Hugging Face. The model uses the youtu_vita architecture and is available in transformers and safetensors formats.
First seen 9 Oct, 06:42 UTC on Hugging Face · tencent1 sourceLast update 3h ago
TencentLaunch · 9 Oct
Youtu-Parsing-Omni
Open-weight model
Openweights
What the sources say
Linked, never rewritten. Official means the lab itself.
Press0
No independent coverage yet.
How it unfolded
Every source in the order it appeared. Times in UTC.
Keep up with Tencent
Tencent on the ScoreIts timelineFollow to mark Tencent's stories across the site. No account needed.