HPD-Parsing
📄
5
Hierarchical parallel document parsing with a 1B VLM
WEI
WEISHU
AI & ML interests
None yet
Recent Activity
updated a Space 4 days ago
PaddlePaddle/hpd-parsing new activity 4 days ago
PaddlePaddle/HPD-Parsing:Demo for this model on Spaces new activity 4 days ago
PaddlePaddle/hpd-parsing:Render output as Markdown + bbox visualization (instead of raw text)Organizations
updated a
Space 4 days ago
Demo for this model on Spaces
👍 6
7
#1 opened 5 days ago
by 
multimodalart
Render output as Markdown + bbox visualization (instead of raw text)
1
#1 opened 4 days ago
by 
WEISHU
liked a
Space 4 days ago
liked a
model 5 days ago
authored a
paper 5 days ago
published a
model 5 days ago
upvoted a paper 5 days ago
updated a
model 5 days ago
Document_Parsing/doc2json 数据是不是不完整
1
#2 opened 2 months ago
by WEISHU
It appears that the Flash series models are not compatible with the vLLM framework for inference.
#1 opened 3 months ago
by WEISHU
0.8B with mtp is slower than without mtp
👀 1
#15 opened 4 months ago
by WEISHU
When vllm deployment is started using mtp config, an error will be reported. Please help！
2
#13 opened 4 months ago
by WEISHU
What are the correct versions of transformers and vllm?
4
#8 opened 4 months ago
by WEISHU
liked 2
models about 1 year ago
liked a
model almost 3 years ago
