zi's picture

zi

menglan

·

AI & ML interests

None yet

Organizations

None yet

New activity in Qwen/Qwen3-VL-30B-A3B-Instruct 4 months ago

how to use vllm to speed up inference?

#11 opened 4 months ago by

New activity in AIDC-AI/Ovis-Image-7B 5 months ago

Will You Make a Step+CFG Distill Version?

#3 opened 5 months ago by

New activity in meituan-longcat/LongCat-Image-Edit 5 months ago

possible to train a lora for it to do a certain task and multiple inputs for editing and referneces?

#4 opened 5 months ago by

New activity in tqliu/Light-Syn 5 months ago

Add comprehensive dataset card for Light-Syn

#1 opened 5 months ago by

New activity in WINDop/OpenGPT-4o-Image 6 months ago

Inconsistent Annotation Format and Lower Data Quality in the Editing Part

#4 opened 7 months ago by

Request to release task tags (e.g., Spatial Reasoning, Object Counting) used in the paper

#6 opened 7 months ago by

New activity in zhihefang/UltraHR-100K 7 months ago

can put the categories meta info (field) in the json file?

#2 opened 7 months ago by

New activity in OpenFace-CQUPT/HumanCaption-HQ-311K 7 months ago

how to download the image parts?

#3 opened 7 months ago by

New activity in tencent/HunyuanImage-2.1 8 months ago

RuntimeError: CUDA error: an illegal memory access was encountered

#5 opened 8 months ago by

New activity in AIDC-AI/Ovis2-34B about 1 year ago

How to only use the text and visual embedding?

#2 opened about 1 year ago by

New activity in google/siglip2-base-patch16-224 about 1 year ago

Error while loading processor: TypeError: expected str, bytes or os.PathLike object, not NoneType

#2 opened about 1 year ago by

New activity in OpenGVLab/InternVideo2_5_Chat_8B over 1 year ago

TypeError: chat() got an unexpected keyword argument 'video_path'

#2 opened over 1 year ago by

Error on get_vision_tower

#3 opened over 1 year ago by