shi-labs/CuMo_dataset download history
shi-labs/CuMo_dataset is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 31 times (13 in the last 7 days), and 827 times in total. It ranks #376,003 among datasets by monthly downloads.
CuMo contains three-stage training: Stage 1: Pre-Training In this stage, we use LLaVA-558K to pretrain MLP. Stage 2: Pre-FineTuning For pre-finetuning, we use the ALLaVA caption data, you may use the original one or the cumo_pft_allava.json in this repo. Stage 3: Visual Instruction Tuning LLaVA-665
Open shi-labs/CuMo_dataset on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.