alxxtexxr/coco_captions_1.25k_serialized_for_Qwen3-VL-8B-Instruct-with-Codebook-8K

--- dataset_info: features: - name: filename dtype: string - name: cocoid dtype: int64 - name: caption dtype: string - name: image dtype: image - name: image_serialized dtype: string splits: - name: train num_bytes: 395057737 num_examples: 1000 - name: val num_bytes: 49382217 num_examples: 125 - name: test num_bytes: 49382217 num_examples: 125 download_size: 490950265 dataset_size: 493822171 configs: - config_name: default data_files: - split: train path: data/train-* - split: val path: data/val-* - split: test path: data/test-* ---