{ "video_params": { "model": "SpaceTimeTransformer", "arch_config": "base_patch16_224", "num_frames": 64, "pretrained": true, "time_init": "zeros" }, "text_params": { "model": "emilyalsentzer/Bio_ClinicalBERT", "pretrained": true, "input": "text" }, "projection": "minimal", "projection_dim": 512, "load_checkpoint": "" }