{ "_class_name": "GroundingEncoder", "_diffusers_version": "0.35.0.dev0", "fourier_freq": 32, "hidden_size": 2048, "init_logit": -5.0, "max_hoi_seq": 32, "mlp_out_std": 0.0003, "n_roles": 3, "pos_embed_dim": 32, "role_embed_dim": 32, "role_std": 0.02, "text_encoder_dim": 4096 }