# @package _group_ quantize_targets: true extractor_mode: layer_norm layer_norm_first: true final_dim: 768 latent_temp: [2.0,0.1,0.999995] encoder_layerdrop: 0.0 dropout_input: 0.0 dropout_features: 0.0 dropout: 0.0 attention_dropout: 0.0 conv_bias: true encoder_layers: 24 encoder_embed_dim: 1024 encoder_ffn_embed_dim: 4096 encoder_attention_heads: 16 feature_grad_mult: 1.0
