{ "_class_name": "UMT5EncoderModel", "architectures": [ "UMT5EncoderModel" ], "classifier_dropout": 0.0, "d_ff": 10240, "d_kv": 64, "d_model": 4096, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "model_type": "umt5", "num_decoder_layers": null, "num_heads": 64, "num_layers": 24, "output_hidden_states": false, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "stacked_params_mapping": [ [ ".qkv_proj", ".q", "q" ], [ ".qkv_proj", ".k", "k" ], [ ".qkv_proj", ".v", "v" ] ], "use_cache": true, "vocab_size": 256384 }