{ "_name_or_path": "t5-base", "architectures": [ "T5ForConditionalGeneration" ], "d_ff": 3072, "d_kv": 64, "d_model": 768, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "relu", "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 12, "num_heads": 12, "num_layers": 12, "output_past": true, "pad_token_id": 0, "relative_attention_num_buckets": 32, "task_specific_params": { "translation_amr_to_text": { "corpus_dir": "data/tdata_generate_t5wtense/", "max_in_len": 512, "max_out_len": 90, "model_name_or_path": "t5-base", "train_fn": "train.txt.features.nowiki.tdata", "valid_fn": "dev.txt.features.nowiki.tdata" } }, "use_cache": true, "vocab_size": 32128 }