{ "architectures": [ "T5ForConditionalGenerationWithMemDecLossFix" ], "d_ff": 3072, "d_kv": 64, "d_model": 768, "dec_memory_length": 16, "dec_mixing_ratio": 0.5, "dec_type": "parallel", "decoder_start_token_id": 0, "distance": "euclidean", "dropout_rate": 0.1, "eos_token_id": 1, "finetuning_task": "email_short_span_loss_fix", "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "margin": 1.0, "max_input_length": 512, "memory_init": "speaker", "memory_length": 16, "memory_type": "no_memory", "mixing_ratio": 0.0, "model_type": "t5", "n_positions": 512, "num_heads": 12, "num_layers": 12, "oracle_memory": "old", "output_past": true, "pad_token_id": 0, "per_turn_length": 1, "pooling": "first", "relative_attention_num_buckets": 32, "speaker": "none", "task_specific_params": { "summarization": { "early_stopping": true, "length_penalty": 2.0, "max_length": 200, "min_length": 30, "no_repeat_ngram_size": 3, "num_beams": 4, "prefix": "summarize: " }, "translation_en_to_de": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to German: " }, "translation_en_to_fr": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to French: " }, "translation_en_to_ro": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to Romanian: " } }, "turn_length": 10, "vocab_size": 32128 }