{ "_name_or_path": "t5-base", "architectures": [ "T5ForConditionalGeneration" ], "attn_method": "linear", "attn_prefix_tuning": false, "class_weights": null, "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", "fix_attention": false, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7" }, "ignore_target": false, "init_prefix_method": "random", "initializer_factor": 1.0, "is_contrastive": false, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7 }, "label_based": false, "label_token_ids": [ [ 16, 10454, 2493, 1 ], [ 1921, 1 ], [ 1690, 1 ], [ 21530, 1 ], [ 11746, 1 ], [ 11122, 1 ], [ 822, 1 ], [ 30430, 1 ] ], "layer_norm_epsilon": 1e-06, "learned_temperature": false, "max_length": 12, "model_type": "t5", "n_positions": 512, "normalize_prefixes": false, "num_decoder_layers": 12, "num_heads": 12, "num_layers": 12, "num_target": 1, "output_past": true, "pad_token_id": 0, "prefix_num": 1, "prefix_tuning": false, "relative_attention_num_buckets": 32, "shared_attn": false, "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: " } }, "temperature": 2000, "train_task_adapters": true, "transformers_version": "4.6.0", "use_cache": true, "vocab_size": 32100 }