{ "_name_or_path": "csebuetnlp/mT5_m2o_english_crossSum", "architectures": [ "MT5ForConditionalGeneration" ], "classifier_dropout": 0.0, "d_ff": 2048, "d_kv": 64, "d_model": 768, "decoder_start_token_id": 250030, "dense_act_fn": "gelu_new", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "length_penalty": 0.6, "max_length": 84, "model_type": "mt5", "num_beams": 4, "num_decoder_layers": 12, "num_heads": 12, "num_layers": 12, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "task_specific_params": { "langid_map": { "amharic": [ 35, "\u2581" ], "arabic": [ 4, "\u2581" ], "azerbaijani": [ 7, "\u2581" ], "bengali": [ 42, "\u2581" ], "burmese": [ 33, "\u2581" ], "chinese_simplified": [ 40, "\u2581" ], "chinese_traditional": [ 44, "\u2581" ], "english": [ 30, "\u2581" ], "french": [ 10, "\u2581" ], "gujarati": [ 27, "\u2581" ], "hausa": [ 43, "\u2581" ], "hindi": [ 21, "\u2581" ], "igbo": [ 9, "\u2581" ], "indonesian": [ 1, "\u2581" ], "japanese": [ 37, "\u2581" ], "kirundi": [ 0, "\u2581" ], "korean": [ 29, "\u2581" ], "kyrgyz": [ 5, "\u2581" ], "marathi": [ 13, "\u2581" ], "nepali": [ 20, "\u2581" ], "oromo": [ 41, "\u2581" ], "pashto": [ 34, "\u2581" ], "persian": [ 23, "\u2581" ], "pidgin": [ 14, "\u2581" ], "portuguese": [ 39, "\u2581" ], "punjabi": [ 17, "\u2581" ], "russian": [ 36, "\u2581" ], "scottish_gaelic": [ 24, "\u2581" ], "serbian_cyrillic": [ 28, "\u2581" ], "serbian_latin": [ 11, "\u2581" ], "sinhala": [ 31, "\u2581" ], "somali": [ 19, "\u2581" ], "spanish": [ 3, "\u2581" ], "swahili": [ 18, "\u2581" ], "tamil": [ 32, "\u2581" ], "telugu": [ 22, "\u2581" ], "thai": [ 6, "\u2581" ], "tigrinya": [ 16, "\u2581" ], "turkish": [ 15, "\u2581" ], "ukrainian": [ 2, "\u2581" ], "urdu": [ 38, "\u2581" ], "uzbek": [ 8, "\u2581" ], "vietnamese": [ 12, "\u2581" ], "welsh": [ 26, "\u2581" ], "yoruba": [ 25, "\u2581" ] } }, "tie_word_embeddings": false, "tokenizer_class": "T5Tokenizer", "torch_dtype": "float32", "transformers_version": "4.44.2", "use_cache": true, "vocab_size": 250112 }