NLPclass/mt5-title-generation
019
1{2 "_name_or_path": "/kaggle/working/outputs/best_model",3 "architectures": [4 "MT5ForConditionalGeneration"5 ],6 "classifier_dropout": 0.0,7 "d_ff": 1024,8 "d_kv": 64,9 "d_model": 512,10 "decoder_start_token_id": 0,11 "dense_act_fn": "gelu_new",12 "dropout_rate": 0.1,13 "eos_token_id": 1,14 "feed_forward_proj": "gated-gelu",15 "initializer_factor": 1.0,16 "is_encoder_decoder": true,17 "is_gated_act": true,18 "layer_norm_epsilon": 1e-06,19 "model_type": "mt5",20 "num_decoder_layers": 8,21 "num_heads": 6,22 "num_layers": 8,23 "pad_token_id": 0,24 "relative_attention_max_distance": 128,25 "relative_attention_num_buckets": 32,26 "tie_word_embeddings": false,27 "tokenizer_class": "T5Tokenizer",28 "torch_dtype": "float32",29 "transformers_version": "4.42.3",30 "use_cache": true,31 "vocab_size": 25011232}33 