google/bert_for_seq_generation_L-24_bbc_encoder
137k
1{2 "architectures": [3 "BertForSeqGenerationEncoderModel"4 ],5 "attention_probs_dropout_prob": 0.1,6 "directionality": "bidi",7 "gradient_checkpointing": false,8 "hidden_act": "gelu",9 "hidden_dropout_prob": 0.1,10 "hidden_size": 1024,11 "initializer_range": 0.02,12 "intermediate_size": 4096,13 "layer_norm_eps": 1e-12,14 "max_position_embeddings": 512,15 "model_type": "bert-generation",16 "num_attention_heads": 16,17 "num_hidden_layers": 24,18 "pad_token_id": 0,19 "vocab_size": 5035820}