google/electra-base-discriminator
18448.1m
1{2 "architectures": [3 "ElectraForPreTraining"4 ],5 "attention_probs_dropout_prob": 0.1,6 "embedding_size": 768,7 "hidden_act": "gelu",8 "hidden_dropout_prob": 0.1,9 "hidden_size": 768,10 "initializer_range": 0.02,11 "intermediate_size": 3072,12 "layer_norm_eps": 1e-12,13 "max_position_embeddings": 512,14 "model_type": "electra",15 "num_attention_heads": 12,16 "num_hidden_layers": 12,17 "pad_token_id": 0,18 "position_embedding_type": "absolute",19 "summary_activation": "gelu",20 "summary_last_dropout": 0.1,21 "summary_type": "first",22 "summary_use_proj": true,23 "transformers_version": "4.6.0.dev0",24 "type_vocab_size": 2,25 "vocab_size": 3052226}27 