r-terada's picture
Upload config.json
ee524e9
raw
history blame contribute delete
625 Bytes
{
"architectures": [
"ElectraForPreTraining"
],
"model_type": "electra",
"model_name": "base",
"vocab_size": 30112,
"embedding_size": 768,
"hidden_size": 768,
"num_hidden_layers": 12,
"num_attention_heads": 12,
"intermediate_size": 3072,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"attention_probs_dropout_prob": 0.1,
"max_position_embeddings": 512,
"type_vocab_size": 2,
"initializer_range": 0.02,
"layer_norm_eps": 1e-12,
"summary_type": "first",
"summary_use_proj": true,
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"pad_token_id": 0,
"position_embedding_type": "absolute"
}