nb-bert-large / config.json
versae's picture
First version of nb-bert-large (codename: T10)
359e05b
raw
history blame
518 Bytes
{
"attention_probs_dropout_prob": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"transformers_version": "4.3.3",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 50000
}