Path: blob/master/C5 - Sequence Models/Week 4/Transformer Network/model_tfd/23454919702d26495337f3da04d1655c7ee010d5ec9d77bdb9e399e00302c0a1.d423bdf2f58dc8b77d5f5d18028d7ae4a72dcfd8f468e81fe979ada957a8c361
6555 views
{
"activation": "gelu",
"architectures": [
"DistilBertForMaskedLM"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"vocab_size": 30522
}