stefan-it's picture
config: add initial configuration for DistilBERT model
832adff
raw
history blame
440 Bytes
{
"_name_or_path": "student_init_pytorch_model.bin",
"activation": "gelu",
"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": true,
"tie_weights_": true,
"vocab_size": 32000
}