transformers/examples/research_projects/distillation/training_configs/distilbert-base-uncased.json

15 lines
277 B
JSON

{
"activation": "gelu",
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"n_heads": 12,
"n_layers": 6,
"sinusoidal_pos_embds": true,
"tie_weights_": true,
"vocab_size": 30522
}