transformers/examples/research_projects/distillation/training_configs/distilroberta-base.json

14 lines
364 B
JSON

{
"vocab_size": 50265,
"hidden_size": 768,
"num_hidden_layers": 6,
"num_attention_heads": 12,
"intermediate_size": 3072,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"attention_probs_dropout_prob": 0.1,
"max_position_embeddings": 514,
"type_vocab_size": 1,
"initializer_range": 0.02,
"layer_norm_eps": 0.00001
}