26 lines
No EOL
652 B
JSON
Executable file
26 lines
No EOL
652 B
JSON
Executable file
{
|
|
"architectures": [
|
|
"BertForMaskedLM"
|
|
],
|
|
"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",
|
|
"type_vocab_size": 2,
|
|
"use_cache": true,
|
|
"vocab_size": 30522,
|
|
"fusion_layer": 19,
|
|
"encoder_width": 1024,
|
|
"cross_module": "ca"
|
|
}
|
|
|