michaelrglass's picture
First version of the SSPT for bert-large-uncased model and tokenizer
e623e2d
raw
history blame contribute delete
534 Bytes
{
"_name_or_path": "/users/mrglass/SSPT/large_100M_hf",
"architectures": [
"BertForQuestionAnswering"
],
"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,
"type_vocab_size": 2,
"vocab_size": 30522
}