Chao Jiang
first version of wiki-sentence-alignment fine-tuned BERT model and the tokenizer
e188626
raw
history blame
553 Bytes
{
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"finetuning_task": "newsela_task2",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_labels": 2,
"output_attentions": false,
"output_hidden_states": true,
"pruned_heads": {},
"torchscript": false,
"type_vocab_size": 2,
"vocab_size": 30522
}