bert_12_layer_model_v2 / config.json
gokuls's picture
Training in progress, epoch 1
5bb437a
raw
history blame
482 Bytes
{
"activation": "gelu",
"architectures": [
"DistilBertForMaskedLM"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "hybridbert",
"n_heads": 12,
"n_layers": 12,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": true,
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"vocab_size": 30522
}