ibert-roberta-large / config.json
kssteven's picture
tokenizer
1013025
raw
history blame
542 Bytes
{
"architectures": [
"IBertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "ibert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"tokenizer_class": "RobertaTokenizer",
"type_vocab_size": 1,
"vocab_size": 50265,
"quant_mode": false
}