hhou435's picture
First version of the chinese_roberta_L-10_H-128 model and tokenizer.
c047318
raw
history blame
No virus
563 Bytes
{
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 128,
"initializer_range": 0.02,
"intermediate_size": 512,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 2,
"num_hidden_layers": 10,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"transformers_version": "4.2.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 21128
}