ScholarBERT-XL / config.json
globuslabs's picture
Add PyTorch model
837c388
raw
history blame contribute delete
732 Bytes
{
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1280,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-12,
"lowercase": false,
"max_position_embeddings": 512,
"model_name": "bert-xl-cased",
"model_type": "bert",
"next_sentence": false,
"num_attention_heads": 20,
"num_hidden_layers": 36,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"tokenizer": "wordpiece",
"torch_dtype": "float32",
"transformers_version": "4.9.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_file": "vocab.txt",
"vocab_size": 50000
}