Back to model page
Model card Files and versions Use in transformers
m-polignano-uniba / bert_uncased_L-12_H-768_A-12_italian_alberto / config.json
system Update config.json 2f69d1e
raw history blame
780 Bytes
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
{
  "architectures": [
    "AlbertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 2,
  "classifier_dropout_prob": 0.1,
  "directionality": "bidi",
  "embedding_size": 128,
  "eos_token_id": 3,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "inner_group_num": 1,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "albert",
  "num_attention_heads": 12,
  "num_hidden_groups": 1,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "pooler_fc_size": 768,
  "pooler_num_attention_heads": 12,
  "pooler_num_fc_layers": 3,
  "pooler_size_per_head": 128,
  "pooler_type": "first_token_transform",
  "type_vocab_size": 2,
  "vocab_size": 128000
}