GENA_LM

1
{
2
    "architectures": [
3
      "BertForMaskedLM"
4
    ],
5
    "attention_probs_dropout_prob": 0.1,
6
    "gradient_checkpointing": false,
7
    "hidden_act": "gelu",
8
    "hidden_dropout_prob": 0.1,
9
    "hidden_size": 1024,
10
    "initializer_range": 0.02,
11
    "intermediate_size": 4096,
12
    "layer_norm_eps": 1e-5,
13
    "max_position_embeddings": 512,
14
    "model_type": "bert",
15
    "num_attention_heads": 16,
16
    "num_hidden_layers": 24,
17
    "pad_token_id": 3,
18
    "pre_layer_norm": true,
19
    "position_embedding_type": "absolute",
20
    "transformers_version": "4.6.0.dev0",
21
    "type_vocab_size": 2,
22
    "use_cache": true,
23
    "vocab_size": 32000
24
  }