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": 768,
10
    "initializer_range": 0.02,
11
    "intermediate_size": 3072,
12
    "layer_norm_eps": 1e-12,
13
    "max_position_embeddings": 4096,
14
    "model_type": "bert",
15
    "num_attention_heads": 12,
16
    "num_hidden_layers": 12,
17
    "pad_token_id": 3,
18
    "pre_layer_norm": true,
19
    "last_layer_norm": false,
20
    "position_embedding_type": "rotary",
21
    "rotary_base": 10000,
22
    "rotary_dim": 32,
23
    "transformers_version": "4.6.0.dev0",
24
    "type_vocab_size": 2,
25
    "use_cache": true,
26
    "vocab_size": 32000,
27
    "sparse_config_cls": "deepspeed.ops.sparse_attention:BigBirdSparsityConfig",
28
    "sparse_attention": {
29
      "num_heads": 12,
30
      "block": 64,
31
      "different_layout_per_head": true,
32
      "num_sliding_window_blocks": 3,
33
      "num_global_blocks": 2,
34
      "num_random_blocks": 3
35
    }
36
}