GENA_LM

1
{
2
    "architectures": [
3
      "BigBirdForPreTraining"
4
    ],
5
    "attention_probs_dropout_prob": 0.1,
6
    "attention_type": "block_sparse",
7
    "block_size": 64,
8
    "num_random_blocks": 3,
9
    "gradient_checkpointing": false,
10
    "hidden_act": "gelu_new",
11
    "hidden_dropout_prob": 0.1,
12
    "hidden_size": 768,
13
    "initializer_range": 0.02,
14
    "intermediate_size": 3072,
15
    "layer_norm_eps": 1e-12,
16
    "max_position_embeddings": 4096,
17
    "model_type": "big_bird",
18
    "num_attention_heads": 12,
19
    "num_hidden_layers": 12,
20
    "pad_token_id": 3,
21
    "position_embedding_type": "absolute",
22
    "rescale_embeddings": false,
23
    "transformers_version": "4.4.0.dev0",
24
    "type_vocab_size": 2,
25
    "use_bias": true,
26
    "use_cache": true,
27
    "vocab_size": 32000
28
  }