config.json

{
  "architectures": [
    "CoLwithBert"
  ],
  "attention_probs_dropout_prob": 0.1,
  "do_voken_cls": true,
  "do_voken_ctr": false,
  "do_voken_reg": false,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "pad_token_id": 0,
  "shared_head": false,
  "type_vocab_size": 2,
  "verbose": true,
  "vocab_size": 30522,
  "voken_dim": null,
  "voken_size": 50000
}