config.json

{
  "adapters": {
    "adapters": {
    },
    "config_map": {
      "d345095bcb01e325": {
        "adapter_residual_before_ln": false,
        "attention_type": null,
        "invertible_adapter": null,
        "leave_out": [],
        "ln_after": false,
        "ln_before": false,
        "mh_adapter": false,
        "new_attention_norm": null,
        "non_linearity": "gelu",
        "original_ln_after": true,
        "original_ln_before": true,
        "output_adapter": true,
        "reduction_factor": 2,
        "residual_before_ln": true
      },
      "text_lang": {
        "adapter_residual_before_ln": false,
        "attention_type": null,
        "invertible_adapter": null,
        "leave_out": [],
        "ln_after": false,
        "ln_before": false,
        "mh_adapter": false,
        "new_attention_norm": null,
        "non_linearity": "gelu",
        "original_ln_after": true,
        "original_ln_before": true,
        "output_adapter": true,
        "reduction_factor": 2,
        "residual_before_ln": true
      }
    }
  },
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "directionality": "bidi",
  "embeddings_type": "full",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "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": 32000
}