config.json

{
  "architectures": [
    "BertLMHeadModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "encoder_ln_mode": "pre-ln",
  "fused_linear_layer": true,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 256,
  "layer_norm_eps": 1e-12,
  "layer_norm_type": "apex",
  "layernorm_embedding": false,
  "max_position_embeddings": 512,
  "max_seq_length": 512,
  "model_type": "bert",
  "num_attention_heads": 1,
  "num_hidden_layers": 1,
  "pad_token_id": 2,
  "position_embedding_type": false,
  "sparse_mask_prediction": true,
  "task_category": "classification",
  "torch_dtype": "float32",
  "transformers_version": "4.37.2",
  "type_vocab_size": 2,
  "useLN": true,
  "use_cache": true,
  "vocab_size": 2368
}