config.json

{
  "architectures": [
    "CharmenElectraModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "config.CharmenElectraConfig",
    "AutoModel": "modeling_charmen.CharmenElectraModel",
    "AutoModelForMultipleChoice": "modeling_charmen.CharmenElectraForMultipleChoice",
    "AutoModelForSequenceClassification": "modeling_charmen.CharmenElectraForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_charmen.CharmenElectraForTokenClassification"
  },
  "classifier_dropout": null,
  "downsampling_factor": 4,
  "embedding_size": 768,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-12,
  "max_block_size": 4,
  "max_position_embeddings": 1024,
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "position_embedding_type": "absolute",
  "sampling": "fp32_gumbel",
  "score_consensus_attn": true,
  "summary_activation": "gelu",
  "summary_last_dropout": 0.1,
  "summary_type": "first",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.21.0",
  "type_vocab_size": 2,
  "upsample_output": true,
  "vocab_size": 261
}