{
  "add_cross_attention": false,
  "architectures": [
    "DzairModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": null,
  "cls_token_id": 2,
  "cross_attention_hidden_size": null,
  "decoder_start_token_id": null,
  "dtype": "float32",
  "eos_token_id": null,
  "finetuning_task": null,
  "generator_hidden_size": 384,
  "generator_intermediate_size": 1024,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "intermediate_size": 1792,
  "is_decoder": false,
  "layer_norm_eps": 1e-05,
  "mask_token_id": 4,
  "max_position_embeddings": 512,
  "model_type": "dzair",
  "num_attention_heads": 12,
  "num_generator_layers": 3,
  "num_hidden_layers": 12,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "prefix": null,
  "pruned_heads": {},
  "qk_norm": true,
  "rope_theta": 10000.0,
  "sep_token_id": 3,
  "share_generator_embeddings": true,
  "task_specific_params": null,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": true,
  "tokenizer_class": null,
  "torchscript": false,
  "transformers_version": "5.17.0",
  "use_bfloat16": false,
  "vocab_size": 48000,
  "auto_map": {
    "AutoConfig": "modeling_dzair.DzairConfig",
    "AutoModel": "modeling_dzair.DzairModel",
    "AutoModelForMaskedLM": "modeling_dzair.DzairForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_dzair.DzairForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_dzair.DzairForTokenClassification"
  }
}