config.json

{
  "_name_or_path": "dangvantuan/bilingual_impl",
  "architectures": [
    "BilingualModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "config.BilingualConfig",
    "AutoModel": "modeling.BilingualModel",
    "AutoModelForMaskedLM": "dangvantuan/bilingual_impl--modeling.BilingualForMaskedLM",
    "AutoModelForMultipleChoice": "dangvantuan/bilingual_impl--modeling.BilingualForMultipleChoice",
    "AutoModelForQuestionAnswering": "dangvantuan/bilingual_impl--modeling.BilingualForQuestionAnswering",
    "AutoModelForSequenceClassification": "dangvantuan/bilingual_impl--modeling.BilingualForSequenceClassification",
    "AutoModelForTokenClassification": "dangvantuan/bilingual_impl--modeling.BilingualForTokenClassification"
  },
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bilingual",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.42.3",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 250037
}