{
  "_name_or_path": "outputs/me5-base-v9/checkpoint-1950",
  "architectures": [
    "XLMRobertaModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 1024,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.45.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 16456,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "Turbo-AI/data-corpus",
      "dataset_column": "text",
      "dataset_name": null,
      "dataset_split": "train",
      "language": "vi",
      "min_frequency": 2,
      "target_vocab_size": null
    },
    "stats": {
      "compression_rate_embedding": 6.58234734122127,
      "compression_rate_full": 35.49094565181363,
      "parameter_size_embedding/raw": 192001536,
      "parameter_size_embedding/trimmed": 12638208,
      "parameter_size_full/raw": 278043648,
      "parameter_size_full/trimmed": 98680320,
      "vocab_size/raw": 250002,
      "vocab_size/trimmed": 16456
    }
  }
}