{
  "architectures": [
    "BertModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "dtype": "float32",
  "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": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "tokenizer_class": "XLMRobertaTokenizer",
  "transformers_version": "4.57.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 32768,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "lbourdois/fineweb-2-trimming",
      "dataset_column": "text",
      "dataset_name": "spa",
      "dataset_split": "train",
      "language": "spa",
      "min_frequency": 2,
      "target_vocab_size": 32766
    },
    "stats": {
      "compression_rate_embedding": 13.105260421457624,
      "compression_rate_full": 29.054006517898607,
      "parameter_size_embedding/raw": 96014208,
      "parameter_size_embedding/trimmed": 12582912,
      "parameter_size_full/raw": 117904565,
      "parameter_size_full/trimmed": 34256000,
      "vocab_size/raw": 250037,
      "vocab_size/trimmed": 32768
    }
  }
}