{
  "_name_or_path": "ckpts/xlm-roberta-base-xnli-de-trimmed-de-5000",
  "architectures": [
    "XLMRobertaForSequenceClassification"
  ],
  "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,
  "id2label": {
    "0": "entailment",
    "1": "neutral",
    "2": "contradiction"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "contradiction": 2,
    "entailment": 0,
    "neutral": 1
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.26.1",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 5002,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "vocabtrimmer/mc4_validation",
      "dataset_column": "text",
      "dataset_name": "de",
      "dataset_split": "validation",
      "language": "de",
      "min_frequency": 2,
      "target_vocab_size": 5000
    },
    "stats": {
      "compression_rate_embedding": 2.0007839937280503,
      "compression_rate_full": 32.32773337774326,
      "parameter_size_embedding/raw": 192001536,
      "parameter_size_embedding/trimmed": 3841536,
      "parameter_size_full/raw": 278045955,
      "parameter_size_full/trimmed": 89885955,
      "vocab_size/raw": 250002,
      "vocab_size/trimmed": 5002
    }
  }
}