config.json

{
  "_name_or_path": "ckpts/xlm-v-base-trimmed-de-10000",
  "architectures": [
    "XLMRobertaForMaskedLM"
  ],
  "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": 514,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.26.1",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 10002,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "vocabtrimmer/mc4_validation",
      "dataset_column": "text",
      "dataset_name": "de",
      "dataset_split": "validation",
      "language": "de",
      "min_frequency": 2,
      "target_vocab_size": 10000
    },
    "stats": {
      "compression_rate_embedding": 1.1093254542611206,
      "compression_rate_full": 12.026639093224697,
      "parameter_size_embedding/raw": 692451072,
      "parameter_size_embedding/trimmed": 7681536,
      "parameter_size_full/raw": 779396349,
      "parameter_size_full/trimmed": 93735186,
      "vocab_size/raw": 901629,
      "vocab_size/trimmed": 10002
    }
  }
}