config.json

{
  "_name_or_path": "MrPotato/ref-seg-ger_large_tokenized",
  "alpha": 0.5,
  "architectures": [
    "XLMRobertaForReferenceSegmentation"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_refseg.XLMRobertaRefSegConfig",
    "AutoModelForTokenClassification": "modeling_refseg.XLMRobertaForReferenceSegmentation"
  },
  "bos_token_id": 0,
  "classifier_dropout": null,
  "custom_pipelines": {
    "ref-seg": {
      "impl": "ref_seg.RefSegPipeline",
      "pt": [
        "AutoModelForTokenClassification"
      ],
      "tf": [
        "TFAutoModelForTokenClassification"
      ]
    }
  },
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "xlm-roberta",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_labels_first": 29,
  "num_labels_second": 2,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.25.1",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 250002
}