config.json

{
  "architectures": [
    "ModernBertForMaskedLMCustom"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modern_bert.ModernBertConfigCustom",
    "AutoModel": "modern_bert.ModernBertModelCustom",
    "AutoModelForMaskedLM": "modern_bert.ModernBertForMaskedLMCustom"
  },
  "bos_token_id": null,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "cls",
  "cls_token_id": 1,
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "dtype": "float32",
  "embedding_dropout": 0.0,
  "eos_token_id": null,
  "hidden_activation": "gelu",
  "hidden_size": 768,
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 1152,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "local_attention": 128,
  "max_position_embeddings": 256,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "model_type": "modern_bert",
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 12,
  "num_hidden_layers": 24,
  "pad_token_id": 3,
  "repetition_factor": 4,
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 160000.0,
      "rope_type": "default"
    },
    "sliding_attention": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    }
  },
  "sep_token_id": 2,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "tie_word_embeddings": true,
  "transformers_version": "5.9.0",
  "vocab_size": 24000
}