config.json

{
  "_name_or_path": "param-bharat/ModernBERT-large-nli-clf",
  "architectures": [
    "ModernBertForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 50281,
  "classifier_activation": "gelu",
  "classifier_bias": true,
  "classifier_dropout": 0.3,
  "classifier_pooling": "cls",
  "cls_token_id": 50281,
  "custom_pipelines": {
    "nli-scorer": {
      "impl": "pipeline.NLIScorer",
      "pt": [
        "AutoModelForSequenceClassification"
      ],
      "tf": []
    }
  },
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "embedding_dropout": 0.0,
  "eos_token_id": 50282,
  "global_attn_every_n_layers": 3,
  "global_rope_theta": 160000.0,
  "gradient_checkpointing": false,
  "hidden_activation": "gelu",
  "hidden_size": 1024,
  "id2label": {
    "0": "False",
    "1": "True"
  },
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 2624,
  "label2id": {
    "False": 0,
    "True": 1
  },
  "layer_norm_eps": 1e-05,
  "local_attention": 128,
  "local_rope_theta": 10000.0,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "model_type": "modernbert",
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "pad_token_id": 50283,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "reference_compile": true,
  "sep_token_id": 50282,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "torch_dtype": "float32",
  "transformers_version": "4.48.0.dev0",
  "vocab_size": 50368
}