config.json

{
  "_name_or_path": "mjbommar/ogbert-2m-base",
  "architectures": [
    "ModernBertForMaskedLM"
  ],
  "model_type": "modernbert",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "cls_token_id": 4,
  "eos_token_id": 1,
  "sep_token_id": 5,
  "pad_token_id": 2,
  "unk_token_id": 3,
  "mask_token_id": 6,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "cls",
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "dtype": "float32",
  "embedding_dropout": 0.0,
  "global_attn_every_n_layers": 3,
  "hidden_act": "gelu",
  "hidden_activation": "gelu",
  "hidden_size": 128,
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 512,
  "layer_norm_eps": 1e-05,
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "local_attention": 128,
  "max_position_embeddings": 1024,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 4,
  "num_hidden_layers": 4,
  "repad_logits_with_grad": false,
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 160000.0,
      "rope_type": "default"
    },
    "sliding_attention": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    }
  },
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "torch_dtype": "float32",
  "transformers_version": "4.47.0",
  "vocab_size": 8192
}