{
 "version": "0.1",
 "base": "answerdotai/ModernBERT-large",
 "flags": {
  "cached": true,
  "markers": true,
  "v3": true
 },
 "encoder": {
  "transformers_version": "5.19.0",
  "architectures": [
   "ModernBertForMaskedLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "float32",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
   "0": "LABEL_0",
   "1": "LABEL_1"
  },
  "label2id": {
   "LABEL_0": 0,
   "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 50432,
  "hidden_size": 1024,
  "intermediate_size": 2624,
  "num_hidden_layers": 28,
  "num_attention_heads": 16,
  "hidden_activation": "gelu",
  "max_position_embeddings": 8192,
  "initializer_range": 0.02,
  "initializer_cutoff_factor": 2.0,
  "norm_eps": 1e-05,
  "norm_bias": false,
  "pad_token_id": 50283,
  "eos_token_id": 50282,
  "bos_token_id": 50281,
  "cls_token_id": 50281,
  "sep_token_id": 50282,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "layer_types": [
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention"
  ],
  "rope_parameters": {
   "full_attention": {
    "rope_theta": 160000.0,
    "rope_type": "default"
   },
   "sliding_attention": {
    "rope_theta": 10000.0,
    "rope_type": "default"
   }
  },
  "local_attention": 128,
  "embedding_dropout": 0.0,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "decoder_bias": true,
  "classifier_pooling": "mean",
  "classifier_dropout": 0.0,
  "classifier_bias": false,
  "classifier_activation": "gelu",
  "deterministic_flash_attn": false,
  "sparse_prediction": false,
  "sparse_pred_ignore_index": -100,
  "tie_word_embeddings": true,
  "_name_or_path": "",
  "global_attn_every_n_layers": 3,
  "gradient_checkpointing": false,
  "layer_norm_eps": 1e-05,
  "model_type": "modernbert",
  "position_embedding_type": "absolute",
  "output_attentions": false
 }
}