{
  "_name_or_path": "LuluHu/dnam2_100k",
  "alibi_starting_size": 512,
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.0,
  "bidirectional": true,
  "classifier_dropout": null,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "hyena_emb_dim": 5,
  "hyena_filter_dropout": 0.2,
  "hyena_filter_order": 128,
  "hyena_lr_pos_emb": 1e-05,
  "hyena_training_additions": false,
  "hyena_w": 10,
  "hyena_w_mod": 1,
  "hyena_wd": 0.1,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "long_conv_kernel_learning_rate": 0.001,
  "long_conv_l_max": 512,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "monarch_mixer_sequence_mixing": true,
  "monarch_mlp_nblocks": 4,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "pool_all": false,
  "position_embedding_type": "absolute",
  "residual_long_conv": true,
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "use_flash_fft": false,
  "use_flash_mm": false,
  "use_glu_mlp": true,
  "use_monarch_mlp": true,
  "use_positional_encodings": true,
  "vocab_size": 5504
}