tokenizer/config.json

{
  "architectures": [
    "GenerannoForTokenClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_generanno.GenerannoConfig",
    "AutoModel": "modeling_generanno.GenerannoModel",
    "AutoModelForMaskedLM": "modeling_generanno.GenerannoForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_generanno.GenerannoForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_generanno.GenerannoForTokenClassification"
  },
  "id2label": {
    "0": "NON_CODING",
    "1": "CDS"
  },
  "label2id": {
    "NON_CODING": 0,
    "CDS": 1
  },
  "k": 6,
  "num_prediction_heads": 2,
  "bos_token_id": 1,
  "dtype": "float32",
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "mask_token_id": 4,
  "max_position_embeddings": 16384,
  "mlp_bias": false,
  "model_type": "generanno",
  "num_attention_heads": 32,
  "num_hidden_layers": 26,
  "num_key_value_heads": 4,
  "pad_token_id": 3,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.0",
  "use_cache": true,
  "vocab_size": 4128
}