config.json

{
  "architectures": [
    "GptBertModel"
  ],
  "attention_dropout": 0.0,
  "attn_implementation": null,
  "auto_map": {
    "AutoConfig": "configuration_gptbert.GptBertConfig",
    "AutoModel": "modeling_gptbert.GptBertModel",
    "AutoModelForCausalLM": "modeling_gptbert.GptBertForCausalLM",
    "AutoModelForMaskedLM": "modeling_gptbert.GptBertForMaskedLM",
    "AutoModelForMultipleChoice": "modeling_gptbert.GptBertForMultipleChoice",
    "AutoModelForQuestionAnswering": "modeling_gptbert.GptBertForQuestionAnswering",
    "AutoModelForSequenceClassification": "modeling_gptbert.GptBertForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_gptbert.GptBertForTokenClassification"
  },
  "bos_token_id": 1,
  "classifier_dropout": 0.2,
  "deterministic_flash_attn": false,
  "embedding_dropout": 0.1,
  "eos_token_id": 2,
  "global_window_length": 8192,
  "hidden_dropout": 0.0,
  "hidden_size": 960,
  "intermediate_size": 2560,
  "layer_norm_eps": 1e-07,
  "local_global_ratio": 4,
  "local_window_length": 256,
  "mask_token_id": 4,
  "max_sequence_length": 16384,
  "model": "norbert4",
  "num_attention_heads": 15,
  "num_layers": 28,
  "pad_token_id": 3,
  "query_key_head_size": 64,
  "rope_theta": 160000,
  "transformers_version": "4.56.2",
  "unk_token_id": 0,
  "use_cache": false,
  "value_head_size": 64,
  "vocab_size": 51200
}