{
  "_name_or_path": "chandar-lab/NeoBERT",
  "architectures": [
    "NeoBERT"
  ],
  "auto_map": {
    "AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
    "AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
    "AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
    "AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
  },
  "classifier_init_range": 0.02,
  "decoder_init_range": 0.02,
  "dim_head": 64,
  "embedding_init_range": 0.02,
  "hidden_size": 768,
  "intermediate_size": 3072,
  "kwargs": {
    "_commit_hash": "d97a4acdc851efed665d0550ea5704f00ad3ef76",
    "architectures": [
      "NeoBERTLMHead"
    ],
    "attn_implementation": null,
    "auto_map": {
      "AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
      "AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
      "AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
      "AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
    },
    "classifier_init_range": 0.02,
    "dim_head": 64,
    "kwargs": {
      "classifier_init_range": 0.02,
      "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
      "trust_remote_code": true
    },
    "model_type": "neobert",
    "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
    "torch_dtype": "float32",
    "transformers_version": "4.48.2",
    "trust_remote_code": true
  },
  "max_length": 4096,
  "model_type": "neobert",
  "norm_eps": 1e-05,
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "pad_token_id": 0,
  "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "trust_remote_code": true,
  "vocab_size": 30522
}