encoder/config.json

{
  "architectures": [
    "NeoBERTLMHead"
  ],
  "auto_map": {
    "AutoConfig": "modeling_neobert.NeoBERTConfig",
    "AutoModel": "modeling_neobert.NeoBERT",
    "AutoModelForMaskedLM": "modeling_neobert.NeoBERTLMHead",
    "AutoModelForQuestionAnswering": "modeling_neobert.NeoBERTForQuestionAnswering",
    "AutoModelForSequenceClassification": "modeling_neobert.NeoBERTForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_neobert.NeoBERTForTokenClassification"
  },
  "decoder_init_range": 0.02,
  "dim_head": 64,
  "dtype": "bfloat16",
  "embedding_init_range": 0.02,
  "encoder_init_range": 0.02,
  "hidden_size": 768,
  "intermediate_size": 3072,
  "max_length": 4096,
  "model_type": "neobert",
  "norm_eps": 1e-06,
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "pad_token_id": 3,
  "transformers_version": "5.16.1",
  "vocab_size": 128000
}