{
  "_name_or_path": "/scratch/fastscratch/NBL/trained_models/test/prokbert-mini-k6s1/checkpoint-470000",
  "architectures": [
    "MegatronBertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 384,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 1024,
  "model_type": "megatron-bert",
  "num_attention_heads": 6,
  "num_hidden_layers": 6,
  "pad_token_id": 0,
  "position_embedding_type": "relative_key_query",
  "torch_dtype": "float32",
  "transformers_version": "4.30.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 4101
}