gf-20L-95M-i4096/config.json

{
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.02,
  "classifier_dropout": null,
  "hidden_act": "relu",
  "hidden_dropout_prob": 0.02,
  "hidden_size": 896,
  "initializer_range": 0.02,
  "intermediate_size": 1792,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 4096,
  "model_type": "bert",
  "num_attention_heads": 14,
  "num_hidden_layers": 20,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.37.1",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 20275
}