bert/deberta-v2-large-japanese/config.json

{
  "_name_or_path": "configs/deberta_v2_large.json",
  "architectures": [
    "DebertaV2ForMaskedLM"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "conv_act": "gelu",
  "conv_kernel_size": 3,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-07,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "pooler_dropout": 0,
  "pooler_hidden_act": "gelu",
  "pooler_hidden_size": 1024,
  "pos_att_type": [
    "p2c",
    "c2p"
  ],
  "position_biased_input": false,
  "position_buckets": 256,
  "relative_attention": true,
  "share_att_key": true,
  "torch_dtype": "float32",
  "transformers_version": "4.23.1",
  "type_vocab_size": 0,
  "vocab_size": 32000
}