|
{ |
|
"model_type": "DebertaV2ForMaskedLM", |
|
"attention_probs_dropout_prob": 0.1, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"max_position_embeddings": 512, |
|
"relative_attention": true, |
|
"position_buckets": 256, |
|
"norm_rel_ebd": "layer_norm", |
|
"share_att_key": true, |
|
"pos_att_type": "c2p|p2c", |
|
"conv_kernel_size": 3, |
|
"conv_act": "gelu", |
|
"layer_norm_eps": 1e-7, |
|
"max_relative_positions": -1, |
|
"position_biased_input": false, |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"type_vocab_size": 0, |
|
"vocab_size": 12800 |
|
} |