microsoft/mdeberta-v3-base
2445.4m
1{2 "model_type": "deberta-v2",3 "attention_probs_dropout_prob": 0.1,4 "hidden_act": "gelu",5 "hidden_dropout_prob": 0.1,6 "hidden_size": 768,7 "initializer_range": 0.02,8 "intermediate_size": 3072,9 "max_position_embeddings": 512,10 "max_relative_positions": -1,11 "num_attention_heads": 12,12 "num_hidden_layers": 6,13 "pos_att_type": "c2p|p2c",14 "position_biased_input": false,15 "position_buckets": 256,16 "norm_rel_ebd": "layer_norm",17 "relative_attention": true,18 "share_att_key": true,19 "type_vocab_size": 0,20 "layer_norm_eps": 1e-7,21 "vocab_size": 25100022}23 