kamalkraj/deberta-base
097
1{2 "_name_or_path": "microsoft/deberta-base",3 "architectures": [4 "DebertaModel"5 ],6 "attention_probs_dropout_prob": 0.1,7 "hidden_act": "gelu",8 "hidden_dropout_prob": 0.1,9 "hidden_size": 768,10 "initializer_range": 0.02,11 "intermediate_size": 3072,12 "layer_norm_eps": 1e-07,13 "max_position_embeddings": 512,14 "max_relative_positions": -1,15 "model_type": "deberta",16 "num_attention_heads": 12,17 "num_hidden_layers": 12,18 "pad_token_id": 0,19 "pooler_dropout": 0,20 "pooler_hidden_act": "gelu",21 "pooler_hidden_size": 768,22 "pos_att_type": [23 "c2p",24 "p2c"25 ],26 "position_biased_input": false,27 "relative_attention": true,28 "transformers_version": "4.10.0.dev0",29 "type_vocab_size": 0,30 "vocab_size": 5026531}32 