deepset/deberta-v3-large-squad2
527.3k
1{2 "_name_or_path": "checkpoint_deberta_large/language_model.bin",3 "architectures": [4 "DebertaV2ForQuestionAnswering"5 ],6 "attention_probs_dropout_prob": 0.1,7 "hidden_act": "gelu",8 "hidden_dropout_prob": 0.1,9 "hidden_size": 1024,10 "initializer_range": 0.02,11 "intermediate_size": 4096,12 "language": "english",13 "layer_norm_eps": 1e-07,14 "max_position_embeddings": 512,15 "max_relative_positions": -1,16 "model_type": "deberta-v2",17 "name": "DebertaV2",18 "norm_rel_ebd": "layer_norm",19 "num_attention_heads": 16,20 "num_hidden_layers": 24,21 "pad_token_id": 0,22 "pooler_dropout": 0,23 "pooler_hidden_act": "gelu",24 "pooler_hidden_size": 1024,25 "pos_att_type": [26 "p2c",27 "c2p"28 ],29 "position_biased_input": false,30 "position_buckets": 256,31 "relative_attention": true,32 "share_att_key": true,33 "summary_activation": "tanh",34 "summary_last_dropout": 0,35 "summary_type": "first",36 "summary_use_proj": false,37 "torch_dtype": "float32",38 "transformers_version": "4.19.0",39 "type_vocab_size": 0,40 "vocab_size": 12810041}42 