rafmacalaba/datause-extraction-v4-finetuned
015
1{2 "_attn_implementation_autoset": true,3 "attention_probs_dropout_prob": 0.1,4 "dtype": "float32",5 "hidden_act": "gelu",6 "hidden_dropout_prob": 0.1,7 "hidden_size": 1024,8 "initializer_range": 0.02,9 "intermediate_size": 4096,10 "layer_norm_eps": 1e-07,11 "legacy": true,12 "max_position_embeddings": 512,13 "max_relative_positions": -1,14 "model_type": "deberta-v2",15 "norm_rel_ebd": "layer_norm",16 "num_attention_heads": 16,17 "num_hidden_layers": 24,18 "pad_token_id": 0,19 "pooler_dropout": 0,20 "pooler_hidden_act": "gelu",21 "pooler_hidden_size": 1024,22 "pos_att_type": [23 "p2c",24 "c2p"25 ],26 "position_biased_input": false,27 "position_buckets": 256,28 "relative_attention": true,29 "share_att_key": true,30 "transformers_version": "4.57.3",31 "type_vocab_size": 0,32 "vocab_size": 12801133}34 