{ "architectures": [ "DebertaV2ForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": 768, "layer_norm_eps": 1e-07, "max_position_embeddings": 128, "max_relative_positions": -1, "model_type": "deberta-v2", "num_attention_heads": 4, "num_hidden_layers": 12, "pad_token_id": 1, "pooler_dropout": 0, "pooler_hidden_act": "gelu", "pooler_hidden_size": 256, "pos_att_type": [ "p2c", "c2p" ], "position_biased_input": false, "relative_attention": true, "tokenizer_class": "BertTokenizer", "torch_dtype": "float32", "transformers_version": "4.42.4", "type_vocab_size": 0, "vocab_size": 30000 }