| { | |
| "architectures": [ | |
| "DebertaForMaskedLM" | |
| ], | |
| "attention_head_size": 128, | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 128, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 128, | |
| "pos_att_type": null, | |
| "position_biased_input": true, | |
| "relative_attention": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.2", | |
| "type_vocab_size": 0, | |
| "vocab_size": 9376 | |
| } | |