| { | |
| "architectures": [ | |
| "DebertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "embedding_size": 32, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 64, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 128, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 768, | |
| "pooler_size": 32, | |
| "pos_att_type": [ | |
| "c2p", | |
| "p2c" | |
| ], | |
| "position_biased_input": false, | |
| "relative_attention": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.9.0.dev0", | |
| "type_vocab_size": 0, | |
| "vocab_size": 5001 | |
| } | |