| { | |
| "architectures": [ | |
| "DebertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-07, | |
| "legacy": true, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0.0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 32, | |
| "pos_att_type": [ | |
| "none" | |
| ], | |
| "position_biased_input": true, | |
| "relative_attention": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.16.0.dev0", | |
| "type_vocab_size": 16, | |
| "vocab_size": 50265 | |
| } | |