{ "architectures": [ "MyBertForMaskedLM" ], "attention_probs_dropout_prob": 0.0, "auto_map": { "AutoConfig": "configuration_mybert.MyBertConfig", "AutoModel": "modeling_mybert.MyBertModel", "AutoModelForMaskedLM": "modeling_mybert.MyBertForMaskedLM", "AutoModelForSequenceClassification": "modeling_mybert.MyBertForSequenceClassification", "AutoModelForTokenClassification": "modeling_mybert.MyBertForTokenClassification", "AutoModelForQuestionAnswering": "modeling_mybert.MyBertForQuestionAnswering" }, "dtype": "float32", "hidden_dropout_prob": 0.0, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 2048, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "model_type": "mybert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "rope_theta": 10000.0, "sparse_prediction": true, "tie_word_embeddings": true, "transformers_version": "5.13.1", "use_bias": false, "vocab_size": 28996 }