{ "_name_or_path": "ltg/norbert3-large", "architectures": [ "NorbertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "auto_map": { "AutoConfig": "ltg/norbert3-large--configuration_norbert.NorbertConfig", "AutoModel": "ltg/norbert3-large--modeling_norbert.NorbertModel", "AutoModelForMaskedLM": "ltg/norbert3-large--modeling_norbert.NorbertForMaskedLM", "AutoModelForMultipleChoice": "ltg/norbert3-large--modeling_norbert.NorbertForMultipleChoice", "AutoModelForQuestionAnswering": "ltg/norbert3-large--modeling_norbert.NorbertForQuestionAnswering", "AutoModelForSequenceClassification": "ltg/norbert3-large--modeling_norbert.NorbertForSequenceClassification", "AutoModelForTokenClassification": "ltg/norbert3-large--modeling_norbert.NorbertForTokenClassification" }, "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3" }, "intermediate_size": 2730, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3 }, "layer_norm_eps": 1e-07, "max_position_embeddings": 512, "num_attention_heads": 16, "num_hidden_layers": 24, "output_all_encoded_layers": true, "position_bucket_size": 32, "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.41.2", "vocab_size": 50000 }