| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "XLMRobertaForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": 0.15, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "Norwegian", | |
| "1": "Swedish", | |
| "2": "Danish", | |
| "3": "Non-Scandinavian" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "label2id": { | |
| "Danish": 2, | |
| "Non-Scandinavian": 3, | |
| "Norwegian": 0, | |
| "Swedish": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "xlm-roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "problem_type": "multi_label_classification", | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "type_vocab_size": 1, | |
| "use_cache": false, | |
| "vocab_size": 50005 | |
| } | |