{ "add_cross_attention": false, "architectures": [ "XLMRobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "dtype": "float32", "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 384, "id2label": { "0": "NO_RELATION", "1": "semantically_similar_to", "2": "shares_purpose_with", "3": "invalidates_with", "4": "configured_by", "5": "depends_on", "6": "contradicts", "7": "replaced_by" }, "initializer_range": 0.02, "intermediate_size": 1536, "is_decoder": false, "label2id": { "NO_RELATION": 0, "configured_by": 4, "contradicts": 6, "depends_on": 5, "invalidates_with": 3, "replaced_by": 7, "semantically_similar_to": 1, "shares_purpose_with": 2 }, "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, "position_embedding_type": "absolute", "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity", "tie_word_embeddings": true, "transformers_version": "5.1.0", "type_vocab_size": 1, "use_cache": true, "vocab_size": 250006 }