{ "architectures": [ "XLMRobertaForTokenClassification" ], "attention_probs_dropout_prob": 0.1, "finetuning_task": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "B-LOC", "1": "B-MISC", "2": "B-ORG", "3": "I-LOC", "4": "I-MISC", "5": "I-ORG", "6": "I-PER", "7": "O" }, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "label2id": { "B-LOC": 0, "B-MISC": 1, "B-ORG": 2, "I-LOC": 3, "I-MISC": 4, "I-ORG": 5, "I-PER": 6, "O": 7 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "num_attention_heads": 16, "num_hidden_layers": 24, "num_labels": 8, "output_attentions": false, "output_hidden_states": false, "output_past": true, "pruned_heads": {}, "torchscript": false, "type_vocab_size": 1, "use_bfloat16": false, "vocab_size": 250002 }