| { |
| "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384", |
| "architectures": [ |
| "BertForTokenClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "finetuning_task": "all_original", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 384, |
| "id2label": { |
| "0": "0", |
| "1": "B-CITATION", |
| "2": "I-CITATION", |
| "3": "B-LAW", |
| "4": "I-LAW" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 1536, |
| "label2id": { |
| "LABEL_0": "O", |
| "LABEL_1": "B-CITATION", |
| "LABEL_2": "I-CITATION", |
| "LABEL_3": "B-LAW", |
| "LABEL_4": "I-LAW" |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "tokenizer_class": "XLMRobertaTokenizer", |
| "torch_dtype": "float16", |
| "transformers_version": "4.28.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 250037 |
| } |
|
|
