{ "_name_or_path": "intfloat/multilingual-e5-small", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 384, "id2label": { "0": "1", "1": "2", "2": "3", "3": "4", "4": "5", "5": "6", "6": "7", "7": "8", "8": "9", "9": "10" }, "initializer_range": 0.02, "intermediate_size": 1536, "label2id": { "1": 0, "10": 9, "2": 1, "3": 2, "4": 3, "5": 4, "6": 5, "7": 6, "8": 7, "9": 8 }, "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", "problem_type": "single_label_classification", "tokenizer_class": "XLMRobertaTokenizer", "torch_dtype": "float32", "transformers_version": "4.44.2", "type_vocab_size": 2, "use_cache": false, "vocab_size": 250037 }