{ "_name_or_path": "Alibaba-NLP/gte-multilingual-base", "architectures": [ "NewModel" ], "attention_probs_dropout_prob": 0.0, "auto_map": { "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig", "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel", "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM", "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice", "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering", "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification", "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification" }, "classifier_dropout": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "layer_norm_type": "layer_norm", "logn_attention_clip1": false, "logn_attention_scale": false, "max_position_embeddings": 8192, "model_type": "new", "num_attention_heads": 12, "num_hidden_layers": 12, "pack_qkv": true, "pad_token_id": 1, "position_embedding_type": "rope", "rope_scaling": { "factor": 8.0, "type": "ntk" }, "rope_theta": 20000, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "type_vocab_size": 1, "unpad_inputs": false, "use_memory_efficient_attention": false, "vocab_size": 46528 }