Ch[SSKJr SSKrSSKrSSKJr SSKJr SSKJ r J r J r \R"\ 5rSSjrSSjrg) ) annotationsN)Path)PretrainedConfig)_save_pretrained_wrapperbackend_should_exportbackend_warn_to_savec 8SSKnSSKJnJnJnJn UUUS.n X);a0SR U R55n [SUSU 35eXn URS UR5S5US '[U5n U R5n S nS n[XX5X5unnU(aURS S5 U R "U4UUS .UD6n[#UR$SS9UlU(a ['X U5 U$![a [S5ef=f)a Load and perhaps export an ONNX model using the Optimum library. Args: model_name_or_path (str): The model name on Hugging Face (e.g. 'naver/splade-cocondenser-ensembledistil') or the path to a local model directory. config (PretrainedConfig): The model configuration. task_name (str): The task name for the model (e.g. 'feature-extraction', 'fill-mask', 'sequence-classification'). model_kwargs (dict): Additional keyword arguments for the model loading. rN)ONNX_WEIGHTS_NAMEORTModelForFeatureExtractionORTModelForMaskedLM!ORTModelForSequenceClassificationzfeature-extractionz fill-maskzsequence-classification, Unsupported task: . Supported tasks: zUsing the ONNX backend requires installing Optimum and ONNX Runtime. You can install them with pip: `pip install optimum[onnxruntime]` or `pip install optimum[onnxruntime-gpu]`providerONNXz*.onnx file_nameconfigexportonnx subfolder) onnxruntimeoptimum.onnxruntimer r r r joinkeys ValueErrorModuleNotFoundError Exceptionpopget_available_providersrexistsrfrom_pretrainedr_save_pretrainedr)model_name_or_pathr task_name model_kwargsortr r r r task_to_model_mappingsupported_tasks model_cls load_pathis_local backend_nametarget_file_globrmodels Z/var/www/html/shao/venv/lib/python3.13/site-packages/sentence_transformers/backend/load.pyload_onnx_modelr4s` !  #?,'H!   1"ii(=(B(B(DEO1)NFL d+  % %     E6e6L6LX^_E/<H LQ   8   s ADDc SSKJnJnJnJn UUUS.nX(;a0SR UR 55n [SUSU 35eXn [U5n U R5n Sn S n[XX4X5upU(aURS S 5 S U;aqUS n[U[5(dV[U5R5(d [S 5e[!USS9n["R$"U5US 'S S S 5 OO0US 'U R&"U4UUS.UD6n[)UR*SS9UlU(a [-X U 5 U$![a [S5ef=f!,(df  Nk=f)a Load and perhaps export an OpenVINO model using the Optimum library. Args: model_name_or_path (str): The model name on Hugging Face (e.g. 'naver/splade-cocondenser-ensembledistil') or the path to a local model directory. config (PretrainedConfig): The model configuration. task_name (str): The task name for the model (e.g. 'feature-extraction', 'fill-mask', 'sequence-classification'). model_kwargs (dict): Additional keyword arguments for the model loading. r)OV_XML_FILE_NAMEOVModelForFeatureExtractionOVModelForMaskedLM OVModelForSequenceClassificationrrrrzUsing the OpenVINO backend requires installing Optimum and OpenVINO. You can install them with pip: `pip install optimum[openvino]`OpenVINOz openvino*.xmlrN ov_configzXov_config should be a dictionary or a path to a .json file containing an OpenVINO configzutf-8)encodingropenvinor)optimum.intel.openvinor6r7r8r9rrrr r!rr$rr" isinstancedictopenjsonloadr%rr&r)r'rr(r)r6r7r8r9r+r,r-r.r/r0r1rr;fr2s r3load_openvino_modelrEZs   #>+'G!   1"ii(=(B(B(DEO1)rQs7" =uu   8 $IXQrP