rhwddlmZddlZddlmZmZddlmZeje Z erddl m Z m Z mZ ddlmZ d d dZy#e$rYwxYw) ) annotationsN) TYPE_CHECKINGLiteral)save_or_push_to_hub_model CrossEncoderSentenceTransformer SparseEncoder)OptimizationConfigc ddlm}m}m} ddlm} m} ddlm} t||xr7t|xr*t|ddxrt|dj| } t||xr7t|xr*t|ddxrt|dj| } t||xrt|j| }| s|s | s td| s| r|dj}n |j}| j!|tt"r0| j$vr tdxst'| d t)fd d |||d | y #t$r tdwxYw)a Export an optimized ONNX model from a SentenceTransformer, SparseEncoder, or CrossEncoder model. The O1-O4 optimization levels are defined by Optimum and are documented here: https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/optimization The optimization levels are: - O1: basic general optimizations. - O2: basic and extended general optimizations, transformers-specific fusions. - O3: same as O2 with GELU approximation. - O4: same as O3 with mixed precision (fp16, GPU-only) See the following pages for more information & benchmarks: - `Sentence Transformer > Usage > Speeding up Inference `_ - `Cross Encoder > Usage > Speeding up Inference `_ Args: model (SentenceTransformer | SparseEncoder | CrossEncoder): The SentenceTransformer, SparseEncoder, or CrossEncoder model to be optimized. Must be loaded with `backend="onnx"`. optimization_config (OptimizationConfig | Literal["O1", "O2", "O3", "O4"]): The optimization configuration or level. model_name_or_path (str): The path or Hugging Face Hub repository name where the optimized model will be saved. push_to_hub (bool, optional): Whether to push the optimized model to the Hugging Face Hub. Defaults to False. create_pr (bool, optional): Whether to create a pull request when pushing to the Hugging Face Hub. Defaults to False. file_suffix (str | None, optional): The suffix to add to the optimized model file name. Defaults to None. Raises: ImportError: If the required packages `optimum` and `onnxruntime` are not installed. ValueError: If the provided model is not a valid SentenceTransformer, SparseEncoder, or CrossEncoder model loaded with `backend="onnx"`. ValueError: If the provided optimization_config is not valid. Returns: None rr)ORTModel ORTOptimizer)AutoOptimizationConfigzPlease install Optimum and ONNX Runtime to use this function. You can install them with pip: `pip install optimum[onnxruntime]` or `pip install optimum[onnxruntime-gpu]` auto_modelz}The model must be a Transformer-based SentenceTransformer, SparseEncoder, or CrossEncoder model loaded with `backend="onnx"`.z\optimization_config must be an OptimizationConfig instance or one of 'O1', 'O2', 'O3', 'O4'.N optimizedc,j|S)N) file_suffix)optimize)save_dirroptimization_config optimizers y/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/sentence_transformers/backend/optimize.pyz-export_optimized_onnx_model..os););L 5-. 6 J 6 E!Hl + 6 uQx**H 5  5-( 6 J 6 E!Hl + 6 uQx**H 5  ! 5[*U[[RZ:[O / L  /#Ah11 #kk ,,Y7I%s+ &<&D&D Dn "8%8 Rg&<>QRT! s:"- W   8   s E++F)FFN)r$z2SentenceTransformer | SparseEncoder | CrossEncoderrz4OptimizationConfig | Literal['O1', 'O2', 'O3', 'O4']r r.r!boolr"r5rz str | NonereturnNone) __future__rloggingtypingrr#sentence_transformers.backend.utilsr getLogger__name__loggerr%rr r r'r r(rrrr@s")I   8 $VV H" e =eMee e  e  e e    sAAA