TiddlmZddlZddlmZmZddlmZeje 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 z ddlm}m}ddlm}|j } t| |s td|j|  ttr0|jvr tdxst|dt fd d |||d | y#t $r t dwxYw) 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-onnx/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 r)ORTModel ORTOptimizer)AutoOptimizationConfigzPlease install Optimum and ONNX Runtime to use this function. You can install them with pip: `pip install sentence-transformers[onnx]` or `pip install sentence-transformers[onnx-gpu]`z}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 h/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/sentence_transformers/backend/optimize.pyz-export_optimized_onnx_model..^s););L((I i * L  ,,Y7I%s+ &<&D&D Dn "8%8 Rg&<>QRT! s:"- 7   ?   s B%%B:)FFN)r"z2SentenceTransformer | SparseEncoder | CrossEncoderrz4OptimizationConfig | Literal['O1', 'O2', 'O3', 'O4']rr*rboolr r.rz str | NonereturnNone) __future__rloggingtypingrr#sentence_transformers.backend.utilsr getLogger__name__loggersentence_transformersrrr r$r r%rrrr:s")I   8 $VV H" T =TMTT T  T  T T    sAAA