ї яЛNg$ЦСV≈ddlmZddlmZddlmZddlmZd└Z Gd└dі╚Zd S) И)зannotations╘зwraps)зPeftAdapterMixinИ)зTransformercС<┤≈t┴і╚┬fd└і╚}|S)zQWrapper to call the method on the auto_model with a check for PEFT compatibility.cС|∙≈|═і╚t|dj┴jі╚}||i|є▌S╘Nr)зcheck_peft_compatible_modelзgetattrз auto_modelз__name__)зselfзargsзkwargsзmethodзfuncs ─З\/var/www/html/ai-engine/env/lib/python3.11/site-packages/sentence_transformers/peft_mixin.pyзwrapperzpeft_wrapper..wrapper sBЬ─Юв(р(я*т*п*щ≤≤a°т+╗T╛]я;т;┬ь┬v░tп&≤vп&п&п&Сr)rrs` rзpeft_wrapperr s5Ь─У┬4│[└[П'П'П'П'Я└[П'П ─NrcСБ≈eZdZdZdd└Zdd└Zedd└і╚Zedd└і╚Zedd └і╚Z edd └і╚Z edd└і╚Zedd └і╚Zedd└і╚Z edd└і╚ZdS)raЎ Wrapper Mixin that adds the functionality to easily load and use adapters on the model. For more details about adapters check out the documentation of PEFT library: https://huggingface.co/docs/peft/index Currently supported PEFT methods follow those supported by transformers library, you can find more information on: https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin зreturnзboolcСx≈t|dtі╚ot|djtі╚Sr)з isinstancerrзPeftAdapterMixinTransformers╘rs rзhas_peft_compatible_modelz*PeftAdapterMixin.has_peft_compatible_model!s-─щ≤$≤q°'╔;я/т/пp╣J╦tюA╪wт?QуSoя4pт4pпprзNonecСL≈|═і╚stdі╚┌dS)Nz`PEFT methods are only supported for Sentence Transformer models that use the Transformer module.)r з ValueErrorrs rrz,PeftAdapterMixin.check_peft_compatible_model$s5─ьв-р-я/т/П щьrЯТП П П rcС≈dS)aь Load adapter weights from file or remote Hub folder." If you are not familiar with adapters and PEFT methods, we invite you to read more about them on PEFT official documentation: https://huggingface.co/docs/peft Requires peft as a backend to load the adapter weights and the underlying model to be compatible with PEFT. Args: *args: Positional arguments to pass to the underlying AutoModel `load_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.load_adapter **kwargs: Keyword arguments to pass to the underlying AutoModel `load_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.load_adapter N╘╘rrrs rзload_adapterzPeftAdapterMixin.load_adapter*s ─П ┬rcС≈dS)aЖ Adds a fresh new adapter to the current model for training purposes. If no adapter name is passed, a default name is assigned to the adapter to follow the convention of PEFT library (in PEFT we use "default" as the default adapter name). Requires peft as a backend to load the adapter weights and the underlying model to be compatible with PEFT. Args: *args: Positional arguments to pass to the underlying AutoModel `add_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.add_adapter **kwargs: Keyword arguments to pass to the underlying AutoModel `add_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.add_adapter Nr%r&s rзadd_adapterzPeftAdapterMixin.add_adapter<s ─П$ ┬rcС≈dS)aЕ Sets a specific adapter by forcing the model to use a that adapter and disable the other adapters. Args: *args: Positional arguments to pass to the underlying AutoModel `set_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.set_adapter **kwargs: Keyword arguments to pass to the underlying AutoModel `set_adapter` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.set_adapter Nr%r&s rзset_adapterzPeftAdapterMixin.set_adapterPs ─П ┬rcС≈dS)zx Disable all adapters that are attached to the model. This leads to inferring with the base model only. Nr%rs rзdisable_adaptersz!PeftAdapterMixin.disable_adapters_С ─П ┬rcС≈dS)zl Enable adapters that are attached to the model. The model will use `self.active_adapter()` Nr%rs rзenable_adaptersz PeftAdapterMixin.enable_adaptersfr.rЗ list[str]cС≈dS)a3 If you are not familiar with adapters and PEFT methods, we invite you to read more about them on the PEFT official documentation: https://huggingface.co/docs/peft Gets the current active adapters of the model. In case of multi-adapter inference (combining multiple adapters for inference) returns the list of all active adapters so that users can deal with them accordingly. For previous PEFT versions (that does not support multi-adapter inference), `module.active_adapter` will return a single string. Nr%rs rзactive_adaptersz PeftAdapterMixin.active_adaptersms ─П ┬rзstrcС≈dS)Nr%rs rзactive_adapterzPeftAdapterMixin.active_adapter{s─ь%(═SrзdictcС≈dS)a If you are not familiar with adapters and PEFT methods, we invite you to read more about them on the PEFT official documentation: https://huggingface.co/docs/peft Gets the adapter state dict that should only contain the weights tensors of the specified adapter_name adapter. If no adapter_name is passed, the active adapter is used. Args: *args: Positional arguments to pass to the underlying AutoModel `get_adapter_state_dict` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.get_adapter_state_dict **kwargs: Keyword arguments to pass to the underlying AutoModel `get_adapter_state_dict` function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/peft#transformers.integrations.PeftAdapterMixin.get_adapter_state_dict Nr%r&s rзget_adapter_state_dictz'PeftAdapterMixin.get_adapter_state_dict~s ─П" ┬rN)rr)rr!)rr1)rr4)rr7)rз __module__з__qualname__з__doc__r rrr'r)r+r-r0r3r6r9r%rrrrs@─────ПППqПqПqПqППППППППЯ└\ПП"ПППЯ└\ПП&ПППЯ└\ПППППЯ└\ПППППЯ└\ПППППЯ└\ППь(п(п(Я└\ь(ЮПППЯ└\ПППrrN) з __future__rз functoolsrзtransformers.integrations.peftrrзmodelsrrr%rrЗrAs≤Пь"п"п"п"п"п"ЮпппппЮ[п[п[п[п[п[ЮпппппП П П ПyПyПyПyПyЯyТyПyПyПyr