tj-"dZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z dd lmZmZd d lmZd d l mZe jeZe rerdd lZddlmZddlmZGddeZd S)z3Abstract base class for all Transformers exporters.) annotations)ABCabstractmethod)MutableMapping) TYPE_CHECKING)version)logging)_is_package_availableis_torch_available)ExportConfigMixin)decompose_for_generationN)Cache)PreTrainedModelcjeZdZUdZgZded<iZded<iZded<dZdZ e ddZ ddZ dS) HfExporterz Abstract base class for all Transformers exporters. Subclass and implement [`~HfExporter.export`] to add a new export backend. z list[str]required_packageszdict[str, str] min_versionstested_versionsc.|dS)N)validate_environment)selfs Y/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/exporters/base.py__init__zHfExporter.__init__7s !!#####c Zgg}}jD]}t|d\}}|s||.j|}|\|dkrV|ddd} |ddd} | | kr||| | f|rHdfd |D} td tj d | g} j D]\}} t|d\}}|dksDtj |dddtj | kr| |d | d |d| r9ttj dd| |rSdd|D}ttj d|ddSdS)zYCheck `required_packages` are installed and warn on version drift from `tested_versions`.T)return_versionNzN/A+r rz, c3RK|]!}|jvr|dj|n|V"dS)z==N)r).0pkgrs r z2HfExporter.validate_environment..Ns]be@T9T9T355$.s3555Z]rzTo use z-, please install the following dependencies: z>=z (found )z requires newer versions of: c32K|]\}}}|d|d|VdS)z : installed z , tested N)r!r"gotwants rr#z2HfExporter.validate_environment..]s@ee^SRUW[3 H HC H H$ H Heeeeeeru~ is experimental and patches many backend internals; behaviour may differ from what was validated. Version drift detected — z-. If you hit issues, try the tested versions.)rr appendrgetsplitjoin ImportErrortype__name__ritemsrparseloggerwarning)rargskwargsmissingdriftr"exists installedtestedinstalled_base tested_basespecsoutdatedminimum_detailss` rrzHfExporter.validate_environment:s R) E EC 5c$ O O O FI s###)--c22F!i5&8&8!*a!8!8!;$ll32215 ![00LL#~{!CDDD  sIIipEqT (;qqjoqqrr r -3355 I ILC0TJJJLAyE!!W]9??33J3J13M%N%NQXQ^_fQgQg%g%g3 G G' G G9 G G GHHH  jd!4hhSWS\S\]eSfSfhhii i  iiee_deeeeeG NN::&??\c???       rmodelr sample_inputs)MutableMapping[str, torch.Tensor | Cache]configrcJtt|jd)u Export the model and return the backend-specific program object. Args: model ([`PreTrainedModel`]): The model to export. sample_inputs (`dict[str, torch.Tensor | Cache]`): **Forward** kwargs — what you'd pass to `model(**sample_inputs)`. These are used directly as the example inputs during tracing. For an autoregressive decode-step export, this means you need to include `past_key_values`, `cache_position`, etc. If you only have generation-style inputs, use [`~HfExporter.export_for_generation`] instead — it runs `model.generate` for you and exports each stage. config ([`~transformers.exporters.configs.ExportConfigMixin`]): Backend-specific configuration. Returns: Backend-specific export artifact. z does not implement `export`. Pick a concrete exporter (`DynamoExporter`, `OnnxExporter`, `ExecutorchExporter`), or override `export` in your subclass with a backend-specific tracing pipeline that consumes `config` and returns the runtime artifact.)NotImplementedErrorr.r/)rrBrCrEs rexportzHfExporter.exportds12"Dzz" 0 0 0   r0ExportConfigMixin | dict[str, ExportConfigMixin]returndict[str, object]c nt||}t|trTt|t|z }|r0t dt |dt |d|}nt||}i}|D]\}\} } || | ||||<+#t$rR} tt|j d|dt| j dt| d| d } ~ wwxYw|S) u Decompose a generative model and export each component independently. Thin wrapper around [`~exporters.utils.decompose_for_generation`] that calls [`~HfExporter.export`] on every returned `(submodel, forward_inputs)` pair. If you need the intermediate `(submodel, forward_inputs)` pairs (for verification, custom inputs, skipping a stage, …), call [`~exporters.utils.decompose_for_generation`] directly. Args: model ([`PreTrainedModel`]): The generative model to export. Must support `model.generate(**sample_inputs)`. sample_inputs (`dict[str, torch.Tensor | Cache]`): **Generate** kwargs — what you'd pass to `model.generate(**sample_inputs)` (typically `input_ids` + `attention_mask`, plus any modality inputs like `pixel_values` / `input_features` for multi-modal models). Per-stage forward kwargs are captured internally. config ([`~transformers.exporters.configs.ExportConfigMixin`] or `dict[str, ExportConfigMixin]`): Backend-specific configuration. Pass a single config to apply to every component, or a `dict` keyed by component name (e.g. `"image_encoder"`, `"language_model"`, `"lm_head"`, `"decode"`) to override per-component — all component names must be present in the dict. Returns: `dict[str, Any]`: `{component_name: backend_specific_artifact}` — same keys as [`~exporters.utils.decompose_for_generation`]. Values are whatever [`~HfExporter.export`] returns for the concrete backend (`ExportedProgram`, `ONNXProgram`, `ExecutorchProgramManager`). z4Per-component `config` dict is missing entries for: z$. Expected one entry per component: .)rEz.export failed on component 'z ' (submodel=z , input keys=z).N)r isinstancedictset ValueErrorsortedfromkeysr0rH Exception RuntimeErrorr.r/list) rrBrCrE componentsr6configsexportednamesubmodel subinputses rexport_for_generationz HfExporter.export_for_generationsD.e]CC fd # # 8*ooF 3G  O6RY??OO9? 9K9KOOOGGmmJ77G&(+5+;+;+=+=   'D'8Y !%XyQU!W!W   "Dzz*[[[[!%h!8[[GKI[[[  s4!C D2 A D--D2N)rBrrCrDrEr)rBrrCrDrErIrJrK) r/ __module__ __qualname____doc__r__annotations__rrrrrrHr^r&rrrr*s $&%%%%#%L%%%%&(O(((($$$(((T   ^ >666666rr)ra __future__rabcrrcollections.abcrtypingr packagingrutilsr utils.import_utilsr r rXrr get_loggerr/r2torch cache_utilsrmodeling_utilsrrr&rrrnsU:9""""""########****** JJJJJJJJ&&&&&&++++++  H % %55 ''''''444444PPPPPPPPPPr