
    h                     r   S SK JrJr  S SKJr  S SKJr  SSKJrJ	r	J
r
   \" S5      r/ SQ/ S	QS
// SQ/ SQ/ SQ/ SQS.r \
" 5       (       d  \" 5       e \S   R                  / SQ5        \S   R                  SS/5        \(       a  SS	KJrJrJrJrJrJrJrJrJrJrJrJr  SSKJr  SSKJrJrJ r J!r!J"r"J#r#J$r$  SSK%J&r&J'r'J(r(J)r)J*r*  SSK+J,r,J-r-J.r.J/r/J0r0J1r1J2r2J3r3J4r4J5r5J6r6J7r7J8r8J9r9J:r:J;r;J<r<J=r=J>r>J?r?J@r@JArAJBrBJCrCJDrDJErEJFrFJGrGJHrHJIrIJJrJJKrKJLrLJMrMJNrNJOrOJPrPJQrQJRrRJSrSJTrTJUrUJVrVJWrWJXrXJYrYJZrZ  SSK[J\r\J]r]J^r^J_r_  SSK`JaraJbrbJcrc   \
" 5       (       d  \" 5       e SSKJdrdJereJfrfJgrg  SSK+JhrhJiri  gS SKjrj\	" \k\l" 5       S   \\mS\0S9\jR                  \k'   g! \ a    Sr GNtf = f! \ a     GN)f = f! \ a     gf = f)    )PackageNotFoundErrorversion)Path)TYPE_CHECKING   )OptionalDependencyNotAvailable_LazyModuleis_diffusers_availabletrlunknown)DatasetMixtureConfigScriptArguments	TrlParserget_datasetinit_zero_verbose)apply_chat_templateextract_promptis_conversationalis_conversational_from_valuemaybe_apply_chat_templatemaybe_convert_to_chatmlmaybe_extract_promptmaybe_unpair_preference_datasetpack_datasetprepare_multimodal_messagestruncate_datasetunpair_preference_datasetBestOfNSampler)SUPPORTED_ARCHITECTURES!AutoModelForCausalLMWithValueHead"AutoModelForSeq2SeqLMWithValueHeadPreTrainedModelWrapperclone_chat_templatecreate_reference_modelsetup_chat_format)/AlignPropConfigAlignPropTrainerAllTrueJudgeBaseBinaryJudge	BaseJudgeBasePairwiseJudgeBaseRankJudge	BCOConfig
BCOTrainer	CPOConfig
CPOTrainer	DPOConfig
DPOTrainerFDivergenceConstantsFDivergenceType	GKDConfig
GKDTrainer
GRPOConfigGRPOTrainerHfPairwiseJudgeIterativeSFTConfigIterativeSFTTrainer	KTOConfig
KTOTrainerLogCompletionsCallbackModelConfigNashMDConfigNashMDTrainerOnlineDPOConfigOnlineDPOTrainerOpenAIPairwiseJudge
ORPOConfigORPOTrainerPairRMJudge	PPOConfig
PPOTrainer	PRMConfig
PRMTrainerRewardConfigRewardTrainer
RLOOConfigRLOOTrainer	SFTConfig
SFTTrainerWinRateCallback	XPOConfig
XPOTrainer)BEMACallbackMergeModelCallbackRichProgressCallbackSyncRefModelCallback)get_kbit_device_mapget_peft_configget_quantization_config)scripts
data_utilsextrasmodelstrainerztrainer.callbacksztrainer.utilsr_   )DDPOPipelineOutputDDPOSchedulerOutputDDPOStableDiffusionPipeline"DefaultDDPOStableDiffusionPipeliner`   
DDPOConfigDDPOTrainer)r   )re   rf   N__file____version__)module_specextra_objects)oimportlib.metadatar   r   pathlibr   typingr   import_utilsr   r	   r
   rh   _import_structureextendr]   r   r   r   r   r   r   r   r   r   r   r   r   r^   r   r_   r   r    r!   r"   r#   r$   r%   r\   r   r   r   r   r   r`   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   rB   rC   rD   rE   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   rQ   rR   rS   rT   trainer.callbacksrU   rV   rW   rX   trainer.utilsrY   rZ   r[   ra   rb   rc   rd   re   rf   sys__name__globals__spec__modules     F/home/james-whalen/.local/lib/python3.13/site-packages/trl/__init__.py<module>r{      s   =    ] ]%.K
 l   0b pZYM ^G!##,.. $
 h&&	
 i ''}(EF    '   ji0 0 0 0 0 0 0 0 0 0 0 0 0b po\\5%''022 (
	
 	
 	54 '	*$k2CKKC  Kj & 		| * s5   F  F  F- FF F*)F*-F65F6