
    bim              	          d Z ddlmZ ddlmZmZmZ g dg dddgd	gg d
g dg dg ddZ	  e       s e       	 ed   j                  g d       ed   j                  ddg       erddl	m
Z
mZmZmZmZmZmZmZmZmZmZ ddlmZmZ ddlmZ dd
lmZmZmZmZmZm Z m!Z! ddl"m#Z#m$Z$m%Z% ddl&m'Z'm(Z(m)Z)m*Z*m+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:m;Z;m<Z<m=Z=m>Z>m?Z?m@Z@mAZAmBZBmCZCmDZDmEZEmFZFmGZGmHZHmIZImJZJmKZKmLZLmMZMmNZNmOZOmPZPmQZQmRZRmSZSmTZTmUZUmVZVmWZW ddlXmYZYmZZZ ddl[m\Z\m]Z]m^Z^ 	  e       s e       	 ddlm_Z_m`Z`maZambZb ddl&mcZcmdZd yddleZe eef eg       d   eehde i      eej                  ef<   y# e$ r Y w xY w# e$ r Y yw xY w)z0.19.1    )TYPE_CHECKING   )OptionalDependencyNotAvailable_LazyModuleis_diffusers_available)init_zero_verboseScriptArguments	TrlParser)apply_chat_templateextract_promptis_conversationalmaybe_apply_chat_templatemaybe_convert_to_chatmlmaybe_extract_promptmaybe_unpair_preference_datasetpack_datasetpack_examplestruncate_datasetunpair_preference_datasetTextEnvironmentTextHistoryBestOfNSampler)SUPPORTED_ARCHITECTURES!AutoModelForCausalLMWithValueHead"AutoModelForSeq2SeqLMWithValueHeadPreTrainedModelWrapperclone_chat_templatecreate_reference_modelsetup_chat_format)1AlignPropConfigAlignPropTrainerAllTrueJudgeBaseBinaryJudge	BaseJudgeBasePairwiseJudgeBaseRankJudge	BCOConfig
BCOTrainer	CPOConfig
CPOTrainerDataCollatorForCompletionOnlyLM	DPOConfig
DPOTrainerFDivergenceConstantsFDivergenceType	GKDConfig
GKDTrainer
GRPOConfigGRPOTrainerHfPairwiseJudgeIterativeSFTConfigIterativeSFTTrainer	KTOConfig
KTOTrainerLogCompletionsCallbackMergeModelCallbackModelConfigNashMDConfigNashMDTrainerOnlineDPOConfigOnlineDPOTrainerOpenAIPairwiseJudge
ORPOConfigORPOTrainerPairRMJudge	PPOConfig
PPOTrainer	PRMConfig
PRMTrainerRewardConfigRewardTrainer
RLOOConfigRLOOTrainer	SFTConfig
SFTTrainerWinRateCallback	XPOConfig
XPOTrainer)r:   RichProgressCallbackSyncRefModelCallback)get_kbit_device_mapget_peft_configget_quantization_config)scripts
data_utilsenvironmentextrasmodelstrainerztrainer.callbacksztrainer.utilsrZ   )DDPOPipelineOutputDDPOSchedulerOutputDDPOStableDiffusionPipeline"DefaultDDPOStableDiffusionPipeliner[   
DDPOConfigDDPOTrainer)r   r   )r   )r	   r
   r   )rQ   rR   )r`   ra   N__file____version__)module_specextra_objects)jrc   typingr   import_utilsr   r   r   _import_structureextendrW   r   r   r   r   r   r   r   r   r   r   r   rX   r   r   rY   r   rZ   r   r   r   r   r   r   r   rV   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   trainer.callbacksrQ   rR   trainer.utilsrS   rT   rU   r\   r]   r^   r_   r`   ra   sys__name__globals__spec__modules     G/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/trl/__init__.py<module>rt      s      ] ] E &}5 2f `Z]O bG!#,.. $
 h&&	
 i ''}(EF    :&   GF2 2 2 2 2 2 2 2 2 2 2 2 2f N\\5%'022 (
	
 	
 	54 '	*$k2CKK] & 		@ * s#   E5 (F 5E>=E>F	F	