^j(ddlmZddlmZddlmZddlmZmZddl m Z eje Z ed eGd d eZed eGd d eZd d gZy))strict)PreTrainedConfig)RopeParameters)auto_docstringlogging) AutoConfigz sesame/csm-1b) checkpointceZdZUdZdZdZdgZddiZdZdZ e d ze d <d Z e e d <d Z e e d<dZe e d<dZe e d<dZe e d<dZe e d<dZe d ze d<dZee d<dZe e d<dZee d<dZee d<d Zee d!<d Ze d ze d"<d Ze d ze d#<d Ze ee zd ze d$<d Ze e!zd ze d%<d&Z"ee d'<d(Z#ee zd ze d)<d&Z$ee d*<d Z%e d ze d+<fd,Z&xZ'S)-CsmDepthDecoderConfiga backbone_hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden representations of the backbone model used with this depth decoder. Example: ```python >>> from transformers import CsmDepthDecoder, CsmDepthDecoderConfig >>> # Initializing a CsmDepthDecoder >>> configuration = CsmDepthDecoderConfig() >>> model = CsmDepthDecoderModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```csm_depth_decoder_modeldepth_decoder_configpast_key_values codebook_size vocab_sizeA N num_codebooksbackbone_hidden_sizei hidden_size intermediate_sizenum_hidden_layersnum_attention_headsr num_key_value_headssilu hidden_act!max_position_embeddings{Gz?initializer_rangeh㈵> rms_norm_epsT use_cache pad_token_id bos_token_id eos_token_idrope_parametersFattention_biasattention_dropoutmlp_biashead_dimc |jddr td|j|j|_|j |jn|j |jz|_t |di|y)Ntie_word_embeddingsFzE`tie_word_embeddings=True` is not supported for CsmDepthDecoderConfig)pop ValueErrorr rr2rsuper __post_init__selfkwargs __class__s t/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/csm/configuration_csm.pyr9z#CsmDepthDecoderConfig.__post_init__Msr ::+U 3de e  # # +'+'?'?D $)-)B HXHX\`\t\tHt  '')(__name__ __module__ __qualname____doc__ model_typebase_config_keykeys_to_ignore_at_inference attribute_map default_thetarint__annotations__rrrrrrr r"strr$r&floatr(r)boolr*r+r,listr-rdictr.r0r1r2r9 __classcell__r=s@r>r r sH "+J,O#4"5MM "M3:" $#$JK!s!s  &'t'J#%S%#u#L%It#L#*##L#*#+/L#S /D(/48O^d*T18 ND ,/us{T)/HdHcDj((r?r cfeZdZUdZdZdZdgZdZee dZ ddiZ d Z e d zed <d Ze ed<d Ze ed<dZe ed<dZe ed<dZe ed<d Ze ed<dZe d zed<dZeed<dZe ed<dZeed<dZeed<dZeed <d!Ze d zed"<d#Ze d zed$<d%Z e e!e zd zed&<d'Z"e d zed(<d Z#e e!e zd zed)<d!Z$e d zed*<d+Z%e e!e zd zed,<d Z&e'e(zd zed-<d.Z)eed/<d0Z*ee zd zed1<d.Z+eed2<d Z,e d zed3<dZ-ed zed4<d Z.e(e/zd zed5<d Z0e(e/zd zed6<fd7Z1xZ2S)8 CsmConfiga codebook_pad_token_id (`int`, *optional*, defaults to 2050): Padding token id for codebook tokens. codebook_eos_token_id (`int`, *optional*, defaults to 0): End of stream token id for codebook tokens. audio_token_id (`int`, *optional*, defaults to 128002): Audio token id in the text input. audio_eos_token_id (`int`, *optional*, defaults to 128003): End of stream token id for audio in the text input. tie_codebooks_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie the codebook tokens embeddings of the backbone model to the codebook tokens embeddings of the depth decoder. depth_decoder_config (`CsmDepthDecoderConfig`, *optional*): Configuration for the depth decoder. codec_config (`PreTrainedConfig`, *optional*): Configuration for the codec. ```python >>> from transformers import CsmForConditionalGeneration, CsmConfig >>> # Initializing a CsmConfig >>> configuration = CsmConfig() >>> # Initializing a model >>> model = CsmForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` csm csm_configrr) codec_configrrrrNrritext_vocab_sizerrrrrrrr r!r"r$r%r&r'r(Tr)ir*icodebook_pad_token_idrcodebook_eos_token_idir+r,audio_token_idiaudio_eos_token_idr-Fr.r/r0r1r2tie_codebooks_embeddingsrrVc |jddr td|j%t|_tj dn4t |jtrtdi|j|_|j0tjd|_tj dn>t |jtr$tjdi|j|_|j|j|_ |j |jn|j|jz|_ d|_t!|Ddi|y)Nr4Fz9`tie_word_embeddings=True` is not supported for CsmConfigzAdepth_decoder_config is None, using default depth decoder config.mimiz9codec_config is None, using default audio encoder config.r5)r6r7rr loggerinfo isinstancerOrVr for_modelr rr2rr4r8r9r:s r>r9zCsmConfig.__post_init__s ::+U 3XY Y  $ $ ,(=(?D % KK[ \ 114 8(=(Z@Y@Y(ZD %    $ * 4 4V rSrSXs<J"O#4"5M" 5K M!#M3:"J!OS!K!s!s!!&'t'J#'S'#u#L%It%L#*%(,3:,453c?T15%L#*%+/L#S /D(/!'NC$J'17d3i$.748O^d*T18 ND ,/us{T)/HdHcDj,0dTk0;?$!11D8?37L$))D07((r?rSN)huggingface_hub.dataclassesrconfiguration_utilsrmodeling_rope_utilsrutilsrrauto.configuration_autor get_loggerr@r`r rS__all__r5r?r>rls /31,0   H %?+8(,8(,8(v?+]( ](,](B r?