bilddlmZddlmZmZddlmZmZmZddl m Z ddl m Z eGdde Z y) ) annotations) dataclassfield)LiteralOptionalUnion) PeftConfig)PeftTypec~eZdZUdZeddddZded<ed d d iZd ed <eddddZded<eddddZ ded<edd diZ ded<edd diZ ded<edd diZ ded <edd d!iZ d"ed#<ed$d d%iZd&ed'<edd d(iZd)ed*<fd+ZxZS), MissConfiga This is the configuration class to store the configuration of a [`MiSSModel`]. Args: r (`int`): The rank of MiSS across different layers. It is best to set 'r' to an even number; otherwise, the default initialization method will not work. The rank of MiSS corresponds to a low-rank decomposition along the in_features dimension. miss_dropout (`float`): The dropout probability for MiSS layers. mini_r (`int`): The rank of MiSS corresponds to a low-rank decomposition along the out_features dimension. When you set `init_weights=mini`, you need to set `mini_r`. Please make sure that `out_features` is divisible by `mini_r`. target_modules (`Optional[Union[List[str], str]]`): The names of the modules to apply the adapter to. If this is specified, only the modules with the specified names will be replaced. When passing a string, a regex match will be performed. When passing a list of strings, either an exact match will be performed or it is checked if the name of the module ends with any of the passed strings. If this is specified as 'all-linear', then all linear modules are chosen, excluding the output layer. If this is not specified, modules will be chosen according to the model architecture. If the architecture is not known, an error will be raised -- in this case, you should specify the target modules manually. exclude_modules (`Optional[Union[List[str], str]]`): The names of the modules to not apply the adapter. When passing a string, a regex match will be performed. When passing a list of strings, either an exact match will be performed or it is checked if the name of the module ends with any of the passed strings. init_weights (bool | Literal["bat", "mini"]): Different initializations correspond to different MiSS variants. By default(balance), the most efficient and general method in MiSS will be used. 'bat': In this mode, you can enable nonlinear updates across different shards. 'mini': In this mode, you can set a smaller rank to use fewer trainable parameters, but it is recommended to keep `out_features % mini_r == 0`. layers_to_transform (`Union[List[int], int]`): The layer indices to transform. If a list of ints is passed, it will apply the adapter to the layer indices that are specified in this list. If a single integer is passed, it will apply the transformations on the layer at this index. layers_pattern (`str`): The layer pattern name, used only if `layers_to_transform` is different from `None`. modules_to_save (`List[str]`): List of modules apart from adapter layers to be set as trainable and saved in the final checkpoint. @zYThe rank of MiSS corresponds to a low-rank decomposition along the in_features dimension.zdIt is best to set 'r' to an even number; otherwise, the default initialization method will not work.)helpnote)defaultmetadataintrgrz MiSS dropoutfloat miss_dropoutzZThe rank of MiSS corresponds to a low-rank decomposition along the out_features dimension.zIt is recommended that mini_r be divisible by out_features. When mini_r == out_features, the mini method is equivalent to the default efficient MiSS.mini_rNzRList of module names or regex expression of the module names to replace with MiSS.zPFor example, ['q', 'v'] or '.*decoder.*(SelfAttention|EncDecAttention).*(q|v)$' )rexamplezOptional[Union[list[str], str]]target_moduleszRList of module names or regex expression of the module names to exclude from MiSS.exclude_modulesTzTrue -> MiSS balance; `bat` -> Bat; `mini` -> smaller rank and efficiencyWhether to initialize the weights of the MiSS layers with their default initialization. Don't change this setting, except if you know exactly what you're doing.zbool | Literal['bat', 'mini'] init_weightszThe layer indexes to transform, is this argument is specified, PEFT will transform only the layers indexes that are specified inside this list. If a single integer is passed, PEFT will transform only the layer at this index.zOptional[Union[list[int], int]]layers_to_transformzThe layer pattern name, used only if `layers_to_transform` is different to None and if the layer pattern is not in the common layers pattern.z Optional[str]layers_patternnonez7Bias type for MiSS. Can be 'none', 'all' or 'MiSS_only'strbiasaList of modules apart from MiSS layers to be set as trainable and saved in the final checkpoint. For example, in Sequence Classification or Token Classification tasks, the final layer `classifier/score` are randomly initialized and as such need to be trainable and saved.zOptional[list[str]]modules_to_savect|tj|_t |j trt|j n |j |_t |jtrt|jn |j|_ t |j tr|j tdt |j tr|j tdyy)NzD`layers_to_transform` cannot be used when `target_modules` is a str.z?`layers_pattern` cannot be used when `target_modules` is a str.)super __post_init__r MISS peft_type isinstancerlistsetrrr ValueErrorr)self __class__s R/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/peft/tuners/miss/config.pyr$zMissConfig.__post_init__}s !(243F3F(MC## $SWSfSf *4D4H4H$)OC$$ %UYUiUi  d))3 /D4L4L4Xcd d d))3 /D4G4G4S^_ _5T /)__name__ __module__ __qualname____doc__rr__annotations__rrrrrrrr r!r$ __classcell__)r,s@r-r r s^'Roz As v~6NOL%Opl FC7<hi 7N38=no8O438 N  3L/ r;s:#(++" s`s` s`r.