bi$hddlmZddlmZmZddlmZmZddlm Z ddl m Z eGdde Z y) ) annotations) dataclassfield)OptionalUnion) PeftConfig)PeftTypeceZdZUdZedddiZded<edddiZded <eddd iZded <ed dd iZ ded<edddiZ ded<edddiZ ded<fdZ xZ S) IA3Configu This is the configuration class to store the configuration of a [`IA3Model`]. Args: 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/Conv1D 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. feedforward_modules (`Optional[Union[List[str], str]]`): The names of the modules to be treated as feedforward modules, as in the original paper. These modules will have (IA)³ vectors multiplied to the input, instead of the output. `feedforward_modules` must be a name or a subset of names present in `target_modules`. fan_in_fan_out (`bool`): Set this to True if the layer to replace stores weight like (fan_in, fan_out). For example, gpt-2 uses `Conv1D` which stores weights like (fan_in, fan_out) and hence this should be set to `True`. modules_to_save (`Optional[List[str]]`): List of modules apart from (IA)³ layers to be set as trainable and saved in the final checkpoint. init_ia3_weights (`bool`): Whether to initialize the vectors in the (IA)³ layers, defaults to `True`. Setting this to `False` is discouraged. NhelpuList of module names or regex expression of the module names to replace with (IA)³.For example, ['q', 'v'] or '.*decoder.*(SelfAttention|EncDecAttention).*(q|v)$'.This can also be a wildcard 'all-linear' which matches all linear/Conv1D layers except the output layer.If 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.)defaultmetadatazOptional[Union[list[str], str]]target_modulesuTList of module names or regex expression of the module names to exclude from (IA)³.exclude_moduleszmList of module names or a regex expression of module names which are feedforwardFor example, ['output.dense']feedforward_modulesFzMSet this to True if the layer to replace stores weight like (fan_in, fan_out)boolfan_in_fan_outaList of modules apart from (IA)^3 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_saveTz7Whether to initialize the vectors in the (IA)^3 layers.init_ia3_weightsct|tj|_t |j trt|j n |j |_t |jtrt|jn |j|_ t |jtrt|jn |j|_ t |jtrLt |j tr1|jj|j s tdyyy)Nz<`feedforward_modules` should be a subset of `target_modules`) super __post_init__r IA3 peft_type isinstancerlistsetrrissubset ValueError)self __class__s Q/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/peft/tuners/ia3/config.pyrzIA3Config.__post_init__`s !(243F3F(MC## $SWSfSf *4D4H4H$)OC$$ %UYUiUi .88P8PRV-WC(( )]a]u]u  d.. 4DDWDWY\9]++44T5H5HI !_``J:^ 4)__name__ __module__ __qualname____doc__rr__annotations__rrrrrr __classcell__)r!s@r"r r s<7< v  7N3 8=pq8O4r0s7#("" Wa Wa War#