U dit@sdZddlZddlZddlZddlZddlZddlZddlZddlZddl Z ddl Z ddl Z ddl Z ddl mZddlmZddl mZmZmZmZmZddlmZddlmZmZmZmZmZmZee Z!e "Z#d d Z$ee%ej&fdd d d Z'ee%ej&fee%dddZ(ee%ej&fee%dddZ)ee%ej&fee%dddZ*ee%ej&fee%dddZ+dde%ee%ej&fe,e j-dddZ.d+ee%ej&fe%eee%ej&fe,ee,eee%e%feee,e%fee%e,ee%ee%e%d ddZ/d,e%ee%ej&feee%ej&fe,ee,eee%e%feee,e%fee%e,ee%ee%e j-d d!d"Z0d-eee%ej&feeee%d#d$d%Z1d&d'Z2d(Z3d)d*Z4dS).z3Utilities to dynamically load objects from the Hub.N)Path) ModuleType)AnyDictListOptionalUnion)try_to_load_from_cache)HF_MODULES_CACHE TRANSFORMERS_DYNAMIC_MODULE_NAME cached_fileextract_commit_hashis_offline_modeloggingcCsPttjkrdStjttjtddttd}|sL|t dS)z_ Creates the cache directory for modules with an init, and adds it to the Python path. NTexist_ok __init__.py) r syspathappendosmakedirsrexiststouch importlibinvalidate_caches) init_pathrE/tmp/pip-unpacked-wheel-bm_b0l5e/transformers/dynamic_module_utils.pyinit_hf_modules1s   r )namereturncCs\ttt|}|js*t|jtj|dd|d}|sX| t dS)z Creates a dynamic module in the cache directory for modules. Args: name (`str` or `os.PathLike`): The name of the dynamic module to create. TrrN) r rr resolveparentrcreate_dynamic_modulerrrrr)r!Zdynamic_module_pathrrrrr%As  r%) module_filer"c CsVt|ddd}|}W5QRXtjd|tjd}|tjd|tjd7}tt|S)z Get the list of modules that are relatively imported in a module file. Args: module_file (`str` or `os.PathLike`): The module file to inspect. Returns: `List[str]`: The list of relative imports in the module. rutf-8encodingz^\s*import\s+\.(\S+)\s*$flagsz^\s*from\s+\.(\S+)\s+import)openreadrefindall MULTILINElistset)r&fcontentZrelative_importsrrrget_relative_importsWs r6csd}|g}g|sg}|D]}|t|qt|jfdd|D}fdd|D}dd|D}t|dk}|qS)a Get the list of all files that are needed for a given module. Note that this function recurses through the relative imports (if a imports b and b imports c, it will return module files for b and c). Args: module_file (`str` or `os.PathLike`): The module file to inspect. Returns: `List[str]`: The list of all relative imports a given module needs (recursively), which will give us the list of module files a given module needs. Fcsg|]}t|qSr)str).0m) module_pathrr sz-get_relative_import_files..csg|]}|kr|qSrrr8r4)all_relative_importsrrr;scSsg|]}|dqS).pyrr<rrrr;sr)extendr6rr$len)r&Z no_changeZfiles_to_checkZ new_importsr4Znew_import_filesr)r=r:rget_relative_import_filesls    rA)filenamer"c Cst|ddd}|}W5QRXtjdd|tjtjBd}tjdd|tjd}tjd|tjd}|tjd |tjd7}d d |D}tt|S) a Extracts all the libraries (not relative imports this time) that are imported in a file. Args: filename (`str` or `os.PathLike`): The module file to inspect. Returns: `List[str]`: The list of all packages required to use the input module. r'r(r)z \s*try\s*:\s*.*?\s*except\s*.*?:r+zHif is_flash_attn[a-zA-Z0-9_]+available\(\):\s*(from flash_attn\s*.*\s*)+z^\s*import\s+(\S+)\s*$z^\s*from\s+(\S+)\s+importcSs$g|]}|ds|ddqS).r) startswithsplit)r8imprrrr;s zget_imports..) r-r.r/subr1DOTALLr0r2r3)rBr4r5importsrrr get_importss rKc Cst|}g}|D]f}zt|Wqtk rt}z4td|d|dt|krb||nW5d}~XYqXqt|dkrtdd |dd |d t |S) a. Check if the current Python environment contains all the libraries that are imported in a file. Will raise if a library is missing. Args: filename (`str` or `os.PathLike`): The module file to check. Returns: `List[str]`: The list of relative imports in the file. z&Encountered exception while importing z: zNo module namedNrz\This modeling file requires the following packages that were not found in your environment: z, z. Run `pip install  `) rKr import_module ImportErrorloggerwarningr7rr@joinr6)rBrJZmissing_packagesrG exceptionrrr check_importss    rTF force_reload) class_namer:rVr"c Cstj|}|dr"|dd}|tjjd}tt|}t|r^t j |dt t j |}t jj||d}|gtttt|}tddd|D}|dkrt j|} | t j |<n|} t| d d |kr|j| || _t| |W5QRSQRXdS) a Import a module on the cache directory for modules and extract a class from it. Args: class_name (`str`): The name of the class to import. module_path (`str` or `os.PathLike`): The path to the module to import. force_reload (`bool`, *optional*, defaults to `False`): Whether to reload the dynamic module from file if it already exists in `sys.modules`. Otherwise, the module is only reloaded if the file has changed. Returns: `typing.Type`: The class looked for. r>NrD)locationcss|]}t||VqdS)N)bytes read_bytesr<rrr sz&get_class_in_module..__transformers_module_hash__rC)rrnormpathendswithreplaceseprr _HF_REMOTE_CODE_LOCKrmodulespoprrgetutilspec_from_file_locationsortedmaprAhashlibsha256rR hexdigestmodule_from_specgetattrloader exec_moduler^) rWr:rVr!r& cached_moduleZ module_specZ module_filesZ module_hashmodulerrrget_class_in_modules*        rt) pretrained_model_name_or_pathr& cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_only repo_type _commit_hashr"c  Ks| dd} | dk r4tdt|dk r0td| }trL|sLtdd}t|}t j |} | rrt j |}n"| dt j j}t|||| | d}g}z8t|||||||||| | d }| s||kr||Wn.tk rtd |d |d YnXt|}tt j j|}t|tt|}|t j |kr||rbt|t||szt|||t|D]Z}|d }t j ||}||rt|t||s~t|||tq~nt!|| }||}|t j j|}t|||s,t|||t|D]L}||d s0t"||d ||||||||d ||d q0t#|dkr|dkrd dd|D}| dkrdn| d}d||}t$d|d|dt j ||S)a Prepares Downloads a module from a local folder or a distant repo and returns its path inside the cached Transformers module. Args: pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained model configuration hosted inside a model repo on huggingface.co. - a path to a *directory* containing a configuration file saved using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`. module_file (`str`): The name of the module file containing the class to look for. cache_dir (`str` or `os.PathLike`, *optional*): Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used. force_download (`bool`, *optional*, defaults to `False`): Whether or not to force to (re-)download the configuration files and override the cached versions if they exist. resume_download: Deprecated and ignored. All downloads are now resumed by default when possible. Will be removed in v5 of Transformers. proxies (`Dict[str, str]`, *optional*): A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request. token (`str` or *bool*, *optional*): The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated when running `huggingface-cli login` (stored in `~/.huggingface`). revision (`str`, *optional*, defaults to `"main"`): The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git. local_files_only (`bool`, *optional*, defaults to `False`): If `True`, will only try to load the tokenizer configuration from local files. repo_type (`str`, *optional*): Specify the repo type (useful when downloading from a space for instance). Passing `token=True` is required when you want to use a private model. Returns: `str`: The path to the module inside the cache. use_auth_tokenNrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.V`token` and `use_auth_token` are both specified. Please set only the argument `token`.z+Offline mode: forcing local_files_only=TrueT/)rvr{r}) rvrwryrxr|rzr{r}r~zCould not locate the z inside rDr>)rvrwrxryrzr{r|r~r cSsg|]}d|qS)z- rr<rrrr;sz*get_cached_module_file..rCzs/zhttps://huggingface.co/z9A new version of the following files was downloaded from z: z . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.)%rewarningswarn FutureWarning ValueErrorrrPinfor7rrisdirbasenamerarbr r rEnvironmentErrorerrorrTr r%rr rfilecmpcmpshutilcopyrrrRrget_cached_module_filer@rQ)rur&rvrwrxryrzr{r|r}r~Zdeprecated_kwargsris_local submodulerrZ new_filesZresolved_module_fileZmodules_neededZfull_submoduleZsubmodule_pathZ module_neededZmodule_needed_fileZ commit_hashZ repo_type_strurlrrrrs>           r) class_referencerurvrwrxryrzr{r|r} code_revisionr"c  Ks| dd} | dk r4tdt|dk r0td| }d|krL|d\} }n|} |d\}}| dkrr|| krr|} t| |d|||||| || d }t|||d S) a> Extracts a class from a module file, present in the local folder or repository of a model. Calling this function will execute the code in the module file found locally or downloaded from the Hub. It should therefore only be called on trusted repos. Args: class_reference (`str`): The full name of the class to load, including its module and optionally its repo. pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained model configuration hosted inside a model repo on huggingface.co. - a path to a *directory* containing a configuration file saved using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`. This is used when `class_reference` does not specify another repo. module_file (`str`): The name of the module file containing the class to look for. class_name (`str`): The name of the class to import in the module. cache_dir (`str` or `os.PathLike`, *optional*): Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used. force_download (`bool`, *optional*, defaults to `False`): Whether or not to force to (re-)download the configuration files and override the cached versions if they exist. resume_download: Deprecated and ignored. All downloads are now resumed by default when possible. Will be removed in v5 of Transformers. proxies (`Dict[str, str]`, *optional*): A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request. token (`str` or `bool`, *optional*): The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated when running `huggingface-cli login` (stored in `~/.huggingface`). revision (`str`, *optional*, defaults to `"main"`): The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git. local_files_only (`bool`, *optional*, defaults to `False`): If `True`, will only try to load the tokenizer configuration from local files. repo_type (`str`, *optional*): Specify the repo type (useful when downloading from a space for instance). code_revision (`str`, *optional*, defaults to `"main"`): The specific revision to use for the code on the Hub, if the code leaves in a different repository than the rest of the model. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git. Passing `token=True` is required when you want to use a private model. Returns: `typing.Type`: The class, dynamically imported from the module. Examples: ```python # Download module `modeling.py` from huggingface.co and cache then extract the class `MyBertModel` from this # module. cls = get_class_from_dynamic_module("modeling.MyBertModel", "sgugger/my-bert-model") # Download module `modeling.py` from a given repo and cache then extract the class `MyBertModel` from this # module. cls = get_class_from_dynamic_module("sgugger/my-bert-model--modeling.MyBertModel", "sgugger/another-bert-model") ```rNrrz--rDr>)rvrwrxryrzr{r|r}rU)rerrrrrFrrt)rrurvrwrxryrzr{r|r}rkwargsrZrepo_idr&rWZ final_modulerrrget_class_from_dynamic_modules8Z  r)objfolderconfigr"c sjdkr&tdd|ddSfdd}t|ttfrT|D] }||qDn|dk rd||g}tjjj}t |t |j }t ||| |t|D],}t |t |j }t ||| |q|S)a  Save the modeling files corresponding to a custom model/configuration/tokenizer etc. in a given folder. Optionally adds the proper fields in a config. Args: obj (`Any`): The object for which to save the module files. folder (`str` or `os.PathLike`): The folder where to save. config (`PretrainedConfig` or dictionary, `optional`): A config in which to register the auto_map corresponding to this custom object. Returns: `List[str]`: The list of files saved. __main__z We can't save the code defining z in z as it's been defined in __main__. You should put this code in a separate module so we can include it in the saved folder and make it easier to share via the Hub.Nc s jj}|dd}|djj}d|krd}d}jjdr|djj}tdddk rtd}|j}|dd}|d|j}n|djj}||f}t|tr|di} || j <| |d<n*t|dddk r||j j <n j |i|_ dS)NrD TokenizerZFastslow_tokenizer_classauto_map) __class__ __module__rF__name__r`ro isinstancedictrfZ _auto_classr) _config module_nameZ last_moduleZ full_namerZfast_tokenizer_classZslow_tokenizerZslow_tok_module_nameZlast_slow_tok_modulerrrr_set_auto_map_in_configAs,     z3custom_object_save.._set_auto_map_in_config)rrPrQrr2tuplerrd__file__rr!rrrrA) rrrrcfgresultZ object_file dest_fileZ needed_filerrrcustom_object_save+s*        rcCs tddS)NzLoading this model requires you to execute custom code contained in the model repository on your local machine. Please set the option `trust_remote_code=True` to permit loading of this model.)r)signumframerrr_raise_timeout_errorwsrc Cs|dkr|rd}n|rtdkrd}zzhttjt}tt|dkrtd|d|d}|dkrnd}q>|dkr>d}q>tdWn*tk rtd|d|d YnXW5|dk rttj|tdXn|rtdd|r|s|std |d |S) NFrzThe repository for z contains custom code which must be executed to correctly load the model. You can inspect the repository content at https://hf.co/z. You can avoid this prompt in future by passing the argument `trust_remote_code=True`. Do you wish to run the custom code? [y/N] )yesy1T)non0rCzS. Please pass the argument `trust_remote_code=True` to allow custom code to be run.zLoading z requires you to execute the configuration file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code=True` to remove this error.) TIME_OUT_REMOTE_CODEsignalSIGALRMalarmrinputlower Exceptionr)Ztrust_remote_codeZ model_nameZhas_local_codeZhas_remote_codeZprev_sig_handlerZanswerrrrresolve_trust_remote_codes>      r) NFNNNNFNN) NFNNNNFNN)N)5__doc__rrkrimportlib.utilrr/rrr threadingtypingrpathlibrtypesrrrrrrZhuggingface_hubr utilsr r r rrrZ get_loggerrrPLockrcr r7PathLiker%r6rArKrTboolTypertrrrrrrrrrrs    !'  4  4  }(L