+sgx\ddlmZddlZddlZddlZddlmZddlmZddlm Z m Z ddl Z ddl Z ddl m Z ddlmZmZmZmZmZddlmZdd lmZej0eZd d ZGd d e j8Zy)) annotationsN)fnmatch)Path)AnyCallable)nn) AutoConfig AutoModel AutoTokenizer MT5ConfigT5Config)is_peft_available)find_adapter_config_filecdfd }|S)Ncttjt|z dt|z fi|S)NT)exist_ok)osmakedirsr)save_directorykwargs_save_pretrained_fn subfolders [/var/www/html/venv/lib/python3.12/site-packages/sentence_transformers/models/Transformer.pywrapperz)_save_pretrained_wrapper..wrappers5 D(94tD"4#7)#CNvNN)rz str | PathreturnNone)rrrs`` r_save_pretrained_wrapperrsO Nrc"eZdZUdZdZded< d dfd ZddZddZddZ dd Z dd Z dd Z dd Z dd ZddZddZddZddZ d d dZd!dZdd"dZed#dZxZS)$ TransformeraHugging Face AutoModel to generate token embeddings. Loads the correct class, e.g. BERT / RoBERTa etc. Args: model_name_or_path: Hugging Face models name (https://huggingface.co/models) max_seq_length: Truncate any inputs longer than max_seq_length model_args: Keyword arguments passed to the Hugging Face Transformers model tokenizer_args: Keyword arguments passed to the Hugging Face Transformers tokenizer config_args: Keyword arguments passed to the Hugging Face Transformers config cache_dir: Cache dir for Hugging Face Transformers to store/load models do_lower_case: If true, lowercases the input (independent if the model is cased or not) tokenizer_name_or_path: Name or path of the tokenizer. When None, then model_name_or_path is used backend: Backend used for model inference. Can be `torch`, `onnx`, or `openvino`. Default is `torch`. Tbool save_in_rootc t |ddg|_||_| |_|i}|i}|i}|j ||| |} |j || || fi|| d|vr||d<tj||n|fd|i||_ |t|jdrtt|jjdrTt|jdr>t|jjj|jj}||_|:|jj"j$|jj_yy)Nmax_seq_length do_lower_casemodel_max_length cache_dirconfigmax_position_embeddings)super__init__ config_keysr&backend _load_config _load_modelr from_pretrained tokenizerhasattr auto_modelr)minr*r'r% __class____name__tokenizer_class) selfmodel_name_or_pathr% model_argstokenizer_args config_argsr(r&tokenizer_name_or_pathr.r)r6s rr,zTransformer.__init__6sa ,o>*  J  !N  K""#5y';W+VYV:V  %*?!$T__%;%;%S%SUYUcUcUtUt!u, ! -59^^5M5M5V5VDOO " " 2 .rc 6t||jd|jd|jdd Bts td|dk7r t dd d lm}|j|fi|d |iStj|fi|d |iS) z"Loads the configuration of a modeltokenrevisionlocal_files_onlyF)r@rArBzgLoading a PEFT model requires installing the `peft` package. You can install it via `pip install peft`.torchaPEFT models can currently only be loaded with the `torch` backend. To use other backends, load the model with `backend="torch"`, call `model[0].auto_model.merge_and_unload()`, save that model with `model.save_pretrained()` and then load the model with the desired backend.r) PeftConfigr() rgetr Exception ValueErrorpeftrDr1r )r9r:r(r.r=rDs rr/zTransformer._load_configfs %"!oog.$4!,1CU!K     %&}'! w (-:--.@eKe[de e))*<a aW`aarc |dk(rt|tr|j|||fi|nDt|tr|j|||fi|nt j |f||d||_|j|||fi|y|dk(r|j|||fi|y|dk(r|j|||fi|ytd|d)zLoads the transformer modelrCr)r(onnxopenvinozUnsupported backend 'z6'. `backend` should be `torch`, `onnx`, or `openvino`.N) isinstancer _load_t5_modelr _load_mt5_modelr r1r4_load_peft_model_load_onnx_model_load_openvino_modelrG)r9r:r)r(r.r;s rr0zTransformer._load_models g &(+###$6 XZXFI.$$$%7YjY"+";";&#/5#NX# "D ! !"4fi V: V   !D ! !"4fi V: V  " %D % %&8&) Zz Z4WI=stu urc tr@PR^   NN; -9e8T8d8d 9  9  9 ,DDOODdDdfjfrfr+s(   & &'98\ R K# <  s C,,Dc &|jdd}|r||fS|jd|}|jdd} | rt| |jnt|j} | r%t| |j|jn#t|j|j} | r| d|nd|} |r<|j | D cgc]!} | j |j#}} nctj|jd|jdd|jd d }|Dcgc]}t|| s|}}| |v}|s`d|vr\| |v}|rVt|d kDr4d|vr0tjd |d |jd|d| d |j|d<||d<|| }t|j}t|d kDr8|d|d<t|jddg|ddj|d<|rQtjd|d|jd|d|r"tjd|d|d|dd||fScc} wcc}w)a Determines whether the model should be exported to the backend, or if it can be loaded directly. Also update the `file_name` and `subfolder` model_args if necessary. These are the cases: 1. If export is set in model_args, just return export 2. If `/` exists; set export to False 3. If `/` exists; set export to False and set subfolder to the backend (e.g. "onnx") 4. If `` contains a folder, add those folders to the subfolder and set the file_name to the last part We will warn if: 1. The expected file does not exist in the model directory given the optional file_name and subfolder. If there are valid files for this backend, but they're don't align with file_name, then we give a useful warning. 2. Multiple files are found in the model directory that match the target file name and the user did not specify the desired file name via `model_kwargs={"file_name": ""}` Args: load_path: The model repository or directory, as a Path instance is_local: Whether the model is local or remote, i.e. whether load_path is a local directory model_args: The model_args dictionary. Notable keys are "export", "file_name", and "subfolder" target_file_name: The expected file name in the model directory, e.g. "model.onnx" or "openvino_model.xml" target_file_glob: The glob pattern to match the target file name, e.g. "*.onnx" or "openvino*.xml" backend_name: The human-readable name of the backend for use in warnings, e.g. "ONNX" or "OpenVINO" Returns: Tuple[bool, dict[str, Any]]: A tuple of the export boolean and the updated model_args dictionary. r]NrYrz/**/z**/modelrAr@) repo_typerAr@z Multiple z files found in z: z, defaulting to zW. Please specify the desired file name via `model_kwargs={"file_name": ""}`.zNo z found in z. Exporting the model to .z#If you intended to load one of the  zN files, please specify the desired file name via `model_kwargs={"file_name": "rz"}`.)rcrEras_posixr.glob relative_tohuggingface_hublist_repo_filesrlenloggerwarningparts)r9rjrkr;target_file_namermrlr]rYrprimary_full_pathsecondary_full_path glob_patternpathmodel_file_names all_filesfname model_foundfile_name_partss rrbz"Transformer._backend_should_exportsN$/ :% %NN;0@A NN;5 ENDI6??ATXYbTcTlTlTn DLL) 4 = = ?dllI.779  @I)D)9(:;PSTdSeNf  S\SaSabnSop4 0 0 ; D D Fp p'77""$!# D9 nnWd3 I 4=]%|@\] ] (+;; {*<-1AAK'(1,J1NNN#L>1A)BTBTBVAYY[\l[mm}R~UUrs+/,, ;'*3 ;' >$_Fy///  ! #&5b&9J{ #&*:>>+r+J&b_]`^`Ma&b&k&k&mJ{ #  NNi]*Y-?-?-A,DD]^j]kklm  9:J9K1\N[^^nop^q]rrwy z!!Y q ^s &J J&Jcdd|d}|r |d|dz }n |d|dz }tj|y)NzSaving the exported zA model is heavily recommended to avoid having to export it again.z# Do so with `model.save_pretrained(z)`.z Do so with `model.push_to_hub(z, create_pr=True)`.)rr)r9r:rkrlto_logs rriz!Transformer._backend_warn_to_savefsN' ~5vw  ;I]:9/99  '- FP rcld|jd|jjjdS)Nz Transformer(z) with Transformer model: r)get_config_dictr4r6r7r9s r__repr__zTransformer.__repr__s7d22455OPTP_P_PiPiPrPrOsstuurc ||d|dd}d|vr|d|d<|jdi||ddi}|d}trddlm}t |j|r|jj j rr|jd}|d}tj||jj j|j } tj| |fd |d<||d <|jjjr*t|d kDrd } t|dkrd } || } | |d<|S)z#Returns token_embeddings, cls_token input_idsattention_mask)rrtoken_type_ids return_dictFr)PeftModelForFeatureExtraction)devicer{)dimtoken_embeddingsall_layer_embeddingsr)r4rrHrrMactive_peft_configis_prompt_learningsizerConesnum_virtual_tokensrcatr)output_hidden_statesr) r9featuresrtrans_features output_states output_tokensr batch_sizerprefix_attention_mask all_layer_idx hidden_statess rforwardzTransformer.forwardsK'/ '&:!;$""4({#**84 5'-KFF# -  jm, jm, -"6*KALL41A 4L L   ?JKs3!AGGI3KKK DNN*#..    5L4Ks0 E$ E .E$ E/E* 'E/E$*E/c\|jDcic]}||j|c}Scc}wr)r-__dict__)r9keys rrzTransformer.get_config_dicts*373C3CDCT]]3''DDDs)c>|jj|||jj|ttj j |dd5}tj|j|ddddy#1swYyxYw)N)safe_serializationsentence_bert_config.jsonwr)indent) r4save_pretrainedr2rerrjoinrfdumpr)r9 output_pathrfOuts rsavezTransformer.savesw '' HZ'[ &&{3 "'',,{,GH# N >RV IId**,d1 = > > >s #'BBcdD]C}tjj||}tjj|sCnt 5}t j |}ddddvrd|dvr|djdd|vrd|dvr|djdd|vrd|dvr|djd|dd|i|S#1swYpxYw)N)rzsentence_roberta_config.jsonzsentence_distilbert_config.jsonzsentence_camembert_config.jsonzsentence_albert_config.jsonz sentence_xlm-roberta_config.jsonzsentence_xlnet_config.jsonr;trust_remote_coder<r=r:r)rrrrarerfrgrc)cls input_path config_namesbert_config_pathfInr)s rrgzTransformer.loads K!# Z E ww~~/0 # $ $YYs^F $ 6 !&9VL=Q&Q < $ $%8 9 v %*=HXAY*Y # $ ( ()< = F "':f]>S'S = ! % %&9 :;j;F;; $ $s CC")NNNNNFNrC)r:rr%z int | Noner;dict[str, Any] | Noner<rr=rr( str | Noner&r"r>rr.rrr)r:rr(rr.rr=dict[str, Any])rr)rjrrkr"r;rrrrmrrlrrztuple[bool, dict[str, Any]])r:rrkrrlrrr)rr)rdict[str, torch.Tensor]rr)rint)T)rz.list[str] | list[dict] | list[tuple[str, str]]rz str | boolrr)rr)rrrr"rr)rrrr!)r7 __module__ __qualname____doc__r#__annotations__r,r/r0rPrRrQrbrirNrOrrrrrr classmethodrg __classcell__)r6s@rr!r!sv.L$ &*,004-1 $#&*.W.W#.W* .W . .W + .W.W.W!$.W.W .W`b8v&5Sn*SXc"c"c"# c"  c"  c"c" %c"J  v#J2\`&C&NX& &PE><rsX"    RR=B   8 $Z<"))Z