ZjASSKJrJr SSKJr SSKJrJr SSKJ r J r J r J r SSK JrJr SSKJrJr \"5(aSSKr"S S \ S S 9r\"S S\ 55rS/rg))OptionalUnion) BatchFeature) ImageInputis_valid_image)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)auto_docstringis_torch_availableNc.\rSrSrSS0SSS.SS0S .rS rg ) ColQwen2ProcessorKwargs"paddinglongestchannels_firstT) data_formatdo_convert_rgbreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__rځ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/colqwen2/processing_colqwen2.pyrr"s, y ," +D1 Ir%rF)totalc ^\rSrSrSS\S-S\S-4U4Sjjjr\SS\S-S\\ -\ \-\ \ -S\ \ S \ 4S jj5rSS jr\S 5r\S \4S j5rSS\S-S\ \ S \ 4SjjrS\\ \-S\ \ S \ 4SjrSS\S\ S4S\S\ S4S\S\SS\S\4S S4 SjjrSrU=r$)ColQwen2Processor/Nvisual_prompt_prefix query_prefixc >[TU]XUS9 [US5(dSO URUl[US5(dSO URUlU=(d SUlU=(d SUlg) aJ visual_prompt_prefix (`str`, *optional*, defaults to `"<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe the image.<|im_end|><|endoftext|>"`): A string that gets tokenized and prepended to the image tokens. query_prefix (`str`, *optional*, defaults to `"Query: "`): A prefix to be used for the query. ) chat_template image_tokenz <|image_pad|> video_tokenz <|video_pad|>zf<|im_start|>user <|vision_start|><|image_pad|><|vision_end|>Describe the image.<|im_end|><|endoftext|>zQuery: N)super__init__hasattrr/r0r+r,)selfimage_processor tokenizerr.r+r,kwargs __class__s r&r2ColQwen2Processor.__init__1ss =Q29)]2S2S?YbYnYn29)]2S2S?YbYnYn$8% u !)5Ir%imagestextr7returnc UR"[4SURR0UD6nUSR SS5nUSLnUcUc [ S5eUbUb [ S5eUGbV[ U5(aU/nOw[U[5(a[ US5(aON[U[5(a.[US[5(a[ USS5(d [ S5eUR/[U5-nUR"SS U0US D6nUS n U bURRS -n Sn [[U55Hn URX|;aPX|RURS XR!5U --S5X|'U S- n URX|;aMPX|RS UR5X|'M UR"U4SS0USD6n [#0U EUES9nUS SS2S4US SS2S 4-n[[$R&"USUR)555n[$R*R,R.R1USS9US'U(a.USR3USS:HS5nUR5SU05 U$Ub[U[65(aU/nO8[U[5(a[US[65(d [ S5eUcUR8S-n/nUH&nUR:U-U-nUR=U5 M( UR"U4SS0USD6nU$g)a Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. tokenizer_init_kwargsrsuffixNz&Either text or images must be providedz5Only one of text or images can be processed at a timerzAimages must be an image, list of images or list of list of imagesr:rimage_grid_thwz<|placeholder|>return_token_type_idsF)data pixel_valuesT) batch_first input_idstoken_type_idsilabelsz*Text must be a string or a list of strings r) _merge_kwargsrr6 init_kwargspop ValueErrorr isinstancelistr+lenr5 merge_sizeranger/replaceprodrtorchsplittolistnnutilsrnn pad_sequence masked_fillupdatestrquery_augmentation_tokenr,append)r4r:r;r7 output_kwargsr?rC texts_doc image_inputsr@ merge_lengthindexi text_inputs return_dataoffsetsrErI texts_queryqueryaugmented_query batch_querys r&__call__ColQwen2Processor.__call__Is"** # "&.."<"<  }-11(DA &d 2 >A s9~.A**il:'0|';'; ,,.?>CXC]C]C_coCo.prs(   **il: $-<#7#78I4K[K[#\IL /..&+ .K ',K{,Kl,KLK""23AqD9KHX[_`>`bfg""Hf#56   $$$v t,,DGS1I1I !MNN~66;%'K"&"3"3e";f"D""?3..&+ .K  +r%c 0nUb[RRS05nURU5 URSS5=(d URR nUVs/sH!nURR "/UQUP76PM# nnUVs/sH oUS--PM n nURXS.5 [S0UD6$s snfs snf)ay Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (`list[list[int]]`, *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. NrrRrA)num_image_tokensnum_image_patchesr)rr#getr^r5rRget_number_of_image_patchesr ) r4 image_sizesr7 vision_datarrR image_sizers num_patchesrrs r&_get_num_multimodal_tokens,ColQwen2Processor._get_num_multimodal_tokenss  "3==AA/SUVM   (&**<>a$BVBVBaBaJ#.!"-J$$@@\*\m\"- !SddRc; A !=Rc d   4Dm n, ,,! es *(C CcURRnURRnUVs/sH o3S;dM UPM nnX-$s snf)N)pixel_values_videosvideo_grid_thw)r6model_input_namesr5)r4tokenizer_input_namesimage_processor_input_namesnames r&r#ColQwen2Processor.model_input_namessY $ @ @&*&:&:&L&L# 9' 8THq}}5F5f55r%c *UR"SSU0UD6$)a Prepare for the model one or several texts. This method is a wrapper around the `__call__` method of the ColQwen2Processor's [`ColQwen2Processor.__call__`]. This method forwards the `text` and `kwargs` arguments to the tokenizer. Args: text (`str`, `list[str]`, `list[list[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). r;rr)r4r;r7s r&process_queries!ColQwen2Processor.process_queriess<}}1$1&11r%query_embeddingsz torch.Tensorpassage_embeddings batch_size output_dtypez torch.dtype output_devicez torch.devicec [U5S:Xa [S5e[U5S:Xa [S5eUSRUSR:wa [S5eUSRUSR:wa [S5eUcUSRn/n[ S[U5U5GHn/n[ R RRRXXs-SSS9n [ S[U5U5H}n [ R RRRX*X-SSS9n UR[ R"SX5RS S 9SRS S 95 M UR[ R"US S 9RU5RU55 GM [ R"USS 9$) a Compute the late-interaction/MaxSim score (ColBERT-like) for the given multi-vector query embeddings (`qs`) and passage embeddings (`ps`). For ColQwen2, a passage is the image of a document page. Because the embedding tensors are multi-vector and can thus have different shapes, they should be fed as: (1) a list of tensors, where the i-th tensor is of shape (sequence_length_i, embedding_dim) (2) a single tensor of shape (n_passages, max_sequence_length, embedding_dim) -> usually obtained by padding the list of tensors. Args: query_embeddings (`Union[torch.Tensor, list[torch.Tensor]`): Query embeddings. passage_embeddings (`Union[torch.Tensor, list[torch.Tensor]`): Passage embeddings. batch_size (`int`, *optional*, defaults to 128): Batch size for computing scores. output_dtype (`torch.dtype`, *optional*, defaults to `torch.float32`): The dtype of the output tensor. If `None`, the dtype of the input embeddings is used. output_device (`torch.device` or `str`, *optional*, defaults to "cpu"): The device of the output tensor. Returns: `torch.Tensor`: A tensor of shape `(n_queries, n_passages)` containing the scores. The score tensor is saved on the "cpu" device. rzNo queries providedzNo passages providedz/Queries and passages must be on the same devicez-Queries and passages must have the same dtypeT)rF padding_valuez bnd,csd->bcnsr)dimrArB)rQrNdevicedtyperSrVrYrZr[r\raeinsummaxsumcatto) r4rrrrrscoresrg batch_scores batch_queriesjbatch_passagess r&score_retrieval!ColQwen2Processor.score_retrieval"s@  A %23 3 ! "a '34 4 A  % %);A)>)E)E ENO O A  $ $(:1(=(C(C CLM M  +A.44L%'q#./:\]"A"##LL-PTTYZT[\]^bbghbi C MM%))La8;;LILL][ \=yyQ''r%)r/r,r0r+)NNNNN)NN)N)Ncpu)rr r!r"r_r2rrrr rPr rrrorzpropertyrr`rrrintrrr$ __classcell__)r8s@r&r)r)/s+/#' 6 "Dj 6 Dj 660%)Z^fT!f++d9o=EV@WWf01 f  ffP-4 C C(#((%)6T!6016  6B2$y/)2012  2H0449 >(^0D DE>(".$~2F"FG>( >( }- >( ^S01 >( >(>(r%r))typingrrfeature_extraction_utilsr image_utilsrrprocessing_utilsr r r r tokenization_utils_baser rrZrrrVrr)__all__rr%r&rsb*#45XXC7 .e p(p(p(f  r%