T^(hY0ddlmZddlmZmZmZddlZddlZddlm Z ddl m Z m Z ddl mZmZddlmZdd lmZdd lmZd d lmZmZej2eZGd de ZGdde ZGddeZeGddeZGddeZ y)) dataclass)OptionalTupleUnionN)CrossEntropyLoss)InstructBlipQFormerConfigInstructBlipVisionConfig)$InstructBlipForConditionalGeneration/InstructBlipForConditionalGenerationModelOutput)PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging)CONFIG_MAPPING AutoConfigc eZdZy)InstructBlipVideoVisionConfigN__name__ __module__ __qualname__}/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/instructblipvideo/modular_instructblipvideo.pyrr)rrc eZdZy)InstructBlipVideoQFormerConfigNrrrrrr-rrrc\eZdZdZdZeeedZ d fd Z e dedede fdZ xZ S) InstructBlipVideoConfiga [`InstructBlipVideoConfig`] is the configuration class to store the configuration of a [`InstructBlipVideoForConditionalGeneration`]. It is used to instantiate a Instructblipvideo model according to the specified arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Instructblipvideo [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVideoVisionConfig`]. qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVideoQFormerConfig`]. text_config (`dict`, *optional*): Dictionary of configuration options used to initialize any [`PretrainedConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. video_token_index (`int`, *optional*): Token index of special video token. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ( ... InstructBlipVideoVisionConfig, ... InstructBlipVideoQFormerConfig, ... OPTConfig, ... InstructBlipVideoConfig, ... InstructBlipVideoForConditionalGeneration, ... ) >>> # Initializing a InstructBlipVideoConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipVideoConfig() >>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipVideoForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PretrainedConfig >>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations >>> vision_config = InstructBlipVideoVisionConfig() >>> qformer_config = InstructBlipVideoQFormerConfig() >>> text_config = OPTConfig() >>> config = InstructBlipVideoConfig.from_text_vision_configs(vision_config, qformer_config, text_config) ```instructblipvideo) text_configqformer_config vision_configc t|di||i}tjd|i}tjd|i}tjdt di||_t di||_d|vr|dnd}t|di||_ ||_ ||_ |j j|j_ |jjtv|_d|_d|_y) NzZvision_config is None. initializing the InstructBlipVideoVisionConfig with default values.z\qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.zTtext_config is None. Initializing the text config with default values (`OPTConfig`). model_typeoptg?g{Gz?r)super__init__loggerinforr$rr#rr"num_query_tokensvideo_token_index hidden_sizeencoder_hidden_sizer&ruse_decoder_only_language_modelinitializer_factorinitializer_range) selfr$r#r"r,r-kwargstext_model_type __class__s rr)z InstructBlipVideoConfig.__init__ps "6"  M KKt u  !N KKv w  K KKn o:K]K<N~N7C{7R+l3X])/:I[I 0!2262D2D2P2P//3/?/?/J/JNo/o,"%!%rr$r#r"c n|d|j|j|jd|S)a  Instantiate a [`InstructBlipVideoConfig`] (or a derived class) from a InstructBlipVideo vision model, Q-Former and language model configurations. Returns: [`InstructBlipVideoConfig`]: An instance of a configuration object )r$r#r"r)to_dict)clsr$r#r"r4s r from_vision_qformer_text_configsz8InstructBlipVideoConfig.from_vision_qformer_text_configssD  '//1)113#++-    r)NNN N)rrr__doc__r&rrr sub_configsr) classmethodr r: __classcell__)r6s@rr r 1sg5 n%J!86K !&F 4 7 &   rr c eZdZy)4InstructBlipVideoForConditionalGenerationModelOutputNrrrrrArAsrrAc2eZdZ ddejdejdeej deejdeej deej deej d eed eed eej d eed edeedee e ffdZ ej ddejdeej deej deej deej d edej fdZ y))InstructBlipVideoForConditionalGenerationN pixel_valuesqformer_input_idsqformer_attention_mask input_idsattention_maskdecoder_input_idsdecoder_attention_maskoutput_attentionsoutput_hidden_stateslabels return_dictinterpolate_pos_encoding use_cachereturnc ~ | | n|jj} |j\}}}}}|j||z|||}|j ||| | | }|d}t j |jddt j|j}|jj|jddd}t j |jddt j|j}|t j|}|j|d}|j|d}t j||gd}|j||||||| | }|dddd|jdddf}|j!|}|j||jj"|zd}t j |jddt j|j}|j$j'|}|t j|}t)|jd dd||jj*k(j-dj/|}|j1j3|j||<nyt4j7d t j||j3|jgd}t j||j3|jgd}|jj8r|j%|||| | | }| r |j:n|d}d} | | j3|j} |dd| jd dddf}|d ddddfj=}!| d ddfj=j3|j}"t?d }#|#|!jAd|jjBjD|"jAd} n@|j%|||||| | | |  }| r |jFn|d} | r |j:n|d}| s||||f}$| | f|$zS|$StI| ||||S)a0 ```python >>> from transformers import InstructBlipVideoProcessor, InstructBlipVideoForConditionalGeneration >>> import torch >>> from huggingface_hub import hf_hub_download >>> import av >>> import numpy as np >>> def read_video_pyav(container, indices): ... ''' ... Decode the video with PyAV decoder. ... Args: ... container (`av.container.input.InputContainer`): PyAV container. ... indices (`List[int]`): List of frame indices to decode. ... Returns: ... result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3). ... ''' ... frames = [] ... container.seek(0) ... start_index = indices[0] ... end_index = indices[-1] ... for i, frame in enumerate(container.decode(video=0)): ... if i > end_index: ... break ... if i >= start_index and i in indices: ... frames.append(frame) ... return np.stack([x.to_ndarray(format="rgb24") for x in frames]) >>> model = InstructBlipVideoForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b", device_map="auto") >>> processor = InstructBlipVideoProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b") >>> file_path = hf_hub_download( ... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset" ... ) >>> container = av.open(file_path) >>> # sample uniformly 4 frames from the videWhy is this video funny?o >>> total_frames = container.streams.video[0].frames >>> indices = np.arange(0, total_frames, total_frames / 4).astype(int) >>> clip = read_video_pyav(container, indices) >>> prompt = "What is happening in the video?" >>> inputs = processor(text=prompt, images=clip, return_tensors="pt").to(model.device) >>> outputs = model.generate( ... **inputs, ... do_sample=False, ... num_beams=5, ... max_length=256, ... repetition_penalty=1.5, ... length_penalty=1.0, ... ) >>> generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip() >>> print(generated_text) "A person is eating a bowl of pasta, and they are using a fork to eat it. The person is sitting at a table, and the plate of pasta is on the table in front" ```N)rDrKrLrNrOrdtypedevicedim)rGrH query_embedsencoder_hidden_statesencoder_attention_maskrKrLrNr-KExpanding inputs for video tokens in InstructBLIPVideo should be done in processing. Please follow instruction here (https://gist.github.com/zucchini-nlp/65f22892b054dc0d68228af56fbeaac2) to update your InstructBLIPVideo model. Using processors without these attributes in the config is deprecated and will throw an error in v4.47.) inputs_embedsrHrKrLrNrP.mean) reduction) r^rHrIrJrKrLrNrMrP)losslogitsvision_outputsqformer_outputslanguage_model_outputs)%configuse_return_dictshapereshape vision_modeltorchonessizelongrV query_tokensexpand ones_likerepeat_interleavecatqformerlanguage_projectionr,language_modelget_input_embeddingsgetattrr- unsqueeze expand_asflattentor* warning_oncer0rb contiguousrviewr" vocab_sizerarA)%r3rDrErFrGrHrIrJrKrLrMrNrOrP batch_sizeframeschannelheightwidthrc image_embedsimage_attention_maskroquery_attention_mask query_outputs query_outputlanguage_model_inputslanguage_model_attention_maskr^special_image_maskoutputsrbra shift_logits shift_labelsloss_fctoutputs% rforwardz1InstructBlipVideoForConditionalGeneration.forwardsP&1%->q-A+A1(DE !% 8 8 F!6 = =j$++JfJfioJoqs t(- ! & & (" -UZZH]HdHd) %C++@@B9M  !"__Y7N 4;; 3T : F"+t{{/L/L"L!W!WXZ![!e!efs!t 0E0M0M0O0R0RS`SgSg0hM, -   z  "II'N>NOdOkOk>l&mstuM"YY.0A0AB_BfBf0ghnoN ;; 6 6))+-"3%9'# *G(3W^^ FD!6==1FKKN?#4a 78%c3B3k2==? %c12g99;>>v}}M ,f= 1 1"dkk6M6M6X6X Y[g[l[lmo[pq))+-"3'="3%9'#* G$/7<jAd t j||j=|jgd }t j||j=|jgd }|jBj$jDsM|jGdd|jd zd z |d<|jGdd|jd z|d<||d}|jBj$jDs||d<|jBjHdi||}|S)a Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.FloatTensor` of shape (batch_size, num_channels, height, width) or (batch_size, num_frames, num_channels, height, width)): Input images or videos to be processed. qformer_input_ids (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): The sequence used as a prompt to be fed to the Q-Former module. qformer_attention_mask (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): Mask to avoid performing attention on padding token indices. input_ids (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): The sequence used as a prompt for the generation. attention_mask (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): Mask to avoid performing attention on padding token indices. interpolate_pos_encoding (`bool`, *optional*, defaults to `False`): Whether to interpolate the positional encoding of the image embeddings. Returns: captions (list): A list of strings of length batch_size * num_captions. hf_device_mapT)rNrONrSrTrrWrY)rGrHrZr[r\rNr-r] max_length min_length)r^rHrGr)%hasattr_preprocess_acceleraterhrirjlast_hidden_staterkrlrmrnrVrorprqrrrsrtrurfr,r" bos_token_idrxr-tensorrepeatrwryrzr{r|r*r}rvis_encoder_decodergetgenerate)r3rDrErFrGrHrOgenerate_kwargsrrrrrrrrorrrrlanguage_attention_mask start_tokensr^rinputsrs rrz2InstructBlipVideoForConditionalGeneration.generateqsb> 4 )  ' ' )6B5G5G2 FGVU#++J,?&RWX (( %=)     %zz,*;*;*=cr*B%**]i]p]pq((// 0B0B10Er2N $zz,*;*;*=cr*B%**]i]p]pq ! )%*__5F%G "-??A?N!7!I!I&VW!I!X!&,@BX+Y_`!a '1%".#7 % %66q:PLJ $ = =>A]A]]`aadpp  l^5::lNaNabI!((Q7I  !"__Y7N3113I>  4;; 3T : F"+t{{/L/L"L!W!WXZ![!e!efs!t 0E0M0M0O0R0RS`SgSg0hM, -   z  "II'N>NOdOkOk>l&mstuM"YY(.*;*;B15598<=A,0/3-1&*).$(~ ''~ !,,~ !))9)9 : ~ E--. ~ !!1!12 ~ $E$4$45~ !))9)9 :~ $D>~ 'tn~ ))*~ d^~ #'~ D>~  uJJ K~ @U]]_9==A0459).q''q$E$4$45q!))9)9 : q E,,- q !!1!12 q#'q   qqrrC)! dataclassesrtypingrrrrktorch.utils.checkpointtorch.nnr;transformers.models.instructblip.configuration_instructbliprr 6transformers.models.instructblip.modeling_instructblipr r configuration_utilsr models.auto.modeling_autorutilsrautorr get_loggerrr*rrr rArCrrrrs ")) % 4J-   H % $<  %> w .w t  ;j   s0Tsr