+ j4<Rt^RIt^RIHt^RIHt^RIHt^RIHtH t ^RI H t ^RI H t ^RIHt^R IHtHtHtHtHt^R IHt]P0!]4t]!R R ] 44t]!R R7!RR]44t]!RR7!RR]]44t.ROtR#)zPyTorch Fuyu model.N)nn)Cache)GenerationMixin)BaseModelOutputWithPoolingCausalLMOutputWithPast)PreTrainedModel) AutoModel)Unpack)TransformersKwargsauto_docstringcan_return_tupleloggingtorch_compilable_check FuyuConfigcRa]tRt^ toRtRtRtRtRtRt Rt .t R.t V3Rlt RtVtR#)FuyuPreTrainedModelmodelTpast_key_valuesc&<V^8dQh/S[;R&#configr)format __classdict__s"g/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/fuyu/modeling_fuyu.py __annotate__ FuyuPreTrainedModel.__annotate__ s N)imagetext)__name__ __module__ __qualname____firstlineno__base_model_prefixinput_modalitiessupports_gradient_checkpointing_supports_attention_backend_supports_flash_attn_supports_sdpa_supports_flex_attn_no_split_modules_skip_keys_device_placement__annotate_func____static_attributes____classdictcell__)rs@rrr sF (&*#"&N#4"5rrzt The Fuyu model which consists of a vision backbone and a language model, without a language modeling head. ) custom_introcaa]tRt^.toV3RlV3RlltV3RlRlt]]V3RlRl44tV3RlRlt ]]R V3R lR ll44t R t Vt V;t #) FuyuModelc <V^8dQhRS[/#rr)rrs"rrFuyuModel.__annotate__4s  z rc<\SV`V4VPVnVPP Vn\ P!VP4Vn\P!VPVP,VP,VP4VnRVnVP!4R#)FN)super__init__ pad_token_id padding_idx text_config vocab_sizer from_configlanguage_modelrLinear patch_size num_channels hidden_sizevision_embed_tokensgradient_checkpointing post_initselfr __class__s&&rr9FuyuModel.__init__4s  !.. ,,77'33F4F4FG#%99    1 1 1F4G4G GI[I[$  ',# rc<V^8dQhRS[PRS[S[P,RS[PRS[P/#)rword_embeddingscontinuous_embeddingsimage_patch_input_indicesreturn)torchTensorlist)rrs"rrr6AsH*!*!*! $ELL1*!$)<< *!  *!rc  VP^,\V48Xg.\R\V4: RVP^,: 24hVP4p\ VP^,4Fp\ P !W5,^8RR7^,pW5,V,pVP^,W%,P^,8d2\RW%,P: RVP: RV R24hW%,V,PVP4WEV3&K V#) ayThis function places the continuous_embeddings into the word_embeddings at the locations indicated by image_patch_input_indices. Different batch elements can have different numbers of continuous embeddings. Args: word_embeddings (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Tensor of word embeddings. continuous_embeddings (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`): Tensor of continuous embeddings. The length of the list is the batch size. Each entry is shape [num_image_embeddings, hidden], and num_image_embeddings needs to match the number of non-negative indices in image_patch_input_indices for that batch element. image_patch_input_indices (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Tensor of indices of the image patches in the input_ids tensor. z7Batch sizes must match! Got len(continuous_embeddings)=z and word_embeddings.shape[0]=T)as_tuplezGNumber of continuous embeddings continuous_embeddings[batch_idx].shape=zA does not match number of continuous token ids src_indices.shape=z in batch element .) shapelen ValueErrorclonerangerPnonzerotodevice)rHrLrMrNoutput_embeddings batch_idx dst_indices src_indicess&&&& rgather_continuous_embeddings&FuyuModel.gather_continuous_embeddingsAsI( %%a(C0E,FFJs3H/I.KKjQ`QfQfghQiPkl ,11344Q78I --(A(LPQ(Q\`abcdK4>{KK  #&;&F&L&LQ&OO ^7L7W7]7]6_`I6A6G6G5II[\e[ffgi9N8XYd8e8h8h!((9 4 59 ! rc`<V^8dQhRS[PRS[S[,RS[S[,/#)r pixel_valueskwargsrO)rP FloatTensorr r tupler)rrs"rrr6os<NN!--N9?@R9SN + +Nrc <VPV4p\VR7#)z pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`): The tensors corresponding to the input images. )last_hidden_state)rDr)rHrerfpatch_embeddingss&&, rget_image_featuresFuyuModel.get_image_featuresms! 33LA)