fThSSKrSSKJr SSKJrJrJrJrJr SSK r SSK J r SSK J r SSK Jr SSKJrJrJrJr SS KJr SS KJr SS KJr SS KJrJrJr SS KJrJ r SSK!J"r" SSK#J$r$J%r%J&r&J'r'J(r( SSK)J*r* SSK+J,r,J-r-J.r. \&"5(a SSK/J s J0r1 \'Rd"\35r4\$"SS\ 55r5\"SS\55r6\"SS\55r7\"SS\55r8"SS\ Rr5r:S\ RvS\S(\>4S)jjr?"S*S+\ Rr5r@"S,S-\ Rr5rA"S.S/\5rB"S0S1\ Rr5rC\$"S2S3\555rD"S4S5\ Rr5rE"S6S7\ Rr5rF"S8S9\ Rr5rG"S:S;\ Rr5rH"S<S=\ Rr5rI"S>S?\ Rr5rJ"S@SA\ Rr5rK"SBSC\ Rr5rL"SDSE\ Rr5rM\$"SFSG9"SHSI\555rN"SJSK\ Rr5rO"SLSM\ Rr5rP\$"SNSG9"SOSP\555rQ"SQSR\5\5rR/SSQrSg)UN) dataclass)CallableListOptionalTupleUnion)nn)ACT2FN)Cache)%ClassifierFreeGuidanceLogitsProcessorGenerationMixinGenerationModeLogitsProcessorList)GenerateDecoderOnlyOutput)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputBaseModelOutputWithPooling ModelOutput)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tupleis_torch_availablelogging torch_int) AutoModel) JanusConfigJanusVisionConfigJanusVQVAEConfigcL\rSrSr\rSrSrS/rSS/r Sr Sr Sr Sr SrSrSrS rg ) JanusPreTrainedModel8modelTLlamaDecoderLayerpast_key_values causal_maskFc[URS5(a URRROURRn[ U[ R [ R45(aWURRRSUS9 URb%URRR5 gg[ U[ R[ R45(aJURRR5 URRRS5 g[ U[ R 5(adURRRSUS9 UR"b2URRUR"R5 ggg)N vision_config)meanstdg?)hasattrconfigr-initializer_range isinstancer LinearConv2dweightdatanormal_biaszero_ GroupNorm LayerNormfill_ Embedding padding_idx)selfmoduler0s `/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/janus/modeling_janus.py _init_weights"JanusPreTrainedModel._init_weightsFsGt{{O44 KK % % 7 7.. fryy"))4 5 5 MM   & &CS & 9{{&   &&(' r|| < = = KK   " " $ MM   $ $S )  - - MM   & &CS & 9!!- ""6#5#56<<>..N)__name__ __module__ __qualname____firstlineno__r" config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_quantized_cache_supports_cache_class_supports_static_cache!_supports_param_buffer_assignmentrD__static_attributes__rGrFrCr&r&8sOL&*#,-#4m"D!N $ !(-%?rFr&cd\rSrSr%SrSr\\R\ S'Sr \R\ S'Sr g)JanusVQVAEOutputYa1 Base class for Janus VQ-VAE mode model outputs. Args: decoded_pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`): Reconstructed pixel values after encoding and decoding the input. embedding_loss (`torch.FloatTensor`): Embedding loss. Ndecoded_pixel_valuesembedding_lossrG) rHrIrJrK__doc__r[rtorch FloatTensor__annotations__r\rWrGrFrCrYrYYs/9=(5#4#45<(,NE%%,rFrYc\rSrSr%SrSr\\R\ S'Sr \\ \ \R\ S'Sr \\ \R\ S'Sr \\ \R\ S'Sr\\ \R\ S'S rg) JanusBaseModelOutputWithPasthat Base class for Janus model's outputs that may also contain a past key/values (to speed up sequential decoding). Args: last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Sequence of hidden-states at the output of the last layer of the model. If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output. past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. image_hidden_states (`tuple(torch.FloatTensor)`, *optional*): Tuple of `torch.FloatTensor` (one for the output of the image embeddings, `(batch_size, num_images, sequence_length, hidden_size)`. image_hidden_states of the model produced by the vision encoder, and optionally by the perceiver Nlast_hidden_stater* hidden_states attentionsimage_hidden_statesrG)rHrIrJrKr]rdrr^r_r`r*rrerfrgrWrGrFrCrbrbhs"H6:x 1 129AEOXeE%*;*;$<=>E8B%(9(9":;BrFrbc"\rSrSr%SrSr\\R\ S'Sr \\R\ S'Sr \\ \R\ S'Sr \\\R\ S'Sr\\\R\ S'Sr\\\R\ S 'S rg) JanusCausalLMOutputWithPastan Base class for Janus causal language model (or autoregressive) outputs. Args: loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided): Language modeling loss (for next-token prediction). logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`): Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. image_hidden_states (`tuple(torch.FloatTensor)`, *optional*): Tuple of `torch.FloatTensor` (one for the output of the image embeddings, `(batch_size, num_images, sequence_length, hidden_size)`. image_hidden_states of the model produced by the vision encoder, and optionally by the perceiver Nlosslogitsr*rerfrgrG)rHrIrJrKr]rkrr^r_r`rlr*rrerrfrgrWrGrFrCriris@)-D(5$$ %,*.FHU&& '.9=OXd5#4#456=8B%(9(9":;BrFric^\rSrSrS\4U4SjjrS\RS\S\S\R4Sjr S S \RS \ S\R4S jjr S r U=r $)JanusVisionEmbeddingsr2c^>[TU]5 XlURUlUR UlUR Ul[R"URURUR UR SS9Ul UR UR -S-Ul URUl [R"URUR5UlURS[ R""UR5R%S5SS9 g)Nvalid) in_channels out_channels kernel_sizestridepaddingr position_ids)r!F) persistent)super__init__r2 hidden_size embed_dim image_size patch_sizer r6 num_channelspatch_embedding num_patches num_positionsr?position_embeddingregister_bufferr^arangeexpandrAr2 __class__s rCr{JanusVisionEmbeddings.__init__s  ++ ++ ++!yy++??  !OOt>1D!--"$,,t/A/A4>>"R ^U\\$:L:L-M-T-TU\-]joprF embeddingsheightwidthreturncURSnURRRSn[RR 5(d%XE:Xa X#:XaURUR 5$URRRS5nURSnX R-nX0R-n [US-5n URSXU5nURSSSS5n[RRUX4SSS 9nURSSSS5RSSU5nU$) a This method allows to interpolate the pre-trained position encodings, to be able to use the model on higher resolution images. This method is also adapted to support torch.jit tracing and no class embeddings. Adapted from: - https://github.com/facebookresearch/dino/blob/de9ee3df6cf39fac952ab558447af1fa1365362a/vision_transformer.py#L174-L194, and - https://github.com/facebookresearch/dinov2/blob/e1277af2ba9496fbadf7aec6eba56e8d882d1e35/dinov2/models/vision_transformer.py#L179-L211 r!rrxg?r rbicubicF)sizemode align_corners)shaperr7r^jit is_tracingrw unsqueezerrreshapepermuter functional interpolateview) rArrrrrpatch_pos_embeddim new_height new_widthsqrt_num_positionss rCinterpolate_pos_encoding.JanusVisionEmbeddings.interpolate_pos_encodings:!&&q) //66<