UhddlZddlmZddlmZmZmZmZmZddl Z ddl m Z ddl m Z ddl mZddlmZmZmZmZdd lmZdd lmZdd lmZdd lmZmZmZdd lmZm Z ddl!m"Z"ddl#m$Z$m%Z%m&Z&m'Z'm(Z(ddl)m*Z*ddl+m,Z,m-Z-m.Z.e&r ddl/m cm0Z1e'jde3Z4e$Gdde Z5eGddeZ6eGddeZ7eGddeZ8Gdde jrZ:de jvded(e>fd)Z?Gd*d+e jrZ@Gd,d-e jrZAGd.d/eZBGd0d1e jrZCe$Gd2d3e5ZDGd4d5e jrZEGd6d7e jrZFGd8d9e jrZGGd:d;e jrZHGd<d=e jrZIGd>d?e jrZJGd@dAe jrZKGdBdCe jrZLGdDdEe jrZMe$dFGGdHdIe5ZNGdJdKe jrZOGdLdMe jrZPe$dNGGdOdPe5ZQGdQdRe5eZRgdSZSy)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) JanusConfigJanusVisionConfigJanusVQVAEConfigcDeZdZeZdZdZdgZddgZdZ dZ dZ dZ dZ dZdZy) JanusPreTrainedModelmodelTLlamaDecoderLayerpast_key_values causal_maskFct|jdr |jjjn|jj}t |t j t jfrY|jjjd||j%|jjjyyt |t jt jfrJ|jjj|jjjdyt |t j rf|jjjd||j"2|jj|j"jyyy)N vision_config)meanstdg?)hasattrconfigr,initializer_range isinstancer LinearConv2dweightdatanormal_biaszero_ GroupNorm LayerNormfill_ Embedding padding_idx)selfmoduler/s z/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/janus/modeling_janus.py _init_weightsz"JanusPreTrainedModel._init_weightsFs;t{{O4 KK % % 7 7.. fryy"))4 5 MM   & &CS & 9{{&   &&(' r|| < = KK   " " $ MM   $ $S )  - MM   & &CS & 9!!- ""6#5#56<<>..N)__name__ __module__ __qualname__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_assignmentrCrDrBr&r&8sOL&*#,-#4m"D!N $ !(-%?rDr&c\eZdZUdZdZeejed<dZ ejed<y)JanusVQVAEOutputaM 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_loss) rErFrG__doc__rVrtorch FloatTensor__annotations__rWrSrDrBrUrUYs/9=(5#4#45<(,NE%%,rDrUceZdZUdZdZeejed<dZ ee e ejed<dZ ee ejed<dZ ee ejed<dZ ee ejed<y)JanusBaseModelOutputWithPasta 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_states)rErFrGrXr^rrYrZr[r)rr_r`rarSrDrBr]r]hs"H6:x 1 129AEOXeE%*;*;$<=>E8B%(9(9":;BrDr]ceZdZUdZdZeejed<dZ eejed<dZ ee ejed<dZ ee ejed<dZee ejed<dZee ejed<y) JanusCausalLMOutputWithPasta 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)r_r`ra)rErFrGrXrdrrYrZr[rer)rr_rr`rarSrDrBrcrcs@)-D(5$$ %,*.FHU&& '.9=OXd5#4#456=8B%(9(9":;BrDrcceZdZdeffd Zdej dededej fdZd dej d e dej fd Z xZ S) JanusVisionEmbeddingsr1cft|||_|j|_|j |_|j |_tj|j|j|j |j d|_ |j |j zdz|_ |j|_ tj|j|j|_|jdt!j"|jj%ddy)Nvalid) in_channels out_channels kernel_sizestridepaddingr position_ids)r!F) persistent)super__init__r1 hidden_size embed_dim image_size patch_sizer r5 num_channelspatch_embedding num_patches num_positionsr>position_embeddingregister_bufferrYarangeexpandr@r1 __class__s rBrszJanusVisionEmbeddings.__init__s  ++ ++ ++!yy++??  !OOt>1D!--"$,,t/A/A4>>"R ^U\\$:L:L-M-T-TU\-]joprD embeddingsheightwidthreturnc|jd}|jjjd}tjj s%||k(r ||k(r|j|j S|jjjd}|jd}||jz}||jz} t|dz} |jd| | |}|jdddd}tjj||| fdd }|jddddjdd|}|S) 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!rrpg?r rbicubicF)sizemode align_corners)shaper|r6rYjit is_tracingro unsqueezerwrreshapepermuter functional interpolateview) r@rrrrzr{patch_pos_embeddim new_height new_widthsqrt_num_positionss rBinterpolate_pos_encodingz.JanusVisionEmbeddings.interpolate_pos_encodingsE!&&q) //66<