fThaHSSKJrJrJrJr SSKrSSKrSSKJr SSKJ r SSK J r SSK J r SSKJrJrJr S S KJrJr S S KJr S S KJrJrJrJrJr \R:"\5r"S S\5r "SS\5r!"SS\5r""SS\5r#"SS\5r$"SS\5r%"SS\5r&"SS\5r'/SQr(g))ListOptionalTupleUnionN)nn) DynamicCache)FlashAttentionKwargs)Unpack)auto_docstringcan_return_tuplelogging)Idefics3ConfigIdefics3VisionConfig)Idefics3ImageProcessor)Idefics3BaseModelOutputWithPast Idefics3ForConditionalGeneration Idefics3ModelIdefics3PreTrainedModelIdefics3VisionTransformerc\rSrSrSrSrSrg)SmolVLMVisionConfig(a This is the configuration class to store the configuration of a [`SmolVLMVisionModel`]. It is used to instantiate a SmolVLM vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the SigLIP checkpoint [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) used in SmolVLM [HuggingFaceTB/SmolVLM2-2.2B-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct). Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 1152): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers.models.smolvlm.modeling_smolvlm import SmolVLMVisionTransformer >>> from transformers.models.smolvlm.configuration_smolvlm import SmolVLMVisionConfig >>> # Initializing a SmolVLMVisionConfig with google/siglip-so400m-patch14-384 style configuration >>> configuration = SmolVLMVisionConfig() >>> # Initializing a SmolVLMVisionTransformer (with random weights) from the google/siglip-so400m-patch14-384 style configuration >>> model = SmolVLMVisionTransformer(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```smolvlm_visionN__name__ __module__ __qualname____firstlineno____doc__ model_type__static_attributes__rc/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/smolvlm/modular_smolvlm.pyrr(s1 f"Jr%rc\rSrSrSrSrg)SmolVLMPreTrainedModel`cZ[URSURR5R5n[ U[ R [ R45(aWURRRSUS9 URb%URRR5 gg[ U[ R5(adURRRSUS9 URb2URRURR5 gg[ U[ R5(aJURRR!S5 URRR5 gg)Ninitializer_range)meanstdg?)getattrconfigget_text_configr+ isinstancerLinearConv2dweightdatanormal_biaszero_ Embedding padding_idx LayerNormfill_)selfmoduler.s r& _init_weights$SmolVLMPreTrainedModel._init_weightsas(dkk#6 8S8S8U8g8gh fryy"))4 5 5 MM   & &CS & 9{{&   &&('  - - MM   & &CS & 9!!- ""6#5#56<<>.  - - MM   $ $S ) KK   " " $.r%rN)rrr r!r@r$rr%r&r(r(`s %r%r(c\rSrSrSrg)SmolVLMVisionTransformerqrNrrr r!r$rr%r&rCrCqr%rCc\rSrSrSrSrSrg) SmolVLMConfiguaC This is the configuration class to store the configuration of a [`SmolVLMModel`]. It is used to instantiate a SmolVLM model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the model of the SmolVLM [HuggingFaceTB/SmolVLM2-2.2B-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should cache the key/value pairs of the attention mechanism. Only relevant if `config.is_decoder=True`. image_token_id (`int`, *optional*, defaults to 128257): The id of the "image" token. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether or not to tie the word embeddings with the token embeddings. vision_config (`IdeficsVisionConfig` or `dict`, *optional*, defaults to `IdeficsVisionConfig`): Custom vision config or dict for the vision tower text_config (`PretrainedConfig` or `dict`, *optional*, defaults to `LlamaConfig`): Custom text config or dict for the text model scale_factor (`int`, *optional*, defaults to 2): The scale factor for the image encoder. pad_token_id (`int`, *optional*, defaults to 128002): The id of the padding token. Example: ```python >>> from transformers import SmolVLMModel, SmolVLMConfig >>> # Initializing configuration >>> configuration = SmolVLMConfig() >>> # Initializing a model from the configuration >>> model = SmolVLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```smolvlmrNrrr%r&rHrHus# JJr%rHc\rSrSrSrg)SmolVLMImageProcessorrNrErr%r&rLrLrFr%rLc\rSrSrSrg)SmolVLMBaseModelOutputWithPastrNrErr%r&rOrOrFr%rOc#@\rSrSrSrS\R S\RS\R4SjrSS\RS \R 4S jjr \ \ "S S 9SS\ \R S \ \RS\ \R S\ \\RS\ \RS\ \RS \ \RS\ \RS\ \S\ \S\ \S\ \S\ \R S\\S\\\44Sjj55rSrg) SmolVLMModelz A subclass of Idefics3Model. We do *not* remove or block the call to inputs_merger in forward. Instead, we override inputs_merger here with custom logic. input_ids inputs_embedsimage_hidden_statesc0URupEnXR:HnURSS9n[R"Xu-S:H5(d [ S5eXu-n[R RRURSS9SSS9n U SSn URSS9n U S- U-n U S- U-n U RS5U -n[R"U5nX>UXSS24X'[R"URS5X5nU$)NdimrzCAt least one sample has tokens not divisible by patch_size.)rXr)value) shapeimage_token_idsumtorchall ValueErrorr functionalpadcumsum unsqueeze zeros_likewhere)r>rTrUrV_ patch_size image_masknum_image_tokensblocks_per_sampleoffsets block_offsetrow_cum chunk_idx local_idx block_idx image_embeds merged_embedss r& inputs_mergerSmolVLMModel.inputs_mergers,/44q"5"55 %>>a>0yy)6!;<<bc c,:((%%))*;*B*Bq*B*I6YZ)[s| ###+q[Z/ q[J.  **1- 9 '' 6 #67LiNcef7f#g   J$8$8$rxry batch_size num_images num_channelsheightwidthnb_values_per_imagereal_images_indsirjpatches_subgridrrVs r&get_image_featuresSmolVLMModel.get_image_featuress?K>P>P; e#(()@Z?Y((+Y?jj#**$ $8#<# (batch_size, max_num_images, 3, max_heights, max_widths) where max_num_images is the maximum number of images among the batch_size samples in the batch. Padding images are not needed beyond padding the pixel_values at the entrance of the model. For efficiency, we only pass through the vision_model's forward the real images by discarding the padding images i.e. pixel_values of size (image_batch_size, 3, height, width) where image_batch_size would be 7 when num_images_per_sample=[1, 3, 1, 2] and max_num_images would be 3. ) custom_introattention_mask position_idspast_key_values use_cacheoutput_attentionsoutput_hidden_states return_dictcache_positionkwargsreturnc .U bU OURRn U bU OURRn U bU OURRn U bU OURRn UR (a9UR R(aU (a[RS5 Sn UbURunnOUbURunnnO [S5eSnU (aUc [5nUR5nUbUcUS:Xa [S5eUc9UR R5"U5RUR 5nUbUb [S5eUbUR#Xg5nO'Ub$URUR$UR S9nUbUbUR'UUUS9nUR "S UUUUU U U S U S . UD6n[)UR*UR,UR.UR0US 9$) NzZ`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...Fz5You have to specify either input_ids or inputs_embedsrzWWhen first calling the model, if input_embeds are passed, input_ids should not be None.zMYou cannot specify both pixel_values and image_hidden_states at the same time)r~r)rTrUrVT) rUrrrrrrrr)rr hidden_states attentionsrVr)r0rrruse_return_dicttraining text_modelgradient_checkpointinglogger warning_oncer]rbr get_seq_lengthget_input_embeddingstorrr~rvrOrrrr)r>rTrrrrUrxryrVrrrrrrr seq_lengthripast_seen_tokensoutputss r&forwardSmolVLMModel.forwards7:2C1N-TXT_T_TqTq$8$D $++JjJj "+!6IDKKV $D>V 'tnV d^V !!1!12V -.V u44 5!V  V r%rRc4^\rSrSrU4SjrU4SjrSrU=r$)SmolVLMForConditionalGenerationiYc>[TU]U5 [U5Ul[R "UR RUR RSS9Ul UR5 g)NF)r8) super__init__rRmodelrr3 text_config hidden_size vocab_sizelm_head post_init)r>r0 __class__s r&r(SmolVLMForConditionalGeneration.__init__ZsS  !&) yy!3!3!?!?ASASA^A^ejk  r%c &>[TU]"S0UD6 g)a Example: ```python >>> import requests >>> import torch >>> from PIL import Image >>> from io import BytesIO >>> from transformers import AutoProcessor, AutoModelForImageTextToText >>> from transformers.image_utils import load_image >>> # Note that passing the image urls (instead of the actual pil images) to the processor is also possible >>> image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg") >>> image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg") >>> image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg") >>> processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct") >>> model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") >>> # Create inputs >>> messages = [ ... { ... "role": "user", ... "content": [ ... {"type": "video", "path": path/to/video}, ... {"type": "text", "text": "What is happening in this video?"}, ... ] ... } ... ] >>> inputs = processor.apply_chat_template([messages], add_generation_prompt=True) >>> # Generate >>> generated_ids = model.generate(**inputs, max_new_tokens=256) >>> generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True) >>> print(generated_texts) ```Nr)rr)r> super_kwargsrs r&r'SmolVLMForConditionalGeneration.forward`sP ','r%)rr)rrr r!rrr$ __classcell__)rs@r&rrYs ((((r%r)rrHrLrr(rRrC))typingrrrrr`torch.utils.checkpointr cache_utilsr modeling_flash_attention_utilsr processing_utilsr utilsr r ridefics3.configuration_idefics3rr"idefics3.image_processing_idefics3ridefics3.modeling_idefics3rrrrr get_loggerrrrr(rCrHrLrOrRr__all__rr%r&rs 0/ 'B&>>RG   H %5 .5 p%4%" 8 ' N' T 2  %D o =o d/(&F/(d r%