# VipLlava ## Overview The VipLlava model was proposed in [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://huggingface.co/papers/2312.00784) by Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee. VipLlava enhances the training protocol of Llava by marking images and interact with the model using natural cues like a "red bounding box" or "pointed arrow" during training. The abstract from the paper is the following: *While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a "red bounding box" or "pointed arrow". Our simple design directly overlays visual markers onto the RGB image, eliminating the need for complex region encodings, yet achieves state-of-the-art performance on region-understanding tasks like Visual7W, PointQA, and Visual Commonsense Reasoning benchmark. Furthermore, we present ViP-Bench, a comprehensive benchmark to assess the capability of models in understanding visual prompts across multiple dimensions, enabling future research in this domain. Code, data, and model are publicly available.* The original code can be found [here](https://github.com/mu-cai/ViP-LLaVA). This model was contributed by [Younes Belkada](https://huggingface.co/ybelkada) ## Usage tips - The architecture is similar than llava architecture except that the multi-modal projector takes a set of concatenated vision hidden states and has an additional layernorm layer on that module. - We advise users to use `padding_side="left"` when computing batched generation as it leads to more accurate results. Simply make sure to call `processor.tokenizer.padding_side = "left"` before generating. - Note the model has not been explicitly trained to process multiple images in the same prompt, although this is technically possible, you may experience inaccurate results. > [!NOTE] > LLaVA models after release v4.46 will raise warnings about adding `processor.patch_size = {{patch_size}}`, `processor.num_additional_image_tokens = {{num_additional_image_tokens}}` and `processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. It is strongly recommended to add the attributes to the processor if you own the model checkpoint, or open a PR if it is not owned by you. Adding these attributes means that LLaVA will try to infer the number of image tokens required per image and expand the text with as many `` placeholders as there will be tokens. Usually it is around 500 tokens per image, so make sure that the text is not truncated as otherwise there will be failure when merging the embeddings. The attributes can be obtained from model config, as `model.config.vision_config.patch_size` or `model.config.vision_feature_select_strategy`. The `num_additional_image_tokens` should be `1` if the vision backbone adds a CLS token or `0` if nothing extra is added to the vision patches. - For better results, we recommend users to use the processor's `apply_chat_template()` method to format your prompt correctly. For that you need to construct a conversation history, passing in a plain string will not format your prompt. Each message in the conversation history for chat templates is a dictionary with keys "role" and "content". The "content" should be a list of dictionaries, for "text" and "image" modalities, as follows: ```python from transformers import AutoProcessor processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf") conversation = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "What’s shown in this image?"}, ], }, { "role": "assistant", "content": [{"type": "text", "text": "This image shows a red stop sign."},] }, { "role": "user", "content": [ {"type": "text", "text": "Describe the image in more details."}, ], }, ] text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True) # Note that the template simply formats your prompt, you still have to tokenize it and obtain pixel values for your images print(text_prompt) >>> "###Human: \nWhat’s shown in this image?###Assistant: This image shows a red stop sign.###Human: Describe the image in more details.###Assistant:" ``` - If you want to construct a chat prompt yourself, below is a list of prompt formats accepted by VipLLaVa checkpoints: ```bash A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: \n###Assistant: ``` For multiple turns conversation: ```bash A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: \n###Assistant: ###Human: ###Assistant: ``` ## VipLlavaConfig[[transformers.VipLlavaConfig]] #### transformers.VipLlavaConfig[[transformers.VipLlavaConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/configuration_vipllava.py#L24) This is the configuration class to store the configuration of a VipLlavaModel. It is used to instantiate a Vipllava 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 [llava-hf/vip-llava-7b-hf](https://huggingface.co/llava-hf/vip-llava-7b-hf) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.5.3/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.5.3/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import VipLlavaForConditionalGeneration, VipLlavaConfig, CLIPVisionConfig, LlamaConfig >>> # Initializing a CLIP-vision config >>> vision_config = CLIPVisionConfig() >>> # Initializing a Llama config >>> text_config = LlamaConfig() >>> # Initializing a VipLlava vipllava-7b style configuration >>> configuration = VipLlavaConfig(vision_config, text_config) >>> # Initializing a model from the vipllava-7b style configuration >>> model = VipLlavaForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vision_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the vision backbone. text_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the text backbone. image_token_index (`int`, *optional*, defaults to `32000`) : The image token index used as a placeholder for input images. projector_hidden_act (`str`, *optional*, defaults to `gelu`) : The activation function used by the multimodal projector. projector_layernorm_eps (`float`, *optional*, defaults to 1e-05) : The layer norm epsilon of the projector layernorm vision_feature_layers (`Union[int, list[int]]`, *optional*, defaults to `[-2, -5, -8, -11, 6]`) : The vision feature layer, or list of layers to select the vision features from. image_seq_length (`int`, *optional*, defaults to `576`) : Sequence length of one image embedding. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## VipLlavaModel[[transformers.VipLlavaModel]] #### transformers.VipLlavaModel[[transformers.VipLlavaModel]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L134) The VipLlava model which consists of a vision backbone and a language model, without a language modeling head. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.VipLlavaModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L213[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "vision_feature_layers", "val": ": int | list[int] | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**lm_kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [CLIPImageProcessor](/docs/transformers/v5.5.3/en/model_doc/clip#transformers.CLIPImageProcessor). See `CLIPImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/v5.5.3/en/model_doc/llava#transformers.LlavaProcessor) uses [CLIPImageProcessor](/docs/transformers/v5.5.3/en/model_doc/clip#transformers.CLIPImageProcessor) for processing images). - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **vision_feature_layers** (`Union[int, list[int]]`, *optional*) -- The vision feature layer, or the list of indexes of the layers to select the vision feature. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0`VipLlavaModelOutputWithPast` or `tuple(torch.FloatTensor)`A `VipLlavaModelOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs. The [VipLlavaModel](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). 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** (`torch.FloatTensor`, *optional*) -- A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`. image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state. **Parameters:** config ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.5.3/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``VipLlavaModelOutputWithPast` or `tuple(torch.FloatTensor)`` A `VipLlavaModelOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs. #### get_image_features[[transformers.VipLlavaModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L149) Obtains image last hidden states from the vision tower and apply multimodal projection. - **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. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. **Parameters:** pixel_values (`torch.FloatTensor]` of shape `(batch_size, channels, height, width)`) : The tensors corresponding to the input images. vision_feature_layers (`Union[int, list[int]]`, *optional*) : The vision feature layer, or the list of indexes of the layers to select the vision feature. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.5.3/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.5.3/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs. #### get_placeholder_mask[[transformers.VipLlavaModel.get_placeholder_mask]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L189) Obtains multimodal placeholder mask from `input_ids` or `inputs_embeds`, and checks that the placeholder token count is equal to the length of multimodal features. If the lengths are different, an error is raised. ## VipLlavaForConditionalGeneration[[transformers.VipLlavaForConditionalGeneration]] #### transformers.VipLlavaForConditionalGeneration[[transformers.VipLlavaForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L276) The VIPLLAVA model which consists of a vision backbone and a language model. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.VipLlavaForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L312[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "vision_feature_layers", "val": ": int | list[int] | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**lm_kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [CLIPImageProcessor](/docs/transformers/v5.5.3/en/model_doc/clip#transformers.CLIPImageProcessor). See `CLIPImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/v5.5.3/en/model_doc/llava#transformers.LlavaProcessor) uses [CLIPImageProcessor](/docs/transformers/v5.5.3/en/model_doc/clip#transformers.CLIPImageProcessor) for processing images). - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **vision_feature_layers** (`Union[int, list[int]]`, *optional*) -- The vision feature layer, or the list of indexes of the layers to select the vision feature. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). - **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) -- If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).0`VipLlavaCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`A `VipLlavaCausalLMOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs. The [VipLlavaForConditionalGeneration](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaForConditionalGeneration) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **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** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.5.3/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). 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** (`torch.FloatTensor`, *optional*) -- A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`. image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state. Example: ```python >>> import torch >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> from transformers import AutoProcessor, VipLlavaForConditionalGeneration >>> model = VipLlavaForConditionalGeneration.from_pretrained("llava-hf/vip-llava-7b-hf", device_map="auto", dtype=torch.float16) >>> processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf") >>> prompt = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: \n{}###Assistant:" >>> question = "Can you please describe this image?" >>> prompt = prompt.format(question) >>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-neg.png" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> inputs = processor(text=text, images=image, return_tensors="pt").to(0, torch.float16) >>> # Generate >>> generate_ids = model.generate(**inputs, max_new_tokens=20) >>> processor.decode(generate_ids[0][len(inputs["input_ids"][0]):], skip_special_tokens=True) The image features a brown and white cat sitting on a green surface, with a red ball in its ``` **Parameters:** config ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.5.3/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``VipLlavaCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`` A `VipLlavaCausalLMOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs. #### get_image_features[[transformers.VipLlavaForConditionalGeneration.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/vipllava/modeling_vipllava.py#L294) - **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. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. Example: ```python >>> from PIL import Image >>> from transformers import AutoProcessor, VipLlavaForConditionalGeneration >>> model = VipLlavaForConditionalGeneration.from_pretrained("llava-hf/vip-llava-7b-hf") >>> processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf") >>> messages = [ ... { ... "role": "user", "content": [ ... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"}, ... {"type": "text", "text": "Where is the cat standing?"}, ... ] ... }, ... ] >>> inputs = processor.apply_chat_template( ... messages, ... tokenize=True, ... return_dict=True, ... return_tensors="pt", ... add_generation_prompt=True ... ) >>> # Generate >>> generate_ids = model.generate(**inputs) >>> processor.batch_decode(generate_ids, skip_special_tokens=True)[0] ``` **Parameters:** pixel_values (`torch.FloatTensor]` of shape `(batch_size, channels, height, width)`) : The tensors corresponding to the input images. vision_feature_layers (`Union[int, list[int]]`, *optional*) : The vision feature layer, or the list of indexes of the layers to select the vision feature. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.5.3/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.5.3/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([VipLlavaConfig](/docs/transformers/v5.5.3/en/model_doc/vipllava#transformers.VipLlavaConfig)) and inputs.