# LLaVa ## Overview LLaVa is an open-source chatbot trained by fine-tuning LlamA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. In other words, it is an multi-modal version of LLMs fine-tuned for chat / instructions. The LLaVa model was proposed in [Visual Instruction Tuning](https://huggingface.co/papers/2304.08485) and improved in [Improved Baselines with Visual Instruction Tuning](https://huggingface.co/papers/2310.03744) by Haotian Liu, Chunyuan Li, Yuheng Li and Yong Jae Lee. The abstract from the paper is the following: *Large multimodal models (LMM) have recently shown encouraging progress with visual instruction tuning. In this note, we show that the fully-connected vision-language cross-modal connector in LLaVA is surprisingly powerful and data-efficient. With simple modifications to LLaVA, namely, using CLIP-ViT-L-336px with an MLP projection and adding academic-task-oriented VQA data with simple response formatting prompts, we establish stronger baselines that achieve state-of-the-art across 11 benchmarks. Our final 13B checkpoint uses merely 1.2M publicly available data, and finishes full training in โˆผ1 day on a single 8-A100 node. We hope this can make state-of-the-art LMM research more accessible. Code and model will be publicly available* drawing LLaVa architecture. Taken from the original paper. This model was contributed by [ArthurZ](https://huggingface.co/ArthurZ) and [ybelkada](https://huggingface.co/ybelkada). The original code can be found [here](https://github.com/haotian-liu/LLaVA/tree/main/llava). ## Usage tips - 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. ### Formatting Prompts with Chat Templates Each **checkpoint** is trained with a specific prompt format, depending on the underlying large language model backbone. To ensure correct formatting, use the processor's `apply_chat_template` method. **Important:** - You must construct a conversation history โ€” passing a plain string won't work. - Each message should be a dictionary with `"role"` and `"content"` keys. - The `"content"` should be a list of dictionaries for different modalities like `"text"` and `"image"`. Here's an example of how to structure your input. We will use [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) and a conversation history of text and image. Each content field has to be a list of dicts, as follows: ```python from transformers import AutoProcessor processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf") conversation = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "Whatโ€™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) "USER: \nUSER: 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 each llava checkpoint: [llava-interleave models](https://huggingface.co/collections/llava-hf/llava-interleave-668e19a97da0036aad4a2f19) requires the following format: ```bash "<|im_start|>user \nWhat is shown in this image?<|im_end|><|im_start|>assistant" ``` For multiple turns conversation: ```bash "<|im_start|>user \n<|im_end|><|im_start|>assistant <|im_end|><|im_start|>user \n<|im_end|><|im_start|>assistant " ``` [llava-1.5 models](https://huggingface.co/collections/llava-hf/llava-15-65f762d5b6941db5c2ba07e0) requires the following format: ```bash "USER: \n ASSISTANT:" ``` For multiple turns conversation: ```bash "USER: \n ASSISTANT: USER: ASSISTANT: USER: ASSISTANT:" ``` ๐Ÿš€ **Bonus:** If you're using `transformers>=4.49.0`, you can also get a vectorized output from `apply_chat_template`. See the **Usage Examples** below for more details on how to use it. ## Usage examples ### Single input inference ```python import torch from transformers import AutoProcessor, LlavaForConditionalGeneration # Load the model in half-precision model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf", device_map="auto") processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf") conversation = [ { "role": "user", "content": [ {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}, {"type": "text", "text": "What is shown in this image?"}, ], }, ] inputs = processor.apply_chat_template( conversation, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device, torch.float16) # Generate generate_ids = model.generate(**inputs, max_new_tokens=30) processor.batch_decode(generate_ids, skip_special_tokens=True) ``` ### Batched inference LLaVa also supports batched inference. Here is how you can do it: ```python import torch from transformers import AutoProcessor, LlavaForConditionalGeneration # Load the model in half-precision model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf", device_map="auto") processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf") # Prepare a batch of two prompts conversation_1 = [ { "role": "user", "content": [ {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}, {"type": "text", "text": "What is shown in this image?"}, ], }, ] conversation_2 = [ { "role": "user", "content": [ {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"}, {"type": "text", "text": "What is shown in this image?"}, ], }, ] inputs = processor.apply_chat_template( [conversation_1, conversation_2], add_generation_prompt=True, tokenize=True, return_dict=True, padding=True, return_tensors="pt" ).to(model.device, torch.float16) # Generate generate_ids = model.generate(**inputs, max_new_tokens=30) processor.batch_decode(generate_ids, skip_special_tokens=True) ``` ## Note regarding reproducing original implementation In order to match the logits of the [original implementation](https://github.com/haotian-liu/LLaVA/tree/main), one needs to additionally specify `do_pad=True` when instantiating `LlavaImageProcessor`: ```python from transformers import LlavaImageProcessor image_processor = LlavaImageProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf", do_pad=True) ``` ### Using Flash Attention 2 Flash Attention 2 is an even faster, optimized version of the previous optimization, please refer to the [Flash Attention 2 section of performance docs](https://huggingface.co/docs/transformers/perf_infer_gpu_one). ## Resources A list of official Hugging Face and community (indicated by ๐ŸŒŽ) resources to help you get started with BEiT. - A [Google Colab demo](https://colab.research.google.com/drive/1qsl6cd2c8gGtEW1xV5io7S8NHh-Cp1TV?usp=sharing) on how to run Llava on a free-tier Google colab instance leveraging 4-bit inference. - A [similar notebook](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/LLaVa/Inference_with_LLaVa_for_multimodal_generation.ipynb) showcasing batched inference. ๐ŸŒŽ ## LlavaConfig[[transformers.LlavaConfig]] #### transformers.LlavaConfig[[transformers.LlavaConfig]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/configuration_llava.py#L26) This is the configuration class to store the configuration of a LlavaModel. It is used to instantiate a Llava 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/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import LlavaForConditionalGeneration, LlavaConfig, CLIPVisionConfig, LlamaConfig >>> # Initializing a CLIP-vision config >>> vision_config = CLIPVisionConfig() >>> # Initializing a Llama config >>> text_config = LlamaConfig() >>> # Initializing a Llava llava-1.5-7b style configuration >>> configuration = LlavaConfig(vision_config, text_config) >>> # Initializing a model from the llava-1.5-7b style configuration >>> model = LlavaForConditionalGeneration(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. image_seq_length (`int`, *optional*, defaults to `576`) : Sequence length of one image embedding. projector_hidden_act (`str`, *optional*, defaults to `gelu`) : The activation function used by the multimodal projector. vision_feature_select_strategy (`Literal[default, full]`, *optional*, defaults to `default`) : The feature selection strategy used to select the vision feature from the vision backbone. vision_feature_layer (`Union[int, list[int]]`, *optional*, defaults to `-2`) : The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. multimodal_projector_bias (`bool`, *optional*, defaults to `True`) : Whether to use bias in the multimodal projector. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## LlavaImageProcessor[[transformers.LlavaImageProcessor]] #### transformers.LlavaImageProcessor[[transformers.LlavaImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/image_processing_llava.py#L38) Constructs a LlavaImageProcessor image processor. preprocesstransformers.LlavaImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **return_tensors** (`str` or [TensorType](/docs/transformers/main/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/main/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** - ****kwargs** ([ImagesKwargs](/docs/transformers/main/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## LlavaImageProcessorPil[[transformers.LlavaImageProcessorPil]] #### transformers.LlavaImageProcessorPil[[transformers.LlavaImageProcessorPil]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/image_processing_pil_llava.py#L31) Constructs a LlavaImageProcessor image processor. preprocesstransformers.LlavaImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **return_tensors** (`str` or [TensorType](/docs/transformers/main/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/main/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** - ****kwargs** ([ImagesKwargs](/docs/transformers/main/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## LlavaProcessor[[transformers.LlavaProcessor]] #### transformers.LlavaProcessor[[transformers.LlavaProcessor]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/processing_llava.py#L40) Constructs a LlavaProcessor which wraps a image processor and a tokenizer into a single processor. [LlavaProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaProcessor) offers all the functionalities of [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) and [TokenizersBackend](/docs/transformers/main/en/main_classes/tokenizer#transformers.TokenizersBackend). See the [~LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) and [~TokenizersBackend](/docs/transformers/main/en/main_classes/tokenizer#transformers.TokenizersBackend) for more information. __call__transformers.LlavaProcessor.__call__https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/processing_llava.py#L71[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | list[list[str]] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.llava.processing_llava.LlavaProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`, *optional*) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **text** (`Union[str, list[str], list[list[str]]]`, *optional*) -- The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If you pass a pretokenized input, set `is_split_into_words=True` to avoid ambiguity with batched inputs. - **return_tensors** (`str` or [TensorType](/docs/transformers/main/en/internal/file_utils#transformers.TensorType), *optional*) -- If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - ****kwargs** ([ProcessingKwargs](/docs/transformers/main/en/main_classes/processors#transformers.ProcessingKwargs), *optional*) -- Additional processing options for each modality (text, images, videos, audio). Model-specific parameters are listed above; see the TypedDict class for the complete list of supported arguments.0[BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature)A [BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature) with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. **Parameters:** image_processor (`LlavaImageProcessor`) : The image processor is a required input. tokenizer (`TokenizersBackend`) : The tokenizer is a required input. patch_size (`int`, *optional*) : Patch size from the vision tower. vision_feature_select_strategy (`str`, *optional*) : The feature selection strategy used to select the vision feature from the vision backbone. Should be same as in model's config chat_template (`str`) : A Jinja template to convert lists of messages in a chat into a tokenizable string. image_token (`str`, *optional*, defaults to `""`) : Special token used to denote image location. num_additional_image_tokens (`int`, *optional*, defaults to 0) : Number of additional tokens added to the image embeddings, such as CLS (+1). If the backbone has no CLS or other extra tokens appended, no need to set this arg. **Returns:** `[BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature)` A [BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature) with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. ## LlavaModel[[transformers.LlavaModel]] #### transformers.LlavaModel[[transformers.LlavaModel]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L130) The Llava model which consists of a vision backbone and a language model, without a language modeling head. This model inherits from [PreTrainedModel](/docs/transformers/main/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.LlavaModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L221[{"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_layer", "val": ": int | list[int] | None = None"}, {"name": "vision_feature_select_strategy", "val": ": str | None = None"}, {"name": "image_sizes", "val": ": torch.Tensor | None = None"}, {"name": "**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/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/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 [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor). See `LlavaImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaProcessor) uses [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) 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/main/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/main/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_layer** (`Union[int, list[int]]`, *optional*) -- The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. - **vision_feature_select_strategy** (`str`, *optional*) -- The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. - **image_sizes** (`torch.Tensor` of shape `(batch_size, 2)`, *optional*) -- The sizes of the images in the batch, being (height, width) for each image.0`LlavaModelOutputWithPast` or `tuple(torch.FloatTensor)`A `LlavaModelOutputWithPast` 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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs. The [LlavaModel](/docs/transformers/main/en/model_doc/llava#transformers.LlavaModel) 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/main/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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``LlavaModelOutputWithPast` or `tuple(torch.FloatTensor)`` A `LlavaModelOutputWithPast` 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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs. #### get_image_features[[transformers.LlavaModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L145) 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, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. Pixel values can be obtained using [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor). See `LlavaImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaProcessor) uses [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) for processing images). vision_feature_layer (`Union[int, list[int]]`, *optional*) : The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. vision_feature_select_strategy (`str`, *optional*) : The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. output_hidden_states (`bool`, *optional*) : Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs. #### get_placeholder_mask[[transformers.LlavaModel.get_placeholder_mask]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L197) 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. ## LlavaForConditionalGeneration[[transformers.LlavaForConditionalGeneration]] #### transformers.LlavaForConditionalGeneration[[transformers.LlavaForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L278) The LLAVA model which consists of a vision backbone and a language model. This model inherits from [PreTrainedModel](/docs/transformers/main/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.LlavaForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L311[{"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_layer", "val": ": int | list[int] | None = None"}, {"name": "vision_feature_select_strategy", "val": ": str | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "image_sizes", "val": ": torch.Tensor | None = None"}, {"name": "**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/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/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 [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor). See `LlavaImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaProcessor) uses [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) 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/main/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/main/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_layer** (`Union[int, list[int]]`, *optional*) -- The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. - **vision_feature_select_strategy** (`str`, *optional*) -- The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. - **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]`. - **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). - **image_sizes** (`torch.Tensor` of shape `(batch_size, 2)`, *optional*) -- The sizes of the images in the batch, being (height, width) for each image.0`LlavaCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`A `LlavaCausalLMOutputWithPast` 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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs. The [LlavaForConditionalGeneration](/docs/transformers/main/en/model_doc/llava#transformers.LlavaForConditionalGeneration) 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/main/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 >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> from transformers import AutoProcessor, LlavaForConditionalGeneration >>> model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf") >>> processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf") >>> prompt = "USER: \nWhat's the content of the image? ASSISTANT:" >>> url = "https://www.ilankelman.org/stopsigns/australia.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> inputs = processor(images=image, text=prompt, return_tensors="pt") >>> # Generate >>> generate_ids = model.generate(**inputs, max_new_tokens=15) >>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] "USER: \nWhat's the content of the image? ASSISTANT: The image features a busy city street with a stop sign prominently displayed" ``` **Parameters:** config ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``LlavaCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`` A `LlavaCausalLMOutputWithPast` 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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs. #### get_image_features[[transformers.LlavaForConditionalGeneration.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py#L296) - **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, LlavaForConditionalGeneration >>> model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf") >>> processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-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, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. Pixel values can be obtained using [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor). See `LlavaImageProcessor.__call__()` for details ([LlavaProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaProcessor) uses [LlavaImageProcessor](/docs/transformers/main/en/model_doc/llava#transformers.LlavaImageProcessor) for processing images). vision_feature_layer (`Union[int, list[int]]`, *optional*) : The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. vision_feature_select_strategy (`str`, *optional*) : The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([LlavaConfig](/docs/transformers/main/en/model_doc/llava#transformers.LlavaConfig)) and inputs.