Hugging Face's logo

Transformers documentation

LLaVA-OneVision

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.46.3).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

LLaVA-OneVision

Overview

The LLaVA-OneVision model was proposed in LLaVA-OneVision: Easy Visual Task Transfer by <Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li

LLaVA-OneVision is a Vision-Language Model that can generate text conditioned on one or several images/videos. The model consists of SigLIP vision encoder and a Qwen2 language backbone. The images are processed with anyres-9 technique where the image is split into 9 patches to better process high resolution images and capture as much details as possible. However, videos are pooled to a total sequence length of 196 tokens each frame for more memory efficient computation. LLaVA-OneVision is available in three sizes: 0.5B, 7B and 72B and achieves remarkable performance on benchmark evaluations.

The abstract from the paper is the following:

We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results demonstrate that LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVAOneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos.

drawing LLaVA-OneVision architecture. Taken from the original paper.

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.
  • Llava-OneVision uses different number of patches for images and thus has to pad the inputs inside modeling code, aside from the padding done when processing the inputs. The default setting is “left-padding” if model is in eval() mode, otherwise “right-padding”.
  • Note that the model should use a specific prompt format, on which the large language model (LLM) was trained. You can use the processor’s apply_chat_template to format your prompts correctly. For that you have to construct a conversation history, passing 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.

We will use llava-onevision-qwen2-7b-si-hf and a conversation history of text and image. Each content field has to be a list of dicts, as follows:

from transformers import AutoProcessor

processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-si-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)
>>> "<|im_start|>user\n<image>What is shown in this image?<|im_end|>\n<|im_start|>assistant\nPage showing the list of options.<|im_end|>"

This model was contributed by RaushanTurganbay. The original code can be found here.

Usage example

Single image inference

Here’s how to load the model and perform inference in half-precision (torch.float16):

from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
import torch
from PIL import Image
import requests

processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf") 
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, low_cpu_mem_usage=True) 
model.to("cuda:0")

# prepare image and text prompt, using the appropriate prompt template
url = "https://github.com/haotian-liu/LLaVA/blob/1a91fc274d7c35a9b50b3cb29c4247ae5837ce39/images/llava_v1_5_radar.jpg?raw=true"
image = Image.open(requests.get(url, stream=True).raw)

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt").to("cuda:0", torch.float16)

# autoregressively complete prompt
output = model.generate(**inputs, max_new_tokens=100)
print(processor.decode(output[0], skip_special_tokens=True))
'user\n\nWhat is shown in this image?\nassistant\nThe image shows a radar chart, also known as a spider chart or a star chart, which is used to compare multiple quantitative variables. Each axis represents a different variable, and the chart is filled with'

Multi image inference

LLaVa-OneVision can perform inference with multiple images as input, where images either belong to the same prompt or different prompts (in batched inference). For that you have to use checkpoints with an “ov” suffix. Here is how you can do it:

import requests
from PIL import Image
import torch
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

# Load the model in half-precision
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf")

# Get three different images
url = "https://www.ilankelman.org/stopsigns/australia.jpg"
image_stop = Image.open(requests.get(url, stream=True).raw)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image_cats = Image.open(requests.get(url, stream=True).raw)

url = "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"
image_snowman = Image.open(requests.get(url, stream=True).raw)

# Prepare a batch of two prompts, where the first one is a multi-turn conversation and the second is not
conversation_1 = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
            ],
    },
    {
        "role": "assistant",
        "content": [
            {"type": "text", "text": "There is a red stop sign in the image."},
            ],
    },
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What about this image? How many cats do you see?"},
            ],
    },
]

conversation_2 = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
            ],
    },
]

prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)
prompts = [prompt_1, prompt_2]

# We can simply feed images in the order they have to be used in the text prompt
inputs = processor(images=[image_stop, image_cats, image_snowman], text=prompts, 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, clean_up_tokenization_spaces=False)
['user\n\nWhat is shown in this image?\nassistant\nThere is a red stop sign in the image.\nuser\n\nWhat about this image? How many cats do you see?\nassistant\ntwo', 'user\n\nWhat is shown in this image?\nassistant\n']

Video inference

LLaVa-OneVision also can perform inference with videos as input, where video frames are treated as multiple images. Here is how you can do it:

import av
import numpy as np
from huggingface_hub import hf_hub_download

import torch
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

# Load the model in half-precision
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf")


def read_video_pyav(container, indices):
    '''
    Decode the video with PyAV decoder.
    Args:
        container (`av.container.input.InputContainer`): PyAV container.
        indices (`List[int]`): List of frame indices to decode.
    Returns:
        result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
    '''
    frames = []
    container.seek(0)
    start_index = indices[0]
    end_index = indices[-1]
    for i, frame in enumerate(container.decode(video=0)):
        if i > end_index:
            break
        if i >= start_index and i in indices:
            frames.append(frame)
    return np.stack([x.to_ndarray(format="rgb24") for x in frames])

# Load the video as an np.array, sampling uniformly 8 frames (can sample more for longer videos, up to 32 frames)
video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
container = av.open(video_path)
total_frames = container.streams.video[0].frames
indices = np.arange(0, total_frames, total_frames / 8).astype(int)
video = read_video_pyav(container, indices)

# For videos we have to feed a "video" type instead of "image"
conversation = [
    {

        "role": "user",
        "content": [
            {"type": "video"},
            {"type": "text", "text": "Why is this video funny?"},
            ],
    },
]

prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
inputs = processor(videos=list(video), text=prompt, return_tensors="pt").to("cuda:0", torch.float16)

out = model.generate(**inputs, max_new_tokens=60)
processor.batch_decode(out, skip_special_tokens=True, clean_up_tokenization_spaces=True)
["user\n\nWhy is this video funny?\nassistant\nThe video appears to be humorous because it shows a young child, who is wearing glasses and holding a book, seemingly reading with a serious and focused expression. The child's glasses are a bit oversized for their face, which adds a comical touch, as it's a common trope to see children wearing"]

Model optimization

Quantization using bitsandbytes

The model can be loaded in 8 or 4 bits, greatly reducing the memory requirements while maintaining the performance of the original model. First make sure to install bitsandbytes, pip install bitsandbytes and make sure to have access to a GPU/accelerator that is supported by the library.

bitsandbytes is being refactored to support multiple backends beyond CUDA. Currently, ROCm (AMD GPU) and Intel CPU implementations are mature, with Intel XPU in progress and Apple Silicon support expected by Q4/Q1. For installation instructions and the latest backend updates, visit this link.

We value your feedback to help identify bugs before the full release! Check out these docs for more details and feedback links.

Simply change the snippet above with:

from transformers import LlavaOnevisionForConditionalGeneration, BitsAndBytesConfig

# specify how to quantize the model
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

model = LlavaOnevisionForConditionalGeneration.from_pretrained(model_id, quantization_config=quantization_config, device_map="auto")

Use Flash-Attention 2 to further speed-up generation

First make sure to install flash-attn. Refer to the original repository of Flash Attention regarding that package installation. Simply change the snippet above with:

from transformers import LlavaOnevisionForConditionalGeneration

model = LlavaOnevisionForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
    use_flash_attention_2=True
).to(0)

LlavaOnevisionConfig

class transformers.LlavaOnevisionConfig

< >

( vision_config = None text_config = None image_token_index = 151646 video_token_index = 151647 projector_hidden_act = 'gelu' vision_feature_select_strategy = 'full' vision_feature_layer = -1 vision_aspect_ratio = 'anyres_max_9' image_grid_pinpoints = None tie_word_embeddings = False **kwargs )

Parameters

  • vision_config (Union[AutoConfig, dict], optional, defaults to SiglipVisionConfig) — The config object or dictionary of the vision backbone.
  • text_config (Union[AutoConfig, dict], optional, defaults to Qwen2Config) — The config object or dictionary of the text backbone.
  • image_token_index (int, optional, defaults to 151646) — The image token index to encode the image prompt.
  • video_token_index (int, optional, defaults to 151647) — The video token index to encode the video prompt.
  • projector_hidden_act (str, optional, defaults to "gelu") — The activation function used by the multimodal projector.
  • vision_feature_select_strategy (str, optional, defaults to "full") — The feature selection strategy used to select the vision feature from the vision backbone. Can be one of "default" or "full". If "default", the CLS token is removed from the vision features. If "full", the full vision features are used.
  • vision_feature_layer (int, optional, defaults to -1) — The index of the layer to select the vision feature.
  • vision_aspect_ratio (str, optional, defaults to "anyres_max_9") — Aspect ratio used when processong image features. The default value is “anyres_max_9”.
  • image_grid_pinpoints (List, optional) — A list of possible resolutions to use for processing high resolution images. Each item in the list should be a tuple or list of the form (height, width).
  • tie_word_embeddings (bool, optional, defaults to False) — Whether the model’s input and output word embeddings should be tied.

This is the configuration class to store the configuration of a LlavaOnevisionForConditionalGeneration. It is used to instantiate an Llava-NeXT 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-onevision-qwen2-7b-ov-hf model.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import LlavaOnevisionForConditionalGeneration, LlavaOnevisionConfig, SiglipVisionConfig, Qwen2Config

>>> # Initializing a CLIP-vision config
>>> vision_config = SiglipVisionConfig()

>>> # Initializing a Llama config
>>> text_config = Qwen2Config()

>>> # Initializing a Llava-Next llava-hf/llava-onevision-qwen2-7b-ov-hf style configuration
>>> configuration = LlavaOnevisionConfig(vision_config, text_config)

>>> # Initializing a model from the llava-hf/llava-onevision-qwen2-7b-ov-hf style configuration
>>> model = LlavaOnevisionForConditionalGeneration(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

LlavaOnevisionProcessor

class transformers.LlavaOnevisionProcessor

< >

( image_processor = None tokenizer = None video_processor = None num_image_tokens = None vision_feature_select_strategy = None chat_template = None image_token = '<image>' video_token = '<video>' **kwargs )

Parameters

  • image_processor (LlavaOnevisionImageProcessor, optional) — The image processor is a required input.
  • tokenizer (LlamaTokenizerFast, optional) — The tokenizer is a required input.
  • video_processor (LlavaOnevisionVideoProcessor, optional) — The video processor is a required input.
  • num_image_tokens (int, optional) — Number of image tokens for one imagethat will be returned by vision tower.
  • vision_feature_select_strategy (str, optional) — The feature selection strategy used to select the vision feature from the vision backbone. Shoudl be same as in model’s config
  • chat_template (str, optional) — A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string.
  • image_token (str, optional, defaults to "<image>") — Special token used to denote image location.
  • video_token (str, optional, defaults to "<video>") — Special token used to denote video location.

Constructs a LLaVa-Onevision processor which wraps a LLaVa-Onevision video processor, LLaVa-NeXT image processor and a LLaMa tokenizer into a single processor.

LlavaNextProcessor offers all the functionalities of LlavaOnevisionVideoProcessor, LlavaOnevisionImageProcessor and LlamaTokenizerFast. See the call(), __call__() and decode() for more information.

batch_decode

< >

( *args **kwargs )

This method forwards all its arguments to LlamaTokenizerFast’s batch_decode(). Please refer to the docstring of this method for more information.

decode

< >

( *args **kwargs )

This method forwards all its arguments to LlamaTokenizerFast’s decode(). Please refer to the docstring of this method for more information.

LlavaOnevisionImageProcessor

class transformers.LlavaOnevisionImageProcessor

< >

( do_resize: bool = True size: typing.Dict[str, int] = None image_grid_pinpoints: typing.List = None resample: Resampling = <Resampling.BICUBIC: 3> do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: typing.Optional[bool] = True do_convert_rgb: bool = True **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions to the specified size. Can be overridden by do_resize in the preprocess method.
  • size (Dict[str, int] optional, defaults to {"shortest_edge" -- 224}): Size of the image after resizing. The shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio. Can be overridden by size in the preprocess method.
  • image_grid_pinpoints (List optional, defaults to [[672, 336], [336, 672], [672, 672], [336, 1008], [1008, 336]]) — A list of possible resolutions to use for processing high resolution images. The best resolution is selected based on the original size of the image. Can be overridden by image_grid_pinpoints in the preprocess method. Not used for processinf videos.
  • resample (PILImageResampling, optional, defaults to Resampling.BICUBIC) — Resampling filter to use if resizing the image. Can be overridden by resample in the preprocess method.
  • do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. Can be overridden by do_rescale in the preprocess method.
  • rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. Can be overridden by rescale_factor in the preprocess method.
  • do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by do_normalize in the preprocess method.
  • image_mean (float or List[float], optional, defaults to [0.48145466, 0.4578275, 0.40821073]) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method.
  • image_std (float or List[float], optional, defaults to [0.26862954, 0.26130258, 0.27577711]) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method.
  • do_pad (bool, optional, defaults to True) — Whether to pad the image. If True, will pad the patch dimension of the images in the batch to the largest number of patches in the batch. Padding will be applied to the bottom and right with zeros.
  • do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB.

Constructs a LLaVa-Onevisino-Video video processor. Based on SiglipImageProcessor with incorporation of processing each video frame.

get_image_patches

< >

( image: <built-in function array> grid_pinpoints size: tuple patch_size: int resample: Resampling data_format: ChannelDimension input_data_format: ChannelDimension ) → List[np.array]

Parameters

  • image (np.array) — The input image to be processed.
  • grid_pinpoints (List) — A string representation of a list of possible resolutions.
  • size (tuple) — Size to resize the original image to.
  • patch_size (int) — Size of the patches to divide the image into.
  • resample (PILImageResampling) — Resampling filter to use if resizing the image.
  • data_format (ChannelDimension or str) — The channel dimension format for the output image.
  • input_data_format (ChannelDimension or str) — The channel dimension format of the input image.

Returns

List[np.array]

A list of NumPy arrays containing the processed image patches.

Process an image with variable resolutions by dividing it into patches.

pad

< >

( image: ndarray padding: typing.Union[int, typing.Tuple[int, int], typing.Iterable[typing.Tuple[int, int]]] mode: PaddingMode = <PaddingMode.CONSTANT: 'constant'> constant_values: typing.Union[float, typing.Iterable[float]] = 0.0 data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None ) → np.ndarray

Parameters

  • image (np.ndarray) — The image to pad.
  • padding (int or Tuple[int, int] or Iterable[Tuple[int, int]]) — Padding to apply to the edges of the height, width axes. Can be one of three formats:
    • ((before_height, after_height), (before_width, after_width)) unique pad widths for each axis.
    • ((before, after),) yields same before and after pad for height and width.
    • (pad,) or int is a shortcut for before = after = pad width for all axes.
  • mode (PaddingMode) — The padding mode to use. Can be one of:
    • "constant": pads with a constant value.
    • "reflect": pads with the reflection of the vector mirrored on the first and last values of the vector along each axis.
    • "replicate": pads with the replication of the last value on the edge of the array along each axis.
    • "symmetric": pads with the reflection of the vector mirrored along the edge of the array.
  • constant_values (float or Iterable[float], optional) — The value to use for the padding if mode is "constant".
  • data_format (str or ChannelDimension, optional) — The channel dimension format for the output image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format. If unset, will use same as the input image.
  • input_data_format (str or ChannelDimension, optional) — The channel dimension format for the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format. If unset, will use the inferred format of the input image.

Returns

np.ndarray

The padded image.

Pads the image with the specified padding and mode. Padding can be in the (height, width) dimension of in the (num_patches) dimension. In the second case an iterable if tuples is expected as input.

preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] do_resize: bool = None size: typing.Dict[str, int] = None image_grid_pinpoints: typing.List = None resample: Resampling = None do_rescale: bool = None rescale_factor: float = None do_normalize: bool = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: typing.Optional[bool] = None do_convert_rgb: bool = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: typing.Optional[transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None )

Parameters

  • images (PIL.Image.Image, np.ndarray, torch.Tensor, List[PIL.Image.Image], List[np.ndarray], List[torch.Tensor]) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported.
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (Dict[str, int], optional, defaults to self.size) — Size of the image after resizing. Shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio.
  • image_grid_pinpoints (List optional, defaults to self.image_grid_pinpoints) — A list of possible resolutions to use for processing high resolution images. The best resolution is selected based on the original size of the image.
  • resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling. Only has an effect if do_resize is set to True.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image.
  • rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
  • do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
  • image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean to use for normalization. Only has an effect if do_normalize is set to True.
  • image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True.
  • do_pad (bool, optional, defaults to self.do_pad) — Whether to pad the image. If True, will pad the patch dimension of the images in the batch to the largest number of patches in the batch. Padding will be applied to the bottom and right with zeros.
  • do_convert_rgb (bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB.
  • return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
    • Unset: Return a list of np.ndarray.
    • TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
    • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
    • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
    • TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
  • data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • Unset: Use the channel dimension format of the input image.
  • input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • "none" or ChannelDimension.NONE: image in (height, width) format.

LlavaOnevisionVideoProcessor

class transformers.LlavaOnevisionVideoProcessor

< >

( do_resize: bool = True size: typing.Dict[str, int] = None resample: Resampling = <Resampling.BICUBIC: 3> do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_convert_rgb: bool = True **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions to the specified size. Can be overridden by do_resize in the preprocess method.
  • size (Dict[str, int] optional, defaults to {"shortest_edge" -- 224}): Size of the image after resizing. The shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio. Can be overridden by size in the preprocess method.
  • resample (PILImageResampling, optional, defaults to Resampling.BICUBIC) — Resampling filter to use if resizing the image. Can be overridden by resample in the preprocess method.
  • do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. Can be overridden by do_rescale in the preprocess method.
  • rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. Can be overridden by rescale_factor in the preprocess method.
  • do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by do_normalize in the preprocess method.
  • image_mean (float or List[float], optional, defaults to [0.48145466, 0.4578275, 0.40821073]) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method.
  • image_std (float or List[float], optional, defaults to [0.26862954, 0.26130258, 0.27577711]) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method.
  • do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB.

Constructs a LLaVa-Onevisino-Video video processor. Based on SiglipImageProcessor with incorporation of processing each video frame.

preprocess

< >

( videos: typing.Union[typing.List[ForwardRef('PIL.Image.Image')], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), typing.List[ForwardRef('np.ndarray')], typing.List[ForwardRef('torch.Tensor')], typing.List[typing.List[ForwardRef('PIL.Image.Image')]], typing.List[typing.List[ForwardRef('np.ndarrray')]], typing.List[typing.List[ForwardRef('torch.Tensor')]]] do_resize: bool = None size: typing.Dict[str, int] = None resample: Resampling = None do_rescale: bool = None rescale_factor: float = None do_normalize: bool = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_convert_rgb: bool = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: typing.Optional[transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None )

Parameters

  • videos (np.ndarray, torch.Tensor, List[np.ndarray], List[torch.Tensor]) — The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (Dict[str, int], optional, defaults to self.size) — Size of the image after resizing. Shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio.
  • resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling. Only has an effect if do_resize is set to True.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image.
  • rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
  • do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
  • image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean to use for normalization. Only has an effect if do_normalize is set to True.
  • image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True.
  • do_convert_rgb (bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB.
  • return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
    • Unset: Return a list of np.ndarray.
    • TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
    • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
    • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
    • TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
  • data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • Unset: Use the channel dimension format of the input image.
  • input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • "none" or ChannelDimension.NONE: image in (height, width) format.

LlavaOnevisionForConditionalGeneration

class transformers.LlavaOnevisionForConditionalGeneration

< >

( config: LlavaOnevisionConfig )

Parameters

  • config (LlavaNextConfig or LlavaNextVisionConfig) — 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() method to load the model weights.

The LLaVA-Onevision model which consists of a vision backbone and a language model. This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: LongTensor = None pixel_values: FloatTensor = None image_sizes: typing.Optional[torch.LongTensor] = None pixel_values_videos: FloatTensor = None image_sizes_videos: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None vision_feature_layer: typing.Optional[int] = None vision_feature_select_strategy: typing.Optional[str] = None vision_aspect_ratio: typing.Optional[str] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None num_logits_to_keep: int = 0 )

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • 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 AutoImageProcessor. See LlavaNextImageProcessor.call() for details. LlavaProcessor uses LlavaNextImageProcessor for processing images.
  • image_sizes (torch.LongTensor of shape (batch_size, 2), optional) — The sizes of the images in the batch, being (height, width) for each image.
  • pixel_values_videos (torch.FloatTensor of shape (batch_size, frames, num_channels, image_size, image_size)) -- The tensors corresponding to the input videos. Pixel values can be obtained using [LlavaNextVideoProcessor](/docs/transformers/main/en/model_doc/llava_next_video#transformers.LlavaNextVideoProcessor). See LlavaNextVideoProcessor.call()` for details. LlavaProcessor uses LlavaNextVideoProcessor for processing videos.
  • image_sizes_videos (torch.LongTensor of shape (batch_size, frames, 2), optional) — The sizes of the videos in the batch, being (height, width) for each frame in the video.
  • 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?

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

    If you want to change padding behavior, you should read modeling_opt._prepare_decoder_attention_mask and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

    • 1 indicates the head is not masked,
    • 0 indicates the head is masked.
  • 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?
  • past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

    Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

    If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_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 (int, optional, defaults to -2) — The index of the layer to select the vision feature.
  • vision_feature_select_strategy (str, optional, defaults to "default") — The feature selection strategy used to select the vision feature from the vision backbone. Can be one of "default" or "full". If "default", the CLS token is removed from the vision features. If "full", the full vision features are used.
  • vision_aspect_ratio (str, optional, defaults to "anyres_max_9") — Aspect ratio used when processong image features. The default value is “anyres_max_9”.
  • 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).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • 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.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.

    Args — 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].

    num_logits_to_keep (int, optional): Calculate logits for the last num_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.

Example:

>>> from PIL import Image
>>> import requests
>>> import torch
>>> from transformers import LlavaOnevisionProcessor, LlavaOnevisionForConditionalGeneration

>>> model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype="float16", device_map="cuda:0")
>>> processor = LlavaOnevisionProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf")

>>> conversation = [
...     {
...       "role": "user",
...       "content": [
...           {"type": "text", "text": "What is shown in this image?"},
...           {"type": "image"},
...         ],
...     },
... ]
>>> prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

>>> image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> raw_image = Image.open(requests.get(image_file, stream=True).raw)
>>> inputs = processor(text=prompt, images=raw_image, return_tensors='pt').to(0, torch.float16)

>>> output = model.generate(**inputs, max_new_tokens=20, do_sample=False)
>>> processor.batch_decode(output, skip_special_tokens=True)[0]
"user\n\nWhat is shown in this image?\nassistant\ncat"
< > Update on GitHub

←LLaVa-NeXT-Video LXMERT→