Transformers documentation

Qwen2-VL

Transformers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.56.2).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Qwen2-VL

Overview

Qwen2-VL 모델은 알리바바 리서치의 Qwen팀에서 개발한 Qwen-VL 모델의 주요 업데이트 버전입니다.

블로그의 요약은 다음과 같습니다:

이 블로그는 지난 몇 년간 Qwen-VL에서 중대한 개선을 거쳐 발전된 Qwen2-VL 모델을 소개합니다. 중요 개선 사항은 향상된 이미지 이해, 고급 비디오 이해, 통합 시각 에이전트 기능, 확장된 다언어 지원을 포함하고 있습니다.모델 아키텍처는 Naive Dynamic Resolution 지원을 통해 임의의 이미지 해상도를 처리할 수 있도록 최적화되었으며, 멀티모달 회전 위치 임베딩(M-ROPE)을 활용하여 1D 텍스트와 다차원 시각 데이터를 효과적으로 처리합니다. 이 업데이트된 모델은 시각 관련 작업에서 GPT-4o와 Claude 3.5 Sonnet 같은 선도적인 AI 시스템과 경쟁력 있는 성능을 보여주며, 텍스트 능력에서는 오픈소스 모델 중 상위권에 랭크되어 있습니다. 이러한 발전은 Qwen2-VL을 강력한 멀티모달 처리 및 추론 능력이 필요한 다양한 응용 분야에서 활용할 수 있는 다재다능한 도구로 만들어줍니다.

Qwen2-VL 구조. 출처: 블로그 게시글

이 모델은 simonJJJ에 의해 기여되었습니다.

사용 예시

단일 미디어 추론

이 모델은 이미지와 비디오를 모두 인풋으로 받을 수 있습니다. 다음은 추론을 위한 예제 코드입니다.


import torch
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor

# 사용 가능한 장치에서 모델을 반 정밀도(half-precision)로 로드
model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", device_map="auto")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")


conversation = [
    {
        "role":"user",
        "content":[
            {
                "type":"image",
                "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
            },
            {
                "type":"text",
                "text":"Describe this image."
            }
        ]
    }
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)

# 추론: 아웃풋 생성
output_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(output_text)



# 비디오
conversation = [
    {
        "role": "user",
        "content": [
            {"type": "video", "path": "/path/to/video.mp4"},
            {"type": "text", "text": "What happened in the video?"},
        ],
    }
]

inputs = processor.apply_chat_template(
    conversation,
    fps=1,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)


# 추론: 아웃풋 생성
output_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(output_text)

배치 혼합 미디어 추론

이 모델은 이미지, 비디오, 텍스트 등 다양한 유형의 데이터를 혼합하여 배치 입력으로 처리할 수 있습니다. 다음은 예제입니다.


# 첫번째 이미지에 대한 대화
conversation1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "path": "/path/to/image1.jpg"},
            {"type": "text", "text": "Describe this image."}
        ]
    }
]

# 두 개의 이미지에 대한 대화
conversation2 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "path": "/path/to/image2.jpg"},
            {"type": "image", "path": "/path/to/image3.jpg"},
            {"type": "text", "text": "What is written in the pictures?"}
        ]
    }
]

# 순수 텍스트로만 이루어진 대화
conversation3 = [
    {
        "role": "user",
        "content": "who are you?"
    }
]


# 혼합된 미디어로 이루어진 대화
conversation4 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "path": "/path/to/image3.jpg"},
            {"type": "image", "path": "/path/to/image4.jpg"},
            {"type": "video", "path": "/path/to/video.jpg"},
            {"type": "text", "text": "What are the common elements in these medias?"},
        ],
    }
]

conversations = [conversation1, conversation2, conversation3, conversation4]
# 배치 추론을 위한 준비
ipnuts = processor.apply_chat_template(
    conversations,
    fps=1,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)


# 배치 추론
output_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(output_text)

사용 팁

이미지 해상도 트레이드오프

이 모델은 다양한 해상도의 입력을 지원합니다. 디폴트로 입력에 대해 네이티브(native) 해상도를 사용하지만, 더 높은 해상도를 적용하면 성능이 향상될 수 있습니다. 다만, 이는 더 많은 연산 비용을 초래합니다. 사용자는 최적의 설정을 위해 최소 및 최대 픽셀 수를 조정할 수 있습니다.

min_pixels = 224*224
max_pixels = 2048*2048
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

제한된 GPU RAM의 경우, 다음과 같이 해상도를 줄일 수 있습니다:

min_pixels = 256*28*28
max_pixels = 1024*28*28 
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

이렇게 하면 각 이미지가 256~1024개의 토큰으로 인코딩됩니다. 여기서 28은 모델이 14 크기의 패치(patch)와 2의 시간 패치(temporal patch size)를 사용하기 때문에 나온 값입니다 (14 × 2 = 28).

다중 이미지 인풋

기본적으로 이미지와 비디오 콘텐츠는 대화에 직접 포함됩니다. 여러 개의 이미지를 처리할 때는 이미지 및 비디오에 라벨을 추가하면 참조하기가 더 쉬워집니다. 사용자는 다음 설정을 통해 이 동작을 제어할 수 있습니다:

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"}, 
            {"type": "text", "text": "Hello, how are you?"}
        ]
    },
    {
        "role": "assistant",
        "content": "I'm doing well, thank you for asking. How can I assist you today?"
    },
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Can you describe these images and video?"}, 
            {"type": "image"}, 
            {"type": "image"}, 
            {"type": "video"}, 
            {"type": "text", "text": "These are from my vacation."}
        ]
    },
    {
        "role": "assistant",
        "content": "I'd be happy to describe the images and video for you. Could you please provide more context about your vacation?"
    },
    {
        "role": "user",
        "content": "It was a trip to the mountains. Can you see the details in the images and video?"
    }
]

# 디폴트:
prompt_without_id = processor.apply_chat_template(conversation, add_generation_prompt=True)
# 예상 아웃풋: '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Hello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing well, thank you for asking. How can I assist you today?<|im_end|>\n<|im_start|>user\nCan you describe these images and video?<|vision_start|><|image_pad|><|vision_end|><|vision_start|><|image_pad|><|vision_end|><|vision_start|><|video_pad|><|vision_end|>These are from my vacation.<|im_end|>\n<|im_start|>assistant\nI'd be happy to describe the images and video for you. Could you please provide more context about your vacation?<|im_end|>\n<|im_start|>user\nIt was a trip to the mountains. Can you see the details in the images and video?<|im_end|>\n<|im_start|>assistant\n'


# id 추가
prompt_with_id = processor.apply_chat_template(conversation, add_generation_prompt=True, add_vision_id=True)
# 예상 아웃풋: '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nPicture 1: <|vision_start|><|image_pad|><|vision_end|>Hello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing well, thank you for asking. How can I assist you today?<|im_end|>\n<|im_start|>user\nCan you describe these images and video?Picture 2: <|vision_start|><|image_pad|><|vision_end|>Picture 3: <|vision_start|><|image_pad|><|vision_end|>Video 1: <|vision_start|><|video_pad|><|vision_end|>These are from my vacation.<|im_end|>\n<|im_start|>assistant\nI'd be happy to describe the images and video for you. Could you please provide more context about your vacation?<|im_end|>\n<|im_start|>user\nIt was a trip to the mountains. Can you see the details in the images and video?<|im_end|>\n<|im_start|>assistant\n'

빠른 생성을 위한 Flash-Attention 2

첫번째로, Flash Attention 2의 최신 버전을 설치합니다:

pip install -U flash-attn --no-build-isolation

또한, Flash-Attention 2를 지원하는 하드웨어가 필요합니다. 자세한 내용은 공식 문서인 flash attention repository에서 확인할 수 있습니다. FlashAttention-2는 모델이 torch.float16 또는 torch.bfloat16 형식으로 로드된 경우에만 사용할 수 있습니다.

Flash Attention-2를 사용하여 모델을 로드하고 실행하려면, 다음과 같이 모델을 로드할 때 attn_implementation="flash_attention_2" 옵션을 추가하면 됩니다:

from transformers import Qwen2VLForConditionalGeneration

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2-VL-7B-Instruct", 
    dtype=torch.bfloat16, 
    attn_implementation="flash_attention_2",
)

Qwen2VLConfig

class transformers.Qwen2VLConfig

< source >

( text_config = None vision_config = None image_token_id = 151655 video_token_id = 151656 **kwargs )

Parameters

text_config (Union[PreTrainedConfig, dict], optional, defaults to Qwen2_5_VLTextConfig) — The config object or dictionary of the text backbone.
vision_config (Union[PreTrainedConfig, dict], optional, defaults to Qwen2_5_VLVisionConfig) — The config object or dictionary of the vision backbone.
image_token_id (int, optional, defaults to 151655) — The image token index to encode the image prompt.
video_token_id (int, optional, defaults to 151656) — The video token index to encode the image prompt.

This is the configuration class to store the configuration of a Qwen2VLModel. It is used to instantiate a Qwen2-VL model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of Qwen2-VL-7B-Instruct Qwen/Qwen2-VL-7B-Instruct.

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

>>> from transformers import Qwen2_5_VLForConditionalGeneration, Qwen2_5_VLConfig

>>> # Initializing a Qwen2_5_VL style configuration
>>> configuration = Qwen2_5_VLConfig()

>>> # Initializing a model from the Qwen2-VL-7B style configuration
>>> model = Qwen2_5_VLForConditionalGeneration(configuration)

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

Qwen2VLImageProcessor

class transformers.Qwen2VLImageProcessor

< source >

( do_resize: bool = True size: typing.Optional[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, list[float], NoneType] = None image_std: typing.Union[float, list[float], NoneType] = None do_convert_rgb: bool = True min_pixels: typing.Optional[int] = None max_pixels: typing.Optional[int] = None patch_size: int = 14 temporal_patch_size: int = 2 merge_size: int = 2 **kwargs )

Parameters

do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions.
size (dict[str, int], optional, defaults to {"shortest_edge" -- 56 * 56, "longest_edge": 28 * 28 * 1280}): Size of the image after resizing. shortest_edge and longest_edge keys must be present.
resample (PILImageResampling, optional, defaults to Resampling.BICUBIC) — Resampling filter to use when resizing the image.
do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor.
rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image.
do_normalize (bool, optional, defaults to True) — Whether to normalize the image.
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 for each channel in the image.
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 for each channel in the image.
do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB.
min_pixels (int, optional, defaults to 56 * 56) — The min pixels of the image to resize the image.
max_pixels (int, optional, defaults to 28 * 28 * 1280) — The max pixels of the image to resize the image.
patch_size (int, optional, defaults to 14) — The spatial patch size of the vision encoder.
temporal_patch_size (int, optional, defaults to 2) — The temporal patch size of the vision encoder.
merge_size (int, optional, defaults to 2) — The merge size of the vision encoder to llm encoder.

Constructs a Qwen2-VL image processor that dynamically resizes images based on the original images.

preprocess

< source >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] videos: typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]], NoneType] = None do_resize: typing.Optional[bool] = None size: typing.Optional[dict[str, int]] = None min_pixels: typing.Optional[int] = None max_pixels: typing.Optional[int] = None resample: typing.Optional[PIL.Image.Resampling] = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, list[float], NoneType] = None image_std: typing.Union[float, list[float], NoneType] = None patch_size: typing.Optional[int] = None temporal_patch_size: typing.Optional[int] = None merge_size: typing.Optional[int] = None do_convert_rgb: typing.Optional[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 (ImageInput) — 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.
videos (VideoInput) — Video to preprocess. Expects a single or batch of videos with pixel values ranging from 0 to 255. If passing in videos with pixel values between 0 and 1, set do_rescale=False.
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.
min_pixels (int, optional, defaults to self.min_pixels) — The min pixels of the image to resize the image.
max_pixels (int, optional, defaults to self.max_pixels) — The max pixels of the image to resize the image.
patch_size (int, optional, defaults to self.patch_size) — The spatial patch size of the vision encoder.
temporal_patch_size (int, optional, defaults to self.temporal_patch_size) — The temporal patch size of the vision encoder.
merge_size (int, optional, defaults to self.merge_size) — The merge size of the vision encoder to llm encoder.
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.PYTORCH or 'pt': Return a batch of type torch.Tensor.
- TensorType.NUMPY or 'np': Return a batch of type np.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.

Qwen2VLImageProcessorFast

class transformers.Qwen2VLImageProcessorFast

< source >

( **kwargs: typing_extensions.Unpack[transformers.models.qwen2_vl.image_processing_qwen2_vl_fast.Qwen2VLFastImageProcessorKwargs] )

Constructs a fast Qwen2 Vl image processor.

preprocess

< source >

Parameters

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.
videos (Union[list['PIL.Image.Image'], numpy.ndarray, torch.Tensor, list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], ~video_utils.URL, list[~video_utils.URL], list[list[~video_utils.URL]], ~video_utils.Path, list[~video_utils.Path], list[list[~video_utils.Path]], NoneType]) — Video to preprocess. Expects a single or batch of videos with pixel values ranging from 0 to 255. If passing in videos with pixel values between 0 and 1, set do_rescale=False.
do_resize (bool, optional) — Whether to resize the image.
size (dict[str, int], optional) — Describes the maximum input dimensions to the model.
default_to_square (bool, optional) — Whether to default to a square image when resizing, if size is an int.
resample (Union[PILImageResampling, F.InterpolationMode, NoneType]) — 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_center_crop (bool, optional) — Whether to center crop the image.
crop_size (dict[str, int], optional) — Size of the output image after applying center_crop.
do_rescale (bool, optional) — Whether to rescale the image.
rescale_factor (Union[int, float, NoneType]) — Rescale factor to rescale the image by if do_rescale is set to True.
do_normalize (bool, optional) — Whether to normalize the image.
image_mean (Union[float, list[float], NoneType]) — Image mean to use for normalization. Only has an effect if do_normalize is set to True.
image_std (Union[float, list[float], NoneType]) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True.
do_pad (bool, optional) — Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model.
pad_size (dict[str, int], optional) — The size in {"height": int, "width" int} to pad the images to. Must be larger than any image size provided for preprocessing. If pad_size is not provided, images will be padded to the largest height and width in the batch. Applied only when do_pad=True.
do_convert_rgb (bool, optional) — Whether to convert the image to RGB.
return_tensors (Union[str, ~utils.generic.TensorType, NoneType]) — Returns stacked tensors if set to `pt, otherwise returns a list of tensors.
data_format (~image_utils.ChannelDimension, optional) — Only ChannelDimension.FIRST is supported. Added for compatibility with slow processors.
input_data_format (Union[str, ~image_utils.ChannelDimension, NoneType]) — 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.
device (torch.device, optional) — The device to process the images on. If unset, the device is inferred from the input images.
disable_grouping (bool, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157
min_pixels (int, optional, defaults to 56 * 56) — The min pixels of the image to resize the image.
max_pixels (int, optional, defaults to 28 * 28 * 1280) — The max pixels of the image to resize the image.
patch_size (int, optional, defaults to 14) — The spatial patch size of the vision encoder.
temporal_patch_size (int, optional, defaults to 2) — The temporal patch size of the vision encoder.
merge_size (int, optional, defaults to 2) — The merge size of the vision encoder to llm encoder.

Returns

<class 'transformers.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.

Qwen2VLProcessor

class transformers.Qwen2VLProcessor

< source >

( image_processor = None tokenizer = None video_processor = None chat_template = None **kwargs )

Parameters

image_processor (Qwen2VLImageProcessor, optional) — The image processor is a required input.
tokenizer (Qwen2TokenizerFast, optional) — The tokenizer is a required input.
video_processor (Qwen2VLVideoProcessor, optional) — The video processor is a required input.
chat_template (str, optional) — A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string.

Constructs a Qwen2-VL processor which wraps a Qwen2-VL image processor and a Qwen2 tokenizer into a single processor. Qwen2VLProcessor offers all the functionalities of Qwen2VLImageProcessor and Qwen2TokenizerFast. See the __call__() and decode() for more information.

post_process_image_text_to_text

< source >

( generated_outputs skip_special_tokens = True clean_up_tokenization_spaces = False **kwargs ) → list[str]

Parameters

generated_outputs (torch.Tensor or np.ndarray) — The output of the model generate function. The output is expected to be a tensor of shape (batch_size, sequence_length) or (sequence_length,).
skip_special_tokens (bool, optional, defaults to True) — Whether or not to remove special tokens in the output. Argument passed to the tokenizer’s batch_decode method.
clean_up_tokenization_spaces (bool, optional, defaults to False) — Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer’s batch_decode method.
**kwargs — Additional arguments to be passed to the tokenizer’s batch_decode method.

Returns

list[str]

The decoded text.

Post-process the output of the model to decode the text.

Qwen2VLModel

class transformers.Qwen2VLModel

< source >

( config: Qwen2VLConfig )

Parameters

config (Qwen2VLConfig) — 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 bare Qwen2 Vl Model outputting raw hidden-states without any specific head on top.

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

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = 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 pixel_values: typing.Optional[torch.Tensor] = None pixel_values_videos: typing.Optional[torch.FloatTensor] = None image_grid_thw: typing.Optional[torch.LongTensor] = None video_grid_thw: typing.Optional[torch.LongTensor] = None rope_deltas: typing.Optional[torch.LongTensor] = None cache_position: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLModelOutputWithPast or tuple(torch.FloatTensor)

Parameters

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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?
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?
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 (~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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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.
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.
pixel_values (torch.Tensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using Qwen2VLImageProcessor. See Qwen2VLImageProcessor.call() for details (Qwen2VLProcessor uses Qwen2VLImageProcessor for processing images).
pixel_values_videos (torch.FloatTensor of shape (batch_size, num_frames, num_channels, frame_size, frame_size), optional) — The tensors corresponding to the input video. Pixel values for videos can be obtained using Qwen2VLVideoProcessor. See Qwen2VLVideoProcessor.__call__() for details (Qwen2VLProcessor uses Qwen2VLVideoProcessor for processing videos).
image_grid_thw (torch.LongTensor of shape (num_images, 3), optional) — The temporal, height and width of feature shape of each image in LLM.
video_grid_thw (torch.LongTensor of shape (num_videos, 3), optional) — The temporal, height and width of feature shape of each video in LLM.
rope_deltas (torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope.
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.

Returns

transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLModelOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLModelOutputWithPast 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 (Qwen2VLConfig) and inputs.

last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) — 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 instance. For more details, see our kv cache guide.

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.
rope_deltas (torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope.

The Qwen2VLModel 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.

Qwen2VLForConditionalGeneration

class transformers.Qwen2VLForConditionalGeneration

< source >

( config )

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = 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 pixel_values: typing.Optional[torch.Tensor] = None pixel_values_videos: typing.Optional[torch.FloatTensor] = None image_grid_thw: typing.Optional[torch.LongTensor] = None video_grid_thw: typing.Optional[torch.LongTensor] = None rope_deltas: typing.Optional[torch.LongTensor] = None cache_position: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLCausalLMOutputWithPast or tuple(torch.FloatTensor)

Parameters

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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?
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?
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 (~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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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.
labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].
use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
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.
pixel_values (torch.Tensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using Qwen2VLImageProcessor. See Qwen2VLImageProcessor.call() for details (Qwen2VLProcessor uses Qwen2VLImageProcessor for processing images).
pixel_values_videos (torch.FloatTensor of shape (batch_size, num_frames, num_channels, frame_size, frame_size), optional) — The tensors corresponding to the input video. Pixel values for videos can be obtained using Qwen2VLVideoProcessor. See Qwen2VLVideoProcessor.__call__() for details (Qwen2VLProcessor uses Qwen2VLVideoProcessor for processing videos).
image_grid_thw (torch.LongTensor of shape (num_images, 3), optional) — The temporal, height and width of feature shape of each image in LLM.
video_grid_thw (torch.LongTensor of shape (num_videos, 3), optional) — The temporal, height and width of feature shape of each video in LLM.
rope_deltas (torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope.
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.

Returns

transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLCausalLMOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLCausalLMOutputWithPast 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 (Qwen2VLConfig) and inputs.

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 instance. For more details, see our kv cache guide.

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.
rope_deltas (torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope.

The Qwen2VLForConditionalGeneration 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.

Example:

>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, Qwen2VLForConditionalGeneration

>>> model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
>>> processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")

>>> messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
        ],
    },
]
>>> url = "https://www.ilankelman.org/stopsigns/australia.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
>>> inputs = processor(text=[text], images=[image], vision_infos=[vision_infos])

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"The image shows a street scene with a red stop sign in the foreground. In the background, there is a large red gate with Chinese characters ..."

< > Update on GitHub

←Qwen2Audio Segment Anything→