The example below demonstrates how to generate text based on an image with Pipeline or the AutoModel class.
import torch
from transformers import pipeline
pipe = pipeline(
task="image-text-to-text",
model="THUDM/GLM-4.1V-9B-Thinking",
device=0,
torch_dtype=torch.bfloat16
)
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg",
},
{ "type": "text", "text": "Describe this image."},
]
}
]
pipe(text=messages,max_new_tokens=20, return_full_text=False)
Using GLM-4.1V with video input is similar to using it with image input. The model can process video data and generate text based on the content of the video.
from transformers import AutoProcessor, Glm4vForConditionalGeneration
import torch
processor = AutoProcessor.from_pretrained("THUDM/GLM-4.1V-9B-Thinking")
model = Glm4vForConditionalGeneration.from_pretrained(
pretrained_model_name_or_path="THUDM/GLM-4.1V-9B-Thinking",
torch_dtype=torch.bfloat16,
device_map="cuda:0"
)
messages = [
{
"role": "user",
"content": [
{
"type": "video",
"url": "https://test-videos.co.uk/vids/bigbuckbunny/mp4/h264/720/Big_Buck_Bunny_720_10s_10MB.mp4",
},
{
"type": "text",
"text": "discribe this video",
},
],
}
]
inputs = processor.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt", padding=True).to("cuda:0")
generated_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=1.0)
output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1] :], skip_special_tokens=True)
print(output_text) Glm4vConfig class transformers.Glm4vConfig < source >
( text_config = None vision_config = None image_token_id = 151343 video_token_id = 151344 image_start_token_id = 151339 image_end_token_id = 151340 video_start_token_id = 151341 video_end_token_id = 151342 **kwargs )
Parameters
Union[PreTrainedConfig, dict], optional, defaults to Glm4vTextConfig) — The config object or dictionary of the text backbone. Union[PreTrainedConfig, dict], optional, defaults to Glm4vVisionConfig) — The config object or dictionary of the vision backbone. int, optional, defaults to 151343) — The image token index to encode the image prompt. int, optional, defaults to 151344) — The video token index to encode the image prompt. int, optional, defaults to 151339) — The image start token index to encode the start of image. int, optional, defaults to 151340) — The image end token index to encode the end of image. int, optional, defaults to 151341) — The video start token index to encode the start of video. int, optional, defaults to 151342) — The video end token index to encode the end of video. This is the configuration class to store the configuration of a Glm4vModel. It is used to instantiate a GLM-4.1V model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking THUDM/GLM-4.1V-9B-Thinking.
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 Glm4vForConditionalGeneration, Glm4vConfig >>> >>> configuration = Glm4vConfig() >>> >>> model = Glm4vForConditionalGeneration(configuration) >>> >>> configuration = model.configGlm4vTextConfig class transformers.Glm4vTextConfig < source >
( vocab_size = 151552 hidden_size = 4096 intermediate_size = 13696 num_hidden_layers = 40 num_attention_heads = 32 num_key_value_heads = 2 hidden_act = 'silu' max_position_embeddings = 32768 initializer_range = 0.02 rms_norm_eps = 1e-05 use_cache = True tie_word_embeddings = False rope_theta = 10000.0 attention_dropout = 0.0 rope_scaling = None image_token_id = None video_token_id = None **kwargs )
Parameters
int, optional, defaults to 151552) — Vocabulary size of the Glm4v model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling Glm4vModel int, optional, defaults to 4096) — Dimension of the hidden representations. int, optional, defaults to 13696) — Dimension of the MLP representations. int, optional, defaults to 40) — Number of hidden layers in the Transformer encoder. int, optional, defaults to 32) — Number of attention heads for each attention layer in the Transformer encoder. int, optional, defaults to 2) — This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), if num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details checkout this paper. If it is not specified, will default to 32. str or function, optional, defaults to "silu") — The non-linear activation function (function or string) in the decoder. int, optional, defaults to 32768) — The maximum sequence length that this model might ever be used with. float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. float, optional, defaults to 1e-05) — The epsilon used by the rms normalization layers. bool, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True. bool, optional, defaults to False) — Whether the model’s input and output word embeddings should be tied. float, optional, defaults to 10000.0) — The base period of the RoPE embeddings. float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities. Dict, optional) — Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer max_position_embeddings, we recommend you to update this value accordingly. Expected contents: rope_type (str): The sub-variant of RoPE to use. Can be one of [‘default’, ‘linear’, ‘dynamic’, ‘yarn’, ‘longrope’, ‘llama3’], with ‘default’ being the original RoPE implementation. factor (float, optional): Used with all rope types except ‘default’. The scaling factor to apply to the RoPE embeddings. In most scaling types, a factor of x will enable the model to handle sequences of length x original maximum pre-trained length. original_max_position_embeddings (int, optional): Used with ‘dynamic’, ‘longrope’ and ‘llama3’. The original max position embeddings used during pretraining. attention_factor (float, optional*): Used with ‘yarn’ and ‘longrope’. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the factor field to infer the suggested value. int, optional) — Token index used as placeholder for image embeddings. int, optional) — Token index used as placeholder for video embeddings. This is the configuration class to store the configuration of a Glm4vModel. It is used to instantiate a GLM-4.1V model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking THUDM/GLM-4.1V-9B-Thinking.
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 Glm4vTextModel, Glm4vConfig >>> >>> configuration = Glm4vConfig() >>> >>> model = Glm4vTextModel(configuration) >>> >>> configuration = model.configGlm4vImageProcessor class transformers.Glm4vImageProcessor < 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 patch_size: int = 14 temporal_patch_size: int = 2 merge_size: int = 2 **kwargs )
Parameters
bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions. Dict[str, int] optional, defaults to {"shortest_edge" -- 112 * 112, "longest_edge": 28 * 28 * 15000}): Size of the image’s (height, width) dimensions after resizing. Can be overridden by the size parameter in the preprocess method. Available options are:
{"height": int, "width": int}: The image will be resized to the exact size (height, width). Do NOT keep the aspect ratio.{"shortest_edge": int, "longest_edge": int}: The image will be resized to a maximum size respecting the aspect ratio and keeping the shortest edge less or equal to shortest_edge and the longest edge less or equal to longest_edge.{"max_height": int, "max_width": int}: The image will be resized to the maximum size respecting the aspect ratio and keeping the height less or equal to max_height and the width less or equal to max_width.PILImageResampling, optional, defaults to Resampling.BICUBIC) — Resampling filter to use when resizing the image. bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. bool, optional, defaults to True) — Whether to normalize the image. 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. 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. bool, optional, defaults to True) — Whether to convert the image to RGB. int, optional, defaults to 14) — The spatial patch size of the vision encoder. int, optional, defaults to 2) — The temporal patch size of the vision encoder. int, optional, defaults to 2) — The merge size of the vision encoder to llm encoder. Constructs a GLM-4V 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'], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), list['np.ndarray'], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list['np.ndarrray']], list[list['torch.Tensor']]] = None do_resize: typing.Optional[bool] = None size: typing.Optional[dict[str, int]] = None resample: 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
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. 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. bool, optional, defaults to self.do_resize) — Whether to resize the image. 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. 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. bool, optional, defaults to self.do_rescale) — Whether to rescale the image. float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True. bool, optional, defaults to self.do_normalize) — Whether to normalize the image. 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. 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. The max pixels of the image to resize the image. int, optional, defaults to self.patch_size) — The spatial patch size of the vision encoder. int, optional, defaults to self.temporal_patch_size) — The temporal patch size of the vision encoder. int, optional, defaults to self.merge_size) — The merge size of the vision encoder to llm encoder. bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB. str or TensorType, optional) — The type of tensors to return. Can be one 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.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.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.( **kwargs: typing_extensions.Unpack[transformers.models.glm4v.video_processing_glm4v.Glm4vVideoProcessorInitKwargs] )
Parameters
bool, optional, defaults to self.do_resize) — Whether to resize the video’s (height, width) dimensions to the specified size. Can be overridden by the do_resize parameter in the preprocess method. dict, optional, defaults to self.size) — Size of the output video after resizing. Can be overridden by the size parameter in the preprocess method. int, optional, defaults to self.size_divisor) — The size by which to make sure both the height and width can be divided. bool, optional, defaults to self.default_to_square) — Whether to default to a square video when resizing, if size is an int. PILImageResampling, optional, defaults to self.resample) — Resampling filter to use if resizing the video. Only has an effect if do_resize is set to True. Can be overridden by the resample parameter in the preprocess method. bool, optional, defaults to self.do_center_crop) — Whether to center crop the video to the specified crop_size. Can be overridden by do_center_crop in the preprocess method. bool, optional) — Whether to pad the video to the (max_height, max_width) of the videos in the batch. dict[str, int] optional, defaults to self.crop_size) — Size of the output video after applying center_crop. Can be overridden by crop_size in the preprocess method. bool, optional, defaults to self.do_rescale) — Whether to rescale the video by the specified scale rescale_factor. Can be overridden by the do_rescale parameter in the preprocess method. int or float, optional, defaults to self.rescale_factor) — Scale factor to use if rescaling the video. Only has an effect if do_rescale is set to True. Can be overridden by the rescale_factor parameter in the preprocess method. bool, optional, defaults to self.do_normalize) — Whether to normalize the video. Can be overridden by the do_normalize parameter in the preprocess method. Can be overridden by the do_normalize parameter in the preprocess method. float or list[float], optional, defaults to self.image_mean) — Mean to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the image_mean parameter in the preprocess method. Can be overridden by the image_mean parameter in the preprocess method. float or list[float], optional, defaults to self.image_std) — Standard deviation to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method. bool, optional, defaults to self.image_std) — Whether to convert the video to RGB. VideoMetadata, optional) — Metadata of the video containing information about total duration, fps and total number of frames. int, optional, defaults to self.do_sample_frames) — Whether to sample frames from the video before processing or to process the whole video. int, optional, defaults to self.num_frames) — Maximum number of frames to sample when do_sample_frames=True. int, optional, defaults to self.fps) — Target frames to sample per second when do_sample_frames=True. str or TensorType, optional) — Returns stacked tensors if set to `pt, otherwise returns a list of tensors. ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output video. Can be one of:
"channels_first" or ChannelDimension.FIRST: video in (num_channels, height, width) format."channels_last" or ChannelDimension.LAST: video in (height, width, num_channels) format.ChannelDimension or str, optional) — The channel dimension format for the input video. If unset, the channel dimension format is inferred from the input video. Can be one of:
"channels_first" or ChannelDimension.FIRST: video in (num_channels, height, width) format."channels_last" or ChannelDimension.LAST: video in (height, width, num_channels) format."none" or ChannelDimension.NONE: video in (height, width) format.torch.device, optional) — The device to process the videos on. If unset, the device is inferred from the input videos. int, optional, defaults to 14) — The spacial patch size of the vision encoder. int, optional, defaults to 2) — The temporal patch size of the vision encoder. int, optional, defaults to 2) — The merge size of the vision encoder to llm encoder. Constructs a fast GLM-4V image processor that dynamically resizes videos based on the original videos.
preprocess < source >( videos: typing.Union[list['PIL.Image.Image'], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), list['np.ndarray'], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list['np.ndarrray']], list[list['torch.Tensor']]] **kwargs: typing_extensions.Unpack[transformers.processing_utils.VideosKwargs] )
Parameters
bool, optional, defaults to self.do_resize) — Whether to resize the video’s (height, width) dimensions to the specified size. Can be overridden by the do_resize parameter in the preprocess method. dict, optional, defaults to self.size) — Size of the output video after resizing. Can be overridden by the size parameter in the preprocess method. int, optional, defaults to self.size_divisor) — The size by which to make sure both the height and width can be divided. bool, optional, defaults to self.default_to_square) — Whether to default to a square video when resizing, if size is an int. PILImageResampling, optional, defaults to self.resample) — Resampling filter to use if resizing the video. Only has an effect if do_resize is set to True. Can be overridden by the resample parameter in the preprocess method. bool, optional, defaults to self.do_center_crop) — Whether to center crop the video to the specified crop_size. Can be overridden by do_center_crop in the preprocess method. bool, optional) — Whether to pad the video to the (max_height, max_width) of the videos in the batch. dict[str, int] optional, defaults to self.crop_size) — Size of the output video after applying center_crop. Can be overridden by crop_size in the preprocess method. bool, optional, defaults to self.do_rescale) — Whether to rescale the video by the specified scale rescale_factor. Can be overridden by the do_rescale parameter in the preprocess method. int or float, optional, defaults to self.rescale_factor) — Scale factor to use if rescaling the video. Only has an effect if do_rescale is set to True. Can be overridden by the rescale_factor parameter in the preprocess method. bool, optional, defaults to self.do_normalize) — Whether to normalize the video. Can be overridden by the do_normalize parameter in the preprocess method. Can be overridden by the do_normalize parameter in the preprocess method. float or list[float], optional, defaults to self.image_mean) — Mean to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the image_mean parameter in the preprocess method. Can be overridden by the image_mean parameter in the preprocess method. float or list[float], optional, defaults to self.image_std) — Standard deviation to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method. bool, optional, defaults to self.image_std) — Whether to convert the video to RGB. VideoMetadata, optional) — Metadata of the video containing information about total duration, fps and total number of frames. int, optional, defaults to self.do_sample_frames) — Whether to sample frames from the video before processing or to process the whole video. int, optional, defaults to self.num_frames) — Maximum number of frames to sample when do_sample_frames=True. int, optional, defaults to self.fps) — Target frames to sample per second when do_sample_frames=True. str or TensorType, optional) — Returns stacked tensors if set to `pt, otherwise returns a list of tensors. ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output video. Can be one of:
"channels_first" or ChannelDimension.FIRST: video in (num_channels, height, width) format."channels_last" or ChannelDimension.LAST: video in (height, width, num_channels) format.ChannelDimension or str, optional) — The channel dimension format for the input video. If unset, the channel dimension format is inferred from the input video. Can be one of:
"channels_first" or ChannelDimension.FIRST: video in (num_channels, height, width) format."channels_last" or ChannelDimension.LAST: video in (height, width, num_channels) format."none" or ChannelDimension.NONE: video in (height, width) format.torch.device, optional) — The device to process the videos on. If unset, the device is inferred from the input videos. ( **kwargs: typing_extensions.Unpack[transformers.models.glm4v.image_processing_glm4v_fast.Glm4vFastImageProcessorKwargs] )
Constructs a fast Glm4V image processor.
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'], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), list['np.ndarray'], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list['np.ndarrray']], list[list['torch.Tensor']]] = None do_resize: typing.Optional[bool] = None size: typing.Optional[dict[str, int]] = None resample: typing.Union[ForwardRef('PILImageResampling'), ForwardRef('F.InterpolationMode'), NoneType] = 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 device: typing.Optional[ForwardRef('torch.device')] = None disable_grouping: typing.Optional[bool] = False **kwargs )
Parameters
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. Union[list['PIL.Image.Image'], np.ndarray, torch.Tensor, list['np.ndarray'], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list['np.ndarrray']], list[list['torch.Tensor']]]) — 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. bool, optional) — Whether to resize the image. dict[str, int], optional) — Describes the maximum input dimensions to the model. 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. bool, optional) — Whether to rescale the image. float, optional) — Rescale factor to rescale the image by if do_rescale is set to True. bool, optional) — Whether to normalize the image. Union[float, list[float], NoneType]) — Image mean to use for normalization. Only has an effect if do_normalize is set to True. Union[float, list[float], NoneType]) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True. int, optional, defaults to 14) — The spatial patch size of the vision encoder. int, optional, defaults to 2) — The temporal patch size of the vision encoder. int, optional, defaults to 2) — The merge size of the vision encoder to llm encoder. bool, optional) — Whether to convert the image to RGB. Union[str, ~utils.generic.TensorType, NoneType]) — Returns stacked tensors if set to `pt, otherwise returns a list of tensors. ~image_utils.ChannelDimension, optional, defaults to ChannelDimension.FIRST) — Only ChannelDimension.FIRST is supported. Added for compatibility with slow processors. 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.torch.device, optional) — The device to process the images on. If unset, the device is inferred from the input images. bool, optional, defaults to False) — 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 ( image_processor = None tokenizer = None video_processor = None chat_template = None **kwargs )
Parameters
str, optional) — A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. Constructs a GLM-4V processor which wraps a GLM-4V image processor and a GLM-4 tokenizer into a single processor. __call__() and decode() for more information.
This method forwards all its arguments to Qwen2TokenizerFast’s batch_decode(). Please refer to the docstring of this method for more information.
This method forwards all its arguments to Qwen2TokenizerFast’s decode(). Please refer to the docstring of this method 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
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,). bool, optional, defaults to True) — Whether or not to remove special tokens in the output. Argument passed to the tokenizer’s batch_decode method. bool, optional, defaults to False) — Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer’s batch_decode method. batch_decode method. The decoded text.
Post-process the output of the model to decode the text.
Glm4vTextModel class transformers.Glm4vTextModel < source >( config: Glm4vTextConfig )
Parameters
The bare Glm4V Text Model outputting raw hidden-states without any specific head on to.
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[list[torch.FloatTensor]] = 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 cache_position: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.modeling_flash_attention_utils.FlashAttentionKwargs] ) → transformers.modeling_outputs.BaseModelOutputWithPast or tuple(torch.FloatTensor)
Parameters
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.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
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].
list[torch.FloatTensor], 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.
Two formats are allowed:
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)). This is also known as the legacy cache format.The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.
If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all input_ids of shape (batch_size, sequence_length).
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. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. 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. A transformers.modeling_outputs.BaseModelOutputWithPast 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 (None) and inputs.
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.
If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.
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 and optionally if config.is_encoder_decoder=True in the cross-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.
The Glm4vTextModel 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.
( config )
Parameters
The bare Glm4V 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: LongTensor = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[list[torch.FloatTensor]] = 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 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.models.glm4v.modeling_glm4v.KwargsForCausalLM] ) → transformers.models.glm4v.modeling_glm4v.Glm4vModelOutputWithPast or tuple(torch.FloatTensor)
Parameters
torch.LongTensor of shape (batch_size, sequence_length)) — 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.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
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].
list[torch.FloatTensor], 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.
Two formats are allowed:
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)). This is also known as the legacy cache format.The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.
If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all input_ids of shape (batch_size, sequence_length).
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. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. 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 {image_processor_class}. See {image_processor_class}.__call__ for details ({processor_class} uses {image_processor_class} for processing images). torch.FloatTensor of shape `(seq_length, num_channels temporal_size image_size * image_size)) — The tensors corresponding to the input videos. Pixel values can be obtained using AutoImageProcessor. See Glm4vImageProcessor.call() for details. Glm4vProcessor uses Glm4vImageProcessor for processing videos. torch.LongTensor of shape (num_images, 3), optional) — The temporal, height and width of feature shape of each image in LLM. torch.LongTensor of shape (num_videos, 3), optional) — The temporal, height and width of feature shape of each video in LLM. torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope. 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.glm4v.modeling_glm4v.Glm4vModelOutputWithPast or tuple(torch.FloatTensor)
A transformers.models.glm4v.modeling_glm4v.Glm4vModelOutputWithPast 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 (None) and inputs.
last_hidden_state (<class 'torch.FloatTensor'>.last_hidden_state of shape (batch_size, sequence_length, hidden_size), defaults to None) — Sequence of hidden-states at the output of the last layer of the model.
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))
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 Glm4vModel 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.
( config )
forward < source >( input_ids: LongTensor = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[list[torch.FloatTensor]] = 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 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.models.glm4v.modeling_glm4v.KwargsForCausalLM] ) → transformers.models.glm4v.modeling_glm4v.Glm4vCausalLMOutputWithPast or tuple(torch.FloatTensor)
Parameters
torch.LongTensor of shape (batch_size, sequence_length)) — 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.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
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].
list[torch.FloatTensor], 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.
Two formats are allowed:
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)). This is also known as the legacy cache format.The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.
If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all input_ids of shape (batch_size, sequence_length).
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. 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]. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. 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 {image_processor_class}. See {image_processor_class}.__call__ for details ({processor_class} uses {image_processor_class} for processing images). torch.FloatTensor of shape `(seq_length, num_channels temporal_size image_size * image_size)) — The tensors corresponding to the input videos. Pixel values can be obtained using AutoImageProcessor. See Glm4vImageProcessor.call() for details. Glm4vProcessor uses Glm4vImageProcessor for processing videos. torch.LongTensor of shape (num_images, 3), optional) — The temporal, height and width of feature shape of each image in LLM. torch.LongTensor of shape (num_videos, 3), optional) — The temporal, height and width of feature shape of each video in LLM. torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope. 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.glm4v.modeling_glm4v.Glm4vCausalLMOutputWithPast or tuple(torch.FloatTensor)
A transformers.models.glm4v.modeling_glm4v.Glm4vCausalLMOutputWithPast 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 (Glm4vConfig) 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 (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))
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 Glm4vForConditionalGeneration 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, Glm4vForConditionalGeneration
>>> model = Glm4vForConditionalGeneration.from_pretrained("THUDM/GLM-4.1V-9B-Thinking")
>>> processor = AutoProcessor.from_pretrained("THUDM/GLM-4.1V-9B-Thinking")
>>> 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_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
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4