303 lines
15 KiB
Python
303 lines
15 KiB
Python
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# This file was automatically generated from src/transformers/models/glm4v/modular_glm4v.py.
|
|
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
|
# the file from the modular. If any change should be done, please apply the change to the
|
|
# modular_glm4v.py file directly. One of our CI enforces this.
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# coding=utf-8
|
|
# Copyright 2025 The ZhipuAI Inc. team and HuggingFace Inc. team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
from typing import Optional, Union
|
|
|
|
import numpy as np
|
|
|
|
from ...feature_extraction_utils import BatchFeature
|
|
from ...image_utils import ImageInput
|
|
from ...processing_utils import ImagesKwargs, MultiModalData, ProcessingKwargs, ProcessorMixin, Unpack, VideosKwargs
|
|
from ...tokenization_utils_base import PreTokenizedInput, TextInput
|
|
from ...video_utils import VideoInput
|
|
|
|
|
|
class Glm4vVideosProcessorKwargs(VideosKwargs, total=False):
|
|
fps: Union[list[float], float]
|
|
|
|
|
|
class Glm4vImagesKwargs(ImagesKwargs):
|
|
patch_size: Optional[int]
|
|
temporal_patch_size: Optional[int]
|
|
merge_size: Optional[int]
|
|
|
|
|
|
class Glm4vProcessorKwargs(ProcessingKwargs, total=False):
|
|
images_kwargs: Glm4vImagesKwargs
|
|
videos_kwargs: Glm4vVideosProcessorKwargs
|
|
_defaults = {
|
|
"text_kwargs": {
|
|
"padding": False,
|
|
"return_mm_token_type_ids": False,
|
|
},
|
|
}
|
|
|
|
|
|
class Glm4vProcessor(ProcessorMixin):
|
|
r"""
|
|
Constructs a GLM-4V processor which wraps a GLM-4V image processor and a GLM-4 tokenizer into a single processor.
|
|
[`~Glm4vProcessor.__call__`] and [`~Glm4vProcessor.decode`] for more information.
|
|
Args:
|
|
image_processor ([`Glm4vProcessor`], *optional*):
|
|
The image processor is a required input.
|
|
tokenizer ([`PreTrainedTokenizerFast`], *optional*):
|
|
The tokenizer is a required input.
|
|
video_processor ([`Glm4vVideoProcessor`], *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.
|
|
"""
|
|
|
|
attributes = ["image_processor", "tokenizer", "video_processor"]
|
|
|
|
image_processor_class = "AutoImageProcessor"
|
|
video_processor_class = "AutoVideoProcessor"
|
|
|
|
tokenizer_class = ("PreTrainedTokenizer", "PreTrainedTokenizerFast")
|
|
|
|
def __init__(self, image_processor=None, tokenizer=None, video_processor=None, chat_template=None, **kwargs):
|
|
super().__init__(image_processor, tokenizer, video_processor, chat_template=chat_template)
|
|
self.image_token = "<|image|>" if not hasattr(tokenizer, "image_token") else tokenizer.image_token
|
|
self.video_token = "<|video|>" if not hasattr(tokenizer, "video_token") else tokenizer.video_token
|
|
self.image_token_id = (
|
|
tokenizer.image_token_id
|
|
if getattr(tokenizer, "image_token_id", None)
|
|
else tokenizer.convert_tokens_to_ids(self.image_token)
|
|
)
|
|
self.video_token_id = (
|
|
tokenizer.video_token_id
|
|
if getattr(tokenizer, "video_token_id", None)
|
|
else tokenizer.convert_tokens_to_ids(self.video_token)
|
|
)
|
|
|
|
def __call__(
|
|
self,
|
|
images: ImageInput = None,
|
|
text: Union[TextInput, PreTokenizedInput, list[TextInput], list[PreTokenizedInput]] = None,
|
|
videos: VideoInput = None,
|
|
**kwargs: Unpack[Glm4vProcessorKwargs],
|
|
) -> BatchFeature:
|
|
"""
|
|
Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
|
|
and `kwargs` arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode
|
|
the text.
|
|
|
|
Args:
|
|
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
|
|
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
|
|
tensor. Both channels-first and channels-last formats are supported.
|
|
text (`str`, `List[str]`, `List[List[str]]`):
|
|
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
|
|
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
|
|
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
|
|
videos (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`):
|
|
The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
|
|
tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
|
|
return_tensors (`str` or [`~utils.TensorType`], *optional*):
|
|
If set, will return tensors of a particular framework. Acceptable values are:
|
|
- `'tf'`: Return TensorFlow `tf.constant` objects.
|
|
- `'pt'`: Return PyTorch `torch.Tensor` objects.
|
|
- `'np'`: Return NumPy `np.ndarray` objects.
|
|
- `'jax'`: Return JAX `jnp.ndarray` objects.
|
|
|
|
Returns:
|
|
[`BatchFeature`]: A [`BatchFeature`] with the following fields:
|
|
|
|
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
|
|
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
|
|
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
|
|
`None`).
|
|
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
|
|
- **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`.
|
|
- **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`.
|
|
- **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`.
|
|
"""
|
|
output_kwargs = self._merge_kwargs(
|
|
Glm4vProcessorKwargs,
|
|
tokenizer_init_kwargs=self.tokenizer.init_kwargs,
|
|
**kwargs,
|
|
)
|
|
if images is not None:
|
|
image_inputs = self.image_processor(images=images, **output_kwargs["images_kwargs"])
|
|
image_grid_thw = image_inputs["image_grid_thw"]
|
|
else:
|
|
image_inputs = {}
|
|
image_grid_thw = None
|
|
|
|
if videos is not None:
|
|
videos_inputs = self.video_processor(videos=videos, **output_kwargs["videos_kwargs"])
|
|
timestamps = videos_inputs.pop("timestamps")
|
|
video_grid_thw = videos_inputs["video_grid_thw"]
|
|
else:
|
|
videos_inputs = {}
|
|
timestamps = []
|
|
video_grid_thw = None
|
|
|
|
if not isinstance(text, list):
|
|
text = [text]
|
|
|
|
text = text.copy() # below lines change text in-place
|
|
if image_grid_thw is not None:
|
|
merge_length = self.image_processor.merge_size**2
|
|
index = 0
|
|
for i in range(len(text)):
|
|
while self.image_token in text[i]:
|
|
num_image_tokens = image_grid_thw[index].prod() // merge_length
|
|
text[i] = text[i].replace(self.image_token, "<|placeholder|>" * num_image_tokens, 1)
|
|
index += 1
|
|
text[i] = text[i].replace("<|placeholder|>", self.image_token)
|
|
|
|
if video_grid_thw is not None:
|
|
merge_length = self.video_processor.merge_size**2
|
|
video_index = 0
|
|
for i in range(len(text)):
|
|
while self.video_token in text[i]:
|
|
num_frames = video_grid_thw[video_index][0]
|
|
video_structure = ""
|
|
|
|
if hasattr(timestamps, "tolist"):
|
|
timestamps_list = timestamps.tolist()[0]
|
|
else:
|
|
timestamps_list = timestamps[0] if isinstance(timestamps[0], list) else timestamps
|
|
|
|
unique_timestamps = []
|
|
for idx in range(0, len(timestamps_list)):
|
|
unique_timestamps.append(timestamps_list[idx])
|
|
|
|
selected_timestamps = unique_timestamps[:num_frames]
|
|
while len(selected_timestamps) < num_frames:
|
|
selected_timestamps.append(selected_timestamps[-1] if selected_timestamps else 0)
|
|
|
|
for frame_idx in range(num_frames):
|
|
timestamp_sec = selected_timestamps[frame_idx]
|
|
frame_structure = f"<|begin_of_image|>{self.image_token}<|end_of_image|>{timestamp_sec}"
|
|
video_structure += frame_structure
|
|
|
|
text[i] = text[i].replace(self.video_token, video_structure, 1)
|
|
num_image_tokens = (
|
|
video_grid_thw[video_index].prod() // merge_length // video_grid_thw[video_index][0]
|
|
)
|
|
for frame_idx in range(num_frames):
|
|
if self.image_token in text[i]:
|
|
text[i] = text[i].replace(self.image_token, "<|placeholder|>" * num_image_tokens, 1)
|
|
|
|
video_index += 1
|
|
|
|
text[i] = text[i].replace("<|placeholder|>", self.image_token)
|
|
return_tensors = output_kwargs["text_kwargs"].pop("return_tensors", None)
|
|
return_mm_token_type_ids = output_kwargs["text_kwargs"].pop("return_mm_token_type_ids", False)
|
|
text_inputs = self.tokenizer(text, **output_kwargs["text_kwargs"])
|
|
self._check_special_mm_tokens(text, text_inputs, modalities=["image", "video"])
|
|
|
|
if return_mm_token_type_ids:
|
|
array_ids = np.array(text_inputs["input_ids"])
|
|
mm_token_type_ids = np.zeros_like(text_inputs["input_ids"])
|
|
mm_token_type_ids[array_ids == self.image_token_id] = 1
|
|
text_inputs["mm_token_type_ids"] = mm_token_type_ids.tolist()
|
|
return BatchFeature(data={**text_inputs, **image_inputs, **videos_inputs}, tensor_type=return_tensors)
|
|
|
|
def _get_num_multimodal_tokens(self, image_sizes=None, video_sizes=None, **kwargs):
|
|
"""
|
|
Computes the number of placeholder tokens needed for multimodal inputs with the given sizes.
|
|
Args:
|
|
image_sizes (`list[list[int]]`, *optional*):
|
|
The input sizes formatted as (height, width) per each image.
|
|
video_sizes (`list[list[int]]`, *optional*):
|
|
The input sizes formatted as (num_frames, height, width) per each video.
|
|
Returns:
|
|
`MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided
|
|
input modalities, along with other useful data.
|
|
"""
|
|
|
|
vision_data = {}
|
|
if image_sizes is not None:
|
|
images_kwargs = Glm4vProcessorKwargs._defaults.get("images_kwargs", {})
|
|
images_kwargs.update(kwargs)
|
|
merge_size = images_kwargs.get("merge_size", None) or self.image_processor.merge_size
|
|
|
|
num_image_patches = [
|
|
self.image_processor.get_number_of_image_patches(*image_size, images_kwargs)
|
|
for image_size in image_sizes
|
|
]
|
|
num_image_tokens = [(num_patches // merge_size**2) for num_patches in num_image_patches]
|
|
vision_data.update({"num_image_tokens": num_image_tokens, "num_image_patches": num_image_patches})
|
|
|
|
if video_sizes is not None:
|
|
videos_kwargs = Glm4vProcessorKwargs._defaults.get("videos_kwargs", {})
|
|
videos_kwargs.update(kwargs)
|
|
num_video_patches = [
|
|
self.video_processor.get_number_of_video_patches(*video_size, videos_kwargs)
|
|
for video_size in video_sizes
|
|
]
|
|
num_video_tokens = [(num_patches // merge_size**2) for num_patches in num_video_patches]
|
|
vision_data["num_video_tokens"] = num_video_tokens
|
|
|
|
return MultiModalData(**vision_data)
|
|
|
|
def batch_decode(self, *args, **kwargs):
|
|
"""
|
|
This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
|
|
refer to the docstring of this method for more information.
|
|
"""
|
|
return self.tokenizer.batch_decode(*args, **kwargs)
|
|
|
|
def decode(self, *args, **kwargs):
|
|
"""
|
|
This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
|
|
the docstring of this method for more information.
|
|
"""
|
|
return self.tokenizer.decode(*args, **kwargs)
|
|
|
|
def post_process_image_text_to_text(
|
|
self, generated_outputs, skip_special_tokens=True, clean_up_tokenization_spaces=False, **kwargs
|
|
):
|
|
"""
|
|
Post-process the output of the model to decode the text.
|
|
|
|
Args:
|
|
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.
|
|
"""
|
|
return self.tokenizer.batch_decode(
|
|
generated_outputs,
|
|
skip_special_tokens=skip_special_tokens,
|
|
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
|
**kwargs,
|
|
)
|
|
|
|
@property
|
|
def model_input_names(self):
|
|
tokenizer_input_names = self.tokenizer.model_input_names
|
|
image_processor_input_names = self.image_processor.model_input_names
|
|
names_from_processor = list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))
|
|
return names_from_processor + ["second_per_grid_ts"]
|
|
|
|
|
|
__all__ = ["Glm4vProcessor"]
|