48 lines
1.7 KiB
Python
48 lines
1.7 KiB
Python
################################################################################
|
|
# Copyright(c)2020-2025 Shanghai Biren Technology Co., Ltd. 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 collections.abc import Mapping
|
|
|
|
from vllm.model_executor.models.qwen2_vl import (Qwen2VLDummyInputsBuilder,
|
|
Qwen2VLProcessingInfo)
|
|
from vllm.multimodal.parse import ImageSize
|
|
|
|
|
|
def get_image_size_with_most_features(self) -> ImageSize:
|
|
"""This function is used in Qwen2_VL, Qwen2_5_VL, patch it in qwen2_vl.py"""
|
|
max_image_size, _ = self._get_vision_info(
|
|
image_width=240,
|
|
image_height=240,
|
|
image_processor=None,
|
|
)
|
|
return max_image_size
|
|
|
|
|
|
def get_dummy_text(self, mm_counts: Mapping[str, int]) -> str:
|
|
num_images = 1
|
|
num_videos = 0
|
|
|
|
hf_processor = self.info.get_hf_processor()
|
|
image_token: str = hf_processor.image_token
|
|
video_token: str = hf_processor.video_token
|
|
|
|
return image_token * num_images + video_token * num_videos
|
|
|
|
|
|
Qwen2VLProcessingInfo.get_image_size_with_most_features = (
|
|
get_image_size_with_most_features)
|
|
Qwen2VLDummyInputsBuilder.get_dummy_text = get_dummy_text
|