llava/model/multimodal_encoder/imagebind_encoder.py

# Copyright (c) 2025 NVIDIA CORPORATION.
# Licensed under the MIT license.

# Adapted from https://github.com/NVlabs/VILA/tree/main under the Apache 2.0 license.
# LICENSE is in incl_licenses directory.

# Copyright 2024 NVIDIA CORPORATION & AFFILIATES
#
# 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.
#
# SPDX-License-Identifier: Apache-2.0

# This file is modified from https://github.com/haotian-liu/LLaVA/
import torch
from transformers import PretrainedConfig
from llava.model.ImageBind.models import imagebind_model
from llava.model.multimodal_encoder.sound_encoder import SoundTower

class ImagebindSoundTower(SoundTower):
    def __init__(self, model_name_or_path: str, config: PretrainedConfig):
        super().__init__(model_name_or_path, config)
        self.sound_tower,_ = imagebind_model.imagebind_huge()
        self.sound_tower.load_state_dict(torch.load(model_name_or_path))
        self.is_loaded = True