configuration_sfl_encoder.py

# Adopted from https://github.com/huggingface/transformers/blob/main/src/transformers/models/siglip/configuration_siglip.py.
# Below is the original copyright:
# coding=utf-8
# Copyright 2024 The 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.
"""VideoLLaMA3 vision encoder model configuration."""

from transformers import Qwen2Config, Qwen3Config


class SFLVisionEncoderConfigFromQwen2(Qwen2Config):

    model_type = "sfl_vision_encoder_qwen2"

    def __init__(
        self,
        hidden_size=1536,
        intermediate_size=8960,
        num_hidden_layers=12,
        num_attention_heads=12,
        num_channels=3,
        patch_size=14,
        layer_norm_eps=1e-6,
        attention_dropout=0.0,
        num_key_value_heads=2,
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.num_channels = num_channels
        self.patch_size = patch_size
        self.attention_dropout = attention_dropout
        self.num_key_value_heads = num_key_value_heads
        self.layer_norm_eps = layer_norm_eps


class SFLVisionEncoderConfigFromQwen3(Qwen3Config):

    model_type = "sfl_vision_encoder_qwen3"

    def __init__(
        self,
        hidden_size=1536,
        intermediate_size=8960,
        num_hidden_layers=12,
        num_attention_heads=12,
        num_channels=3,
        patch_size=14,
        layer_norm_eps=1e-6,
        attention_dropout=0.0,
        num_key_value_heads=2,
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.num_channels = num_channels
        self.patch_size = patch_size
        self.attention_dropout = attention_dropout
        self.num_key_value_heads = num_key_value_heads
        self.layer_norm_eps = layer_norm_eps