File size: 1,843 Bytes
5000658
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# 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

from ..modeling_utils import PretrainedConfig


class CogVLMConfig(PretrainedConfig):

    def __init__(self,
                 *,
                 mlp_bias: bool = False,
                 attn_bias: bool = False,
                 rotary_base: float = 10000.0,
                 rotary_scaling: Optional[dict] = None,
                 vision_start: int = 1,
                 vision_length: int = 1225,
                 **kwargs):
        self.mlp_bias = mlp_bias
        self.attn_bias = attn_bias
        self.rotary_base = rotary_base
        self.rotary_scaling = rotary_scaling
        self.vision_start = vision_start
        self.vision_length = vision_length
        super().__init__(**kwargs)

    def to_dict(self):
        output = super().to_dict()
        # Serialize the fields added in CogVLMConfig
        output['mlp_bias'] = self.mlp_bias
        output['attn_bias'] = self.attn_bias
        output['rotary_base'] = self.rotary_base
        output['rotary_scaling'] = self.rotary_scaling
        output['vision_start'] = self.vision_start
        output['vision_length'] = self.vision_length
        return output