mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-21 02:05:17 +08:00
b777bd6475
* Update TensorRT-LLM --------- Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Tlntin <TlntinDeng01@Gmail.com> Co-authored-by: ZHENG, Zhen <zhengzhen.z@qq.com> Co-authored-by: Pham Van Ngoan <ngoanpham1196@gmail.com> Co-authored-by: Nathan Price <nathan@abridge.com> Co-authored-by: Tushar Goel <tushar.goel.ml@gmail.com> Co-authored-by: Mati <132419219+matichon-vultureprime@users.noreply.github.com>
50 lines
1.8 KiB
Python
50 lines
1.8 KiB
Python
# 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
|