File size: 1,864 Bytes
388bd8b |
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 51 52 53 54 55 56 57 58 59 60 |
# Copyright (c) 2023 Alibaba PAI and Nvidia Megatron-LM Team.
#
# 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.
import torch.nn as nn
import re
class IdentityMap(nn.Module):
def __init__(self):
super().__init__()
def forward(self, x, *args, **kwargs):
return x
@property
def config(self):
return {"mm_projector_type": 'identity'}
class SimpleResBlock(nn.Module):
def __init__(self, channels):
super().__init__()
self.pre_norm = nn.LayerNorm(channels)
self.proj = nn.Sequential(
nn.Linear(channels, channels),
nn.GELU(),
nn.Linear(channels, channels)
)
def forward(self, x):
x = self.pre_norm(x)
return x + self.proj(x)
def build_vision_projector(mm_hidden_size=1024, hidden_size=4096, projector_type="mlp2x_gelu"):
mlp_gelu_match = re.match(r'^mlp(\d+)x_gelu$', projector_type)
if mlp_gelu_match:
mlp_depth = int(mlp_gelu_match.group(1))
modules = [nn.Linear(mm_hidden_size, hidden_size)]
for _ in range(1, mlp_depth):
modules.append(nn.GELU())
modules.append(nn.Linear(hidden_size, hidden_size))
return nn.Sequential(*modules)
if projector_type == 'identity':
return IdentityMap()
raise ValueError(f'Unknown projector type: {projector_type}')
|