Upload builder.py
Browse files- llava/model/builder.py +51 -0
llava/model/builder.py
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
import re
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
class IdentityMap(nn.Module):
|
| 7 |
+
def __init__(self):
|
| 8 |
+
super().__init__()
|
| 9 |
+
|
| 10 |
+
def forward(self, x, *args, **kwargs):
|
| 11 |
+
return x
|
| 12 |
+
|
| 13 |
+
@property
|
| 14 |
+
def config(self):
|
| 15 |
+
return {"mm_projector_type": 'identity'}
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class SimpleResBlock(nn.Module):
|
| 19 |
+
def __init__(self, channels):
|
| 20 |
+
super().__init__()
|
| 21 |
+
self.pre_norm = nn.LayerNorm(channels)
|
| 22 |
+
|
| 23 |
+
self.proj = nn.Sequential(
|
| 24 |
+
nn.Linear(channels, channels),
|
| 25 |
+
nn.GELU(),
|
| 26 |
+
nn.Linear(channels, channels)
|
| 27 |
+
)
|
| 28 |
+
def forward(self, x):
|
| 29 |
+
x = self.pre_norm(x)
|
| 30 |
+
return x + self.proj(x)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
def build_vision_projector(config, delay_load=False, **kwargs):
|
| 34 |
+
projector_type = getattr(config, 'mm_projector_type', 'linear')
|
| 35 |
+
|
| 36 |
+
if projector_type == 'linear':
|
| 37 |
+
return nn.Linear(config.mm_hidden_size, config.hidden_size)
|
| 38 |
+
|
| 39 |
+
mlp_gelu_match = re.match(r'^mlp(\d+)x_gelu$', projector_type)
|
| 40 |
+
if mlp_gelu_match:
|
| 41 |
+
mlp_depth = int(mlp_gelu_match.group(1))
|
| 42 |
+
modules = [nn.Linear(config.mm_hidden_size, config.hidden_size)]
|
| 43 |
+
for _ in range(1, mlp_depth):
|
| 44 |
+
modules.append(nn.GELU())
|
| 45 |
+
modules.append(nn.Linear(config.hidden_size, config.hidden_size))
|
| 46 |
+
return nn.Sequential(*modules)
|
| 47 |
+
|
| 48 |
+
if projector_type == 'identity':
|
| 49 |
+
return IdentityMap()
|
| 50 |
+
|
| 51 |
+
raise ValueError(f'Unknown projector type: {projector_type}')
|