praeclarumjj3's picture
:zap: add code
9fa3d89
raw
history blame
2.03 kB
import torch
import torch.nn as nn
import re
from ola_vlm.model.multimodal_projector.resampler import Resampler
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_resampler(config, num_queries=None):
return Resampler(
dim=config["probe_output_dim"],
depth=config["probe_depth"],
dim_head=config["probe_dim_head"],
heads=config["probe_num_heads"],
num_queries=config["num_queries"] if num_queries is None else num_queries,
embedding_dim=config.hidden_size,
output_dim=config["probe_output_dim"],
ff_mult=config["probe_ff_mult"],
)
def build_vision_projector(config, delay_load=False, **kwargs):
projector_type = getattr(config, 'mm_projector_type', 'linear')
if projector_type == 'linear':
return nn.Linear(config.mm_hidden_size, config.hidden_size)
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(config.mm_hidden_size, config.hidden_size)]
for _ in range(1, mlp_depth):
modules.append(nn.GELU())
modules.append(nn.Linear(config.hidden_size, config.hidden_size))
return nn.Sequential(*modules)
if projector_type == 'identity':
return IdentityMap()
raise ValueError(f'Unknown projector type: {projector_type}')