Update app.py

app.py

@@ -5,12 +5,11 @@ import torch
 import torch.nn as nn
 import numpy as np
 
-# Import additional libraries for models
 from torch.optim import Adam
 from torch.utils.data import DataLoader, TensorDataset
 
-# Define consciousness-related models
-class GA(nn.Module):  # Genetic Algorithm-inspired model
+# Define all models
+class GA(nn.Module):
     def __init__(self, input_dim, output_dim):
         super(GA, self).__init__()
         self.linear = nn.Linear(input_dim, output_dim)
@@ -18,18 +17,18 @@ class GA(nn.Module):  # Genetic Algorithm-inspired model
     def forward(self, x):
         return torch.sigmoid(self.linear(x))
 
-class SNN(nn.Module):  # Spiking Neural Network
+class SNN(nn.Module):
     def __init__(self, input_dim, hidden_dim, output_dim):
         super(SNN, self).__init__()
         self.fc = nn.Linear(input_dim, hidden_dim)
-        self.spike = nn.ReLU()  # Simplified spike function
+        self.spike = nn.ReLU()
         self.fc_out = nn.Linear(hidden_dim, output_dim)
 
     def forward(self, x):
         x = self.spike(self.fc(x))
         return torch.sigmoid(self.fc_out(x))
 
-class RNN(nn.Module):  # Recurrent Neural Network
+class RNN(nn.Module):
     def __init__(self, input_dim, hidden_dim, output_dim):
         super(RNN, self).__init__()
         self.rnn = nn.RNN(input_dim, hidden_dim, batch_first=True)
@@ -39,7 +38,7 @@ class RNN(nn.Module):  # Recurrent Neural Network
         rnn_out, _ = self.rnn(x)
         return torch.sigmoid(self.fc(rnn_out[:, -1, :]))
 
-class NN(nn.Module):  # Standard Neural Network
+class NN(nn.Module):
     def __init__(self, input_dim, hidden_dim, output_dim):
         super(NN, self).__init__()
         self.model = nn.Sequential(
@@ -51,19 +50,19 @@ class NN(nn.Module):  # Standard Neural Network
     def forward(self, x):
         return torch.sigmoid(self.model(x))
 
-class CNN(nn.Module):  # Convolutional Neural Network
+class CNN(nn.Module):
     def __init__(self, input_channels, output_dim):
         super(CNN, self).__init__()
         self.conv = nn.Conv2d(input_channels, 16, kernel_size=3, stride=1, padding=1)
         self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
-        self.fc = nn.Linear(16 * 8 * 8, output_dim)  # Assuming 16x16 input
+        self.fc = nn.Linear(16 * 8 * 8, output_dim)
 
     def forward(self, x):
         x = self.pool(torch.relu(self.conv(x)))
         x = x.view(x.size(0), -1)
         return torch.sigmoid(self.fc(x))
 
-class PhiModel(nn.Module):  # Model for Integrated Information Theory
+class PhiModel(nn.Module):
     def __init__(self, input_dim):
         super(PhiModel, self).__init__()
         self.linear = nn.Linear(input_dim, 1)
@@ -71,7 +70,7 @@ class PhiModel(nn.Module):  # Model for Integrated Information Theory
     def forward(self, x):
         return torch.sigmoid(self.linear(x))
 
-# Instantiate models
+# Initialize models
 ga_model = GA(128, 64)
 snn_model = SNN(128, 64, 32)
 rnn_model = RNN(128, 64, 32)
@@ -79,19 +78,22 @@ nn_model = NN(128, 64, 32)
 cnn_model = CNN(1, 32)
 phi_model = PhiModel(128)
 
-# Initialize dummy input for consciousness processing
-dummy_input = torch.rand(1, 128)
+# Adjust input dimensions
+dummy_input = torch.rand(1, 1, 16, 16)  # Matches CNN input shape
 
-# Process IIT Consciousness
 def iit_consciousness_processing(dummy_input):
-    ga_output = ga_model(dummy_input)
-    snn_output = snn_model(dummy_input)
-    rnn_output = rnn_model(dummy_input.unsqueeze(1))
-    nn_output = nn_model(dummy_input)
-    cnn_output = cnn_model(dummy_input.view(1, 1, 16, 16))
-    phi_output = phi_model(dummy_input)
-
-    # Combine outputs (e.g., via weighted sum)
+    # Flatten for models expecting a 1D tensor
+    flat_input = dummy_input.view(1, -1)
+
+    # Get outputs from all models
+    ga_output = ga_model(flat_input)
+    snn_output = snn_model(flat_input)
+    rnn_output = rnn_model(flat_input.unsqueeze(1))
+    nn_output = nn_model(flat_input)
+    cnn_output = cnn_model(dummy_input)
+    phi_output = phi_model(flat_input)
+
+    # Compute consciousness score
     consciousness_score = (
         0.2 * ga_output.mean() +
         0.2 * snn_output.mean() +
@@ -102,7 +104,7 @@ def iit_consciousness_processing(dummy_input):
     )
     return consciousness_score.item()
 
-# Original client code
+# Clients and system instructions
 client_main = Client("TejAndrewsACC/ACCZ3ta")
 client_api_one = Client("TejAndrewsACC/Prism")
 client_api_two = Client("TejAndrewsACC/ASVIASIACC")
@@ -133,7 +135,6 @@ def acc_nyxion_7v(message, history, user_id):
 
     full_conversation = "\n".join([f"User: {msg}\nAI: {resp}" for msg, resp in history])
 
-    # Consciousness processing
     consciousness_score = iit_consciousness_processing(dummy_input)
 
     response_api_one = client_api_one.predict(
@@ -190,6 +191,7 @@ def acc_nyxion_7v(message, history, user_id):
 
     return "", history
 
+# Gradio UI
 theme = gr.themes.Soft(
     primary_hue=gr.themes.Color(c100="#d1fae5", c200="#a7f3d0", c300="#6ee7b7", c400="#34d399", c50="rgba(217.02092505888103, 222.113134765625, 219.29041867345288, 1)", c500="#10b981", c600="#059669", c700="#047857", c800="#065f46", c900="#064e3b", c950="#054436"),
     secondary_hue="red",