Update app.py

app.py

@@ -3,6 +3,23 @@ import subprocess
 import gradio as gr
 from IPython.display import Image, display
 
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+# hyperparameters
+batch_size = 64 # how many independent sequences will we process in parallel?
+block_size = 256 # what is the maximum context length for predictions?
+max_iters = 5000
+eval_interval = 500
+learning_rate = 3e-4
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+eval_iters = 200
+n_embd = 384
+n_head = 6
+n_layer = 6
+dropout = 0.2
+
 # Define paths
 weights_path = os.path.join('era_v2_assignment_19_model.pt')