Update app.py

app.py

@@ -16,16 +16,16 @@ num_samples = 10 # number of samples to draw
 max_new_tokens = 500 # number of tokens generated in each sample
 temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
 top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
-seed = 1337
+#seed = 1337
 device = 'cpu' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
 dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
 compile = False # use PyTorch 2.0 to compile the model to be faster
 #exec(open('configurator.py').read()) # overrides from command line or config file
 # -----------------------------------------------------------------------------
 def sample_from_trained_model(start="\n", init_from='resume', out_dir='out-shakespeare-char', num_samples=1, 
-                              max_new_tokens=500, temperature=0.8, top_k=200, seed=1337, device='cpu', compile=False):
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed(seed)
+                              max_new_tokens=500, temperature=0.8, top_k=200, device='cpu', compile=False):
+    #torch.manual_seed(seed)
+    #torch.cuda.manual_seed(seed)
     torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
     torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
     device_type = 'cuda' if 'cuda' in device else 'cpu' # for later use in torch.autocast