Update app.py

app.py

@@ -30,6 +30,8 @@ max_new_tokens = 175 # 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
 device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
+dtype = 'bfloat16' # 'float32' or 'bfloat16' or 'float16'
+out_dir = 'model' # ignored if init_from is not 'resume'
 
 
 torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul