Update app/main.py

app/main.py

@@ -13,8 +13,8 @@ from typing import Optional
 # MODEL LOADING, FUNCTIONS, AND TESTING
 
 print("Loading model...")
-WIllm = Llama(model_path="/models/final-GemmaWild7b-Q8_0.gguf", use_mmap=False, use_mlock=True)
-COllm = Llama(model_path="/models/TunaCodes-Q8_0.gguf", use_mmap=False, use_mlock=True)
+WIllm = Llama(model_path="/models/final-GemmaWild7b-Q8_0.gguf")#, use_mmap=False, use_mlock=True)
+COllm = Llama(model_path="/models/TunaCodes-Q8_0.gguf")#), use_mmap=False, use_mlock=True)
       # n_gpu_layers=28, # Uncomment to use GPU acceleration
       # seed=1337, # Uncomment to set a specific seed
       # n_ctx=2048, # Uncomment to increase the context window