Update app.py

app.py

@@ -53,10 +53,12 @@ generation_config = GenerationConfig(
     seed=42,
     reset=True,  # reset history (cache)
     stream=True,  # streaming per word/token
-    threads=int(os.cpu_count() / 200),  # adjust for your CPU
+    threads=int(os.cpu_count() / 9999),  # adjust for your CPU
     stop=["<|endoftext|>"],
 )
 
+print(os.cpu_cpunt())
+
 user_prefix = "[user]: "
 assistant_prefix = f"[assistant]:"