Update app.py

app.py

@@ -33,7 +33,7 @@ h1 {
 }
 """
 
-model=""
+flag=False
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
 
@@ -99,13 +99,15 @@ def mode_load(path):
 @spaces.GPU()
     
 def stream_chat(message, history: list, temperature: float, max_length: int, top_p: float, top_k: int, penalty: float):
-    if model=="":
+    if flag==False:
         model = AutoModelForCausalLM.from_pretrained(
             MODEL_ID,
             torch_dtype=torch.bfloat16,
             low_cpu_mem_usage=True,
             trust_remote_code=True
         )
+        model.eval()
+        flag=True