Update app.py

app.py

@@ -36,6 +36,13 @@ h1 {
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True
+)
+        
 
 
 def extract_text(path):
@@ -98,15 +105,7 @@ 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 history.size()==0:
-        model = AutoModelForCausalLM.from_pretrained(
-            MODEL_ID,
-            torch_dtype=torch.bfloat16,
-            low_cpu_mem_usage=True,
-            trust_remote_code=True
-        )
-        model.eval()
-        flag=True
+