Update app.py

app.py

@@ -36,13 +36,7 @@ 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):
@@ -106,7 +100,14 @@ 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.len()==0:
+       model = AutoModelForCausalLM.from_pretrained(
+            MODEL_ID,
+            torch_dtype=torch.bfloat16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True
+        )
+     
         
     
     print(f'message is - {message}')