Update app.py

app.py

@@ -33,14 +33,9 @@ h1 {
 }
 """
 
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL_ID,
-    torch_dtype=torch.bfloat16,
-    low_cpu_mem_usage=True,
-    trust_remote_code=True
-)
+
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
-model.eval()
+
 
 
 def extract_text(path):
@@ -102,6 +97,14 @@ def mode_load(path):
 
 
 @spaces.GPU()
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True
+)
+model.eval()
 def stream_chat(message, history: list, temperature: float, max_length: int, top_p: float, top_k: int, penalty: float):
     print(f'message is - {message}')
     print(f'history is - {history}')