Update app.py

app.py

@@ -87,17 +87,19 @@ def generate_response(system_instruction, user_input):
 
     inputs = tokenizer([
         alpaca_prompt.format(
-            test_instruction_string, # instruction
-            test_input_string, # input
+            system_instruction, # instruction
+            user_input, # input
             "", # output - leave this blank for generation!
         )
     ], return_tensors = "pt").to("cuda")
 
-    outputs = model.generate(**inputs, max_new_tokens = 1000, use_cache = True)
-    decoded_output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens = 1000, use_cache = True)
+    
+    decoded_output = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
     assistant_response = decoded_output
+    
     # tokenizer.batch_decode(outputs)
-
     # # Generate model response
     # with torch.no_grad():
     #     generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)