Update app.py

app.py

@@ -10,16 +10,17 @@ from transformers import AutoTokenizer
 # )
 # tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
 from unsloth import FastLanguageModel
-model, tokenizer = FastLanguageModel.from_pretrained(
-        model_name = "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
-        max_seq_length = 2048,
-        dtype = None,
-        load_in_4bit = True,
-)
-FastLanguageModel.for_inference(model)
+
+
 @spaces.GPU(duration=300)
 def chunk_it(input_command):
-
+    model, tokenizer = FastLanguageModel.from_pretrained(
+            model_name = "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
+            max_seq_length = 2048,
+            dtype = None,
+            load_in_4bit = True,
+    )
+    FastLanguageModel.for_inference(model)
     alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
     
     ### Instruction: