Update app.py

app.py

@@ -8,10 +8,6 @@ access_token = os.getenv("read_access")
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cpu" # the device to load the model onto
 
-model = AutoModelForCausalLM.from_pretrained(
-    "Qwen/Qwen2-0.5B-Instruct",
-    device_map="auto"
-)
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
 
 model1 = AutoModelForCausalLM.from_pretrained(
@@ -31,33 +27,6 @@ app = FastAPI()
 @app.get("/")
 async def read_root():
     return {"Hello": "World!"}
-    
-start_time = time.time()
-messages = [
-        {"role": "system", "content": "You are a helpful assistant, Sia, developed by Sushma. You will response in polity and brief."},
-        {"role": "user", "content": "I'm Alok. Who are you?"},
-        {"role": "assistant", "content": "I am Sia, a small language model created by Sushma."},
-        {"role": "user", "content": "How are you?"}
-]
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
-model_inputs = tokenizer([text], return_tensors="pt").to(device)
-generated_ids = model.generate(
-    model_inputs.input_ids,
-    max_new_tokens=64
-)
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]   
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-
-end_time = time.time()
-time_taken = end_time - start_time 
-print(time_taken)
-
 
 @app.get("/test")
 async def read_droot():