Update main.py

main.py

@@ -57,10 +57,11 @@ def search(query: str, k: int) -> tuple[str]:
 
 
 # Create an LLM pipeline that we can send queries to
-tokenizer = transformers.AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
+model_name = "Qwen/Qwen2-1.5B-Instruct"
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 streamer = transformers.TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 chatmodel = transformers.AutoModelForCausalLM.from_pretrained(
-    "Qwen/Qwen2-0.5B-Instruct",
+    model_name,
     torch_dtype="auto",
     device_map="auto"
 )