Update qwen.py

qwen.py

@@ -1,3 +1,14 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2-7B-Instruct",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B-Instruct")
+
 def respond(
     message,
 ):