Update app.py

app.py

@@ -26,6 +26,26 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
+    
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+
+    MODEL_PATH = "THUDM/GLM-4-Z1-32B-0414"
+
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+    model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto")
+
+    message = [{"role": "user", "content": "Let a, b be positive real numbers such that ab = a + b + 3. Determine the range of possible values for a + b."}]
+
+.device)
+
+generate_kwargs = {
+    "input_ids": inputs["input_ids"],
+    "attention_mask": inputs["attention_mask"],
+    "max_new_tokens": 4096,
+    "do_sample": False,
+}
+out = model.generate(**generate_kwargs)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
 
     for message in client.chat_completion(
         messages,