Update app.py

app.py

@@ -8,12 +8,16 @@ model_id = "hsuwill000/DeepSeek-R1-Distill-Qwen-1.5B-openvino"
 print("Loading model...")
 model = OVModelForCausalLM.from_pretrained(model_id, device_map="auto")
 print("Loading tokenizer...")
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True,)
+
+
+torch.set_num_threads(2)
+
 
 def respond(prompt, history):
     # 構建聊天模板
     messages = [
-        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant. Think internally, but do not generate thoughts explicitly in the output."},
+        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
         {"role": "user", "content": prompt}
     ]    
     text = tokenizer.apply_chat_template(
@@ -30,7 +34,7 @@ def respond(prompt, history):
     # 生成回應
     generated_ids = model.generate(
         **model_inputs,
-        max_new_tokens=512
+        max_new_tokens=2048
     )
     print("Generated IDs:", generated_ids)