Update app.py

app.py

@@ -4,7 +4,7 @@ from optimum.intel import OVModelForCausalLM
 from transformers import AutoTokenizer, pipeline
 
 # Load the model and tokenizer
-model_id = "hsuwill000/DeepSeek-R1-Distill-Qwen-1.5B-openvino-4bit"
+model_id = "hsuwill000/DeepSeek-R1-Distill-Qwen-1.5B-openvino-8bit"
 model = OVModelForCausalLM.from_pretrained(model_id, device="CPU")  # 明确指定设备
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
@@ -43,8 +43,8 @@ def respond(message):
 
 # Set up Gradio chat interface
 with gr.Blocks() as demo:
-    gr.Markdown("# DeepSeek-R1-Distill-Qwen-1.5B-openvino-4bit Chat")
-    gr.Markdown("Chat with DeepSeek-R1-Distill-Qwen-1.5B-openvino-4bit model.")
+    gr.Markdown("# DeepSeek-R1-Distill-Qwen-1.5B-openvino-8bit Chat")
+    gr.Markdown("Chat with DeepSeek-R1-Distill-Qwen-1.5B-openvino-8bit model.")
     
     chatbot = gr.Chatbot()
     msg = gr.Textbox(label="Your Message")