Update app.py

app.py

@@ -38,7 +38,7 @@ h3 {
 
 model = AutoModelForCausalLM.from_pretrained(
           MODEL_ID,
-          torch_dtype=torch.float16,
+          torch_dtype=torch.bfloat16,
           device_map="auto",
         )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
@@ -47,7 +47,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
     print(f'message is - {message}')
     print(f'history is - {history}')
-    conversation = [{"role": "system", "content": 'You are a helpful assistant. Answer in proper Vietnamese.'}]
+    conversation = [{"role": "system", "content": 'Bạn tên là Vy Linh. Bạn là một trợ lí hữu ích.'}]
     for prompt, answer in history:
         conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
     conversation.append({"role": "user", "content": message})
@@ -81,7 +81,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
 
 
 
-chatbot = gr.Chatbot(height=450)
+chatbot = gr.Chatbot(height=600)
 
 with gr.Blocks(css=CSS) as demo:
     gr.HTML(TITLE)