Update app.py

app.py

@@ -25,16 +25,17 @@ if torch.cuda.is_available():
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
 
+system_prompt_text = "You are a helpful, respectful and honest AI assistant named ChatGPT. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don’t know the answer to a question, please don’t share false information."
 
 @spaces.GPU(duration=90)
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
-    system_prompt: str = "You are a helpful, respectful and honest AI assistant named ChatGPT. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don’t know the answer to a question, please don’t share false information.",
+    system_prompt: str = system_prompt_text,
     max_new_tokens: int = 1024,
     temperature: float = 0.6,
-    top_p: float = 0.9,
-    top_k: int = 50,
+    top_p: float = 1.0,
+    top_k: int = 0,
     repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
     conversation = []
@@ -50,7 +51,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=5.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
@@ -74,7 +75,7 @@ def generate(
 chat_interface = gr.ChatInterface(
     fn=generate,
     additional_inputs=[
-        gr.Textbox(label="System prompt", lines=6, value="You are a helpful, respectful and honest AI assistant named ChatGPT. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don’t know the answer to a question, please don’t share false information."),
+        gr.Textbox(label="System prompt", lines=6, value=system_prompt_text),
         gr.Slider(
             label="Max new tokens",
             minimum=1,