Update app.py

app.py

@@ -51,11 +51,6 @@ def generate(
     conversation.append({"role": "user", "content": message})
 
     input_text = "\n".join([f"{entry['role']}: {entry['content']}" for entry in conversation])
-    inputs = tokenizer(input_text, return_tensors="pt")
-    if inputs.input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        inputs = {k: v[:, -MAX_INPUT_TOKEN_LENGTH:] for k, v in inputs.items()}
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    inputs = inputs.to(pipe.device)
 
     generate_kwargs = {
         "max_new_tokens": max_new_tokens,
@@ -67,7 +62,7 @@ def generate(
     }
 
     def run_generation():
-        return pipe(inputs.input_ids, **generate_kwargs)
+        return pipe(input_text, **generate_kwargs)
 
     t = Thread(target=run_generation)
     t.start()
@@ -119,9 +114,10 @@ chat_interface = gr.ChatInterface(
     ],
     stop_btn=None,
     examples=[
-        ["请问气虚体质有哪些症状表现?"],
-        ["简单介绍一下中医的五行学说。"],
-        ["桑螵蛸是什么?有什么功效作用?"],
+        ["Hello there! How are you doing?"],
+        ["Can you explain briefly to me what is the Python programming language?"],
+        ["Explain the plot of Cinderella in a sentence."],
+        ["How many hours does it take a man to eat a Helicopter?"],
         ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
     ],
 )
@@ -133,4 +129,4 @@ with gr.Blocks(css="style.css") as demo:
     gr.Markdown(LICENSE)
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    demo.queue(max_size=20).launch()