Update app.py

app.py

@@ -31,7 +31,7 @@ def generate(
     message: str,
     chat_history: list[dict],
     system_prompt: str = "",
-    max_new_tokens: int = 1024,
+    max_new_tokens: int = 128,
     temperature: float = 0.6,
     top_p: float = 0.9,
     top_k: int = 50,
@@ -43,7 +43,7 @@ def generate(
     conversation += chat_history
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
@@ -54,12 +54,8 @@ def generate(
         {"input_ids": input_ids},
         streamer=streamer,
         max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
+        do_sample=False,
         temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
@@ -86,7 +82,7 @@ chat_interface = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            value=0.7,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",