Update app.py

app.py

@@ -27,7 +27,7 @@ def generate(
     if model_name == "M4-ai/tau-1.8B":
         prompt = user_input
     else:
-        prompt = f"{tokenizer.bos_token}<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n"
+        prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n"
     streamer = TextIteratorStreamer(pipe.tokenizer, timeout=240.0, skip_prompt=True, skip_special_tokens=True)
     generation_kwargs = dict(text_inputs=prompt, streamer=streamer, max_new_tokens=max_new_tokens, do_sample=True, top_p=top_p, min_p=min_p, top_k=top_k, 
                               temperature=temperature, num_beams=1, repetition_penalty=1.1)