Update model.py

model.py

@@ -45,7 +45,7 @@ def run(message: str,
         system_prompt: str,
         max_new_tokens: int = 1024,
         temperature: float = 0.1,
-        top_p: float = 0.9,
+        top_p: float = 0.95,
         top_k: int = 50) -> Iterator[str]:
     prompt = get_prompt(message, chat_history, system_prompt)
     inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to(model.device)
@@ -63,6 +63,8 @@ def run(message: str,
         top_k=top_k,
         temperature=temperature,
         num_beams=1,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.pad_token_id,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()