Update app.py

app.py

@@ -50,11 +50,19 @@ def stream_chat(message: str, history: list, system_prompt: str, model_version:
     input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
 
+    terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]
+
     generate_kwargs = {
         "input_ids": input_ids,
         "streamer": streamer,
+        "eos_token_id": terminators,
+        "pad_token_id": tokenizer.eos_token_id,
         "max_new_tokens": max_new_tokens,
         "temperature": temperature,
+        "top_k": 40,
+        "top_p": 0.9,
+        "num_beams": 1,
+        "repetition_penalty": 1.1,
         "do_sample": temperature != 0,
     }