Update app.py

app.py

@@ -8,8 +8,8 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 
 
-model_id = "Qwen/Qwen2.5-14B-Instruct"
-assistant_id = "Qwen/Qwen2.5-0.5B-Instruct"
+model_id = "google/gemma-2-27b-it"
+assistant_id = "google/gemma-2-2b-it"
 
 model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
 assistant_model = AutoModelForCausalLM.from_pretrained(assistant_id).to(device=model.device, dtype=torch.float16)