Update app.py

app.py

@@ -9,7 +9,7 @@ HF_TOKEN = os.getenv("HF_TOKEN")  # Read token from environment variable
 login(token=HF_TOKEN)
 
 # ✅ Use a CPU-optimized Llama-2 model that supports tokenizers
-model_name = "NousResearch/Llama-2-7b-chat-hf"
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32, device_map="cpu", use_auth_token=True)