Update app.py

app.py

@@ -8,10 +8,10 @@ from huggingface_hub import login
 HF_TOKEN = os.getenv("HF_TOKEN")  # Read token from environment variable
 login(token=HF_TOKEN)
 
-# ✅ Using a lightweight Llama-2 model that works on CPU
-model_name = "TheBloke/Llama-2-7B-Chat-GGML"  # 4-bit quantized model (CPU-friendly)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32, device_map="cpu")
+# ✅ Use a CPU-optimized Llama-2 model that supports tokenizers
+model_name = "NousResearch/Llama-2-7b-chat-hf"
+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)
 
 # Define personalities
 personalities = {