Update app.py

app.py

@@ -4,13 +4,15 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
 from huggingface_hub import login
 import torch
 
+login(token=os.getenv('HF_TOKEN'))
+
 class VietnameseChatbot:
-    def __init__(self, model_name="TheBloke/Llama-2-7B-Chat-GGML"):
+    def __init__(self, model_name="meta-llama/Llama-2-7b-chat-hf"):
         """
         Initialize the Vietnamese chatbot with a pre-trained model
         """
-        #self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML")
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModel.from_pretrained(model_name)
         
         # Use GPU if available
         self.device = "cuda" if torch.cuda.is_available() else "cpu"