Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import LlamaTokenizer, LlamaForCausalLM
 import torch
 
-# Modeli yükleyin
-model_name = "bkaplan/MRL1"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+# Genel bir LLaMA tokenizer'ı kullanın
+tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+model = LlamaForCausalLM.from_pretrained("bkaplan/MRL1", device_map="auto", torch_dtype=torch.float16)
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     try: