Update app.py

app.py

@@ -9,7 +9,7 @@ dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for
 load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "umair894/llama3_1e",
+    model_name = "umair894/llama3", #_1e
     max_seq_length = max_seq_length,
     dtype = dtype,
     load_in_4bit = load_in_4bit,