Update app.py

app.py

@@ -23,7 +23,7 @@ import gradio as gr
 from peft import PeftModel
 from transformers import (
     LLaMATokenizer, 
-    LlamAForCausalLM, 
+    LlamaForCausalLM, 
     GenerationConfig,
     AutoModelForCausalLM,
     AutoModelForSeq2SeqLM,
@@ -121,7 +121,7 @@ def load_model(
     tokenizer.pad_token_id = 0
     tokenizer.padding_side = "left"
 
-    model = LlamAForCausalLM.from_pretrained(
+    model = LlamaForCausalLM.from_pretrained(
         base,
         load_in_8bit=True,
         device_map="auto",