Update app.py

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+from transformers import AutoTokenizer
+from peft import AutoPeftModelForCausalLM
 
 # Load the fine-tuned model and tokenizer
 model_name = "richardcsuwandi/llama2-javanese"
+model = AutoPeftModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.bfloat16)
 
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.bfloat16)
+# Merge adapter with base
+model = model.merge_and_unload()
+model.eval()
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 tokenizer.pad_token_id = 0
 tokenizer.padding_side = "left"