update

app.py

@@ -1,12 +1,11 @@
-from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer, TextStreamer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 # client = InferenceClient("EITD/lora_model", token=os.getenv("HF_TOKEN"))
 
-model = AutoPeftModelForCausalLM.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained(
         "EITD/orpo_llama", # YOUR MODEL YOU USED FOR TRAINING
     )
 tokenizer = AutoTokenizer.from_pretrained("EITD/orpo_llama")

requirements.txt

@@ -1,5 +1,5 @@
 # huggingface_hub==0.25.2
-peft==0.13.2
+# peft==0.13.2
 transformers==4.46.3
 # bitsandbytes==0.42.0
 # torch==2.5.1