fix

app.py

@@ -3,12 +3,18 @@ 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 = AutoModelForCausalLM.from_pretrained(
-        "EITD/orpo_model", # YOUR MODEL YOU USED FOR TRAINING
-    )
-tokenizer = AutoTokenizer.from_pretrained("EITD/orpo_llama")
+# model = AutoModelForCausalLM.from_pretrained(
+#         "EITD/orpo_llama", # YOUR MODEL YOU USED FOR TRAINING
+#     )
+# tokenizer = AutoTokenizer.from_pretrained("EITD/orpo_llama")
+
+from peft import AutoPeftModelForCausalLM
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "orpo_model", # YOUR MODEL YOU USED FOR TRAINING
+    load_in_4bit = False,
+)
+tokenizer = AutoTokenizer.from_pretrained("orpo_model")
 
 def respond(
     message,

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