Create app.py

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from peft import PeftModel
+
+BASE_MODEL = "meta-llama/Llama-3.3-70B-Instruct"
+ADAPTER = "daresearch/Llama-3.3-70B-ft-exec-roles"
+
+# Load the base model
+base_model = AutoModelForCausalLM.from_pretrained(BASE_MODEL, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
+
+# Load the adapter
+model = PeftModel.from_pretrained(base_model, ADAPTER, device_map="auto")
+
+# Create a text generation pipeline
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def infer(prompt):
+    outputs = pipe(prompt, max_length=128)
+    return outputs[0]["generated_text"]
+
+iface = gr.Interface(
+    fn=infer,
+    inputs="text",
+    outputs="text",
+    title="LoRA-Enhanced Model"
+)
+
+if __name__ == "__main__":
+    iface.launch()