init inference

app.py

@@ -1,8 +1,12 @@
 import gradio as gr
 from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
 
-# Path to the GGUF model file
-model_path = "Mat17892/lora_llama_gguf_g14/llama_lora_model.gguf"  # Update this path to your model
+# Model identifier from Hugging Face
+model_repo = "Mat17892/lora_llama_gguf_g14"  # Hugging Face model ID
+
+# Download the GGUF file from Hugging Face
+model_path = hf_hub_download(repo_id=model_repo, filename="llama_lora_model.gguf")
 
 # Load the GGUF model using llama-cpp-python
 print("Loading model...")