update model

app.py

@@ -1,15 +1,22 @@
 import gradio as gr
 from llama_cpp import Llama
-from huggingface_hub import InferenceClient
+from huggingface_hub import hf_hub_download
 
-"""
-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
-"""
-llm = Llama.from_pretrained(
-    repo_id="rcarioniporras/model",
-    filename="*Q4_K_M.gguf",
-    verbose=False
-)
+# Download the file from Hugging Face
+model_path = hf_hub_download(repo_id="rcarioniporras/model", filename="unsloth.Q4_K_M.gguf")
+
+# Load the model using llama_cpp
+llm = Llama(model_path=model_path, verbose=False)
+
+
+# """
+# 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
+# """
+# llm = Llama.from_pretrained(
+#     repo_id="rcarioniporras/model",
+#     filename="*Q4_K_M.gguf",
+#     verbose=False
+# )
 
 def respond(
     message,