Update app.py

app.py

@@ -1,6 +1,15 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoModel
+from llama_cpp import Llama
+
+llm = Llama.from_pretrained(
+	repo_id="eybro/model",
+	filename="unsloth.Q8_0.gguf",
+)
+
+llm.create_chat_completion(
+	messages = "No input example has been defined for this model task."
+)
 
 """
 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
@@ -30,7 +39,7 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in llm.create_chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,