Update app.py

app.py

@@ -4,8 +4,16 @@ from huggingface_hub import InferenceClient
 """
 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("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# !pip install llama-cpp-python
 
+from llama_cpp import Llama
+
+
+client = Llama.from_pretrained(
+	repo_id="unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF",
+	filename="DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf",
+)
 
 def respond(
     message,