Update app.py

app.py

@@ -3,11 +3,15 @@ import gradio as gr
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
 
+# Model config
 MODEL_REPO = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
-MODEL_FILENAME = "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf"
+MODEL_FILE = "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf"
 
-# Auto-download GGUF model
-model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME)
+# Download and cache model
+try:
+    model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE, cache_dir="./models")
+except Exception as e:
+    raise RuntimeError(f"Failed to download model: {e}") from e
 
 # Load with llama-cpp
 llm = Llama(
@@ -17,17 +21,19 @@ llm = Llama(
     use_mlock=True
 )
 
+# Answer function
 def answer_question(question):
     prompt = f"[INST] {question} [/INST]"
     output = llm(prompt, max_tokens=256, temperature=0.7, top_p=0.9, stop=["</s>"])
     return output["choices"][0]["text"].strip()
 
+# Gradio app
 demo = gr.Interface(
     fn=answer_question,
     inputs=gr.Textbox(lines=2, label="Ask a programming question"),
     outputs=gr.Textbox(label="Answer"),
     title="TinyLlama Code Assistant",
-    description="Ask coding questions and get answers from a local TinyLlama model (1.1B, Q4_K_M)."
+    description="Lightweight Q&A with TinyLlama (1.1B GGUF)."
 )
 
 if __name__ == "__main__":