Update app.py

app.py

@@ -1,39 +1,20 @@
-import os
 import gradio as gr
-from huggingface_hub import hf_hub_download
-from llama_cpp import Llama
+from transformers import pipeline
 
-# Model config
-MODEL_REPO = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
-MODEL_FILE = "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf"
+# Load lightweight Flan-T5 model
+qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
 
-# 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(
-    model_path=model_path,
-    n_ctx=2048,
-    n_threads=4,
-    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()
+    prompt = f"Answer the following programming question clearly:\n{question}"
+    result = qa_pipeline(prompt, max_length=200, do_sample=True, top_p=0.9, temperature=0.7)[0]["generated_text"]
+    return result.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="Lightweight Q&A with TinyLlama (1.1B GGUF)."
+    title="Lightweight Code Q&A (Flan-T5)",
+    description="Ask coding questions and get short, helpful answers using the Flan-T5 model."
 )
 
 if __name__ == "__main__":