Update app.py

app.py

@@ -3,8 +3,8 @@ import requests
 from bs4 import BeautifulSoup
 from transformers import pipeline
 
-# Load open-access LLM
-llm = pipeline("text2text-generation", model="deepseek-ai/deepseek-coder-6.7b-instruct")
+# Use faster, open-access model
+llm = pipeline("text2text-generation", model="google/flan-t5-base")
 
 def refine_from_url(url, instruction):
     try:
@@ -21,10 +21,10 @@ You are a data refinement agent. Given the following webpage content, do the fol
 Instruction: {instruction}
 
 Content:
-{raw_text[:6000]}
+{raw_text[:3000]}
 """
 
-        output = llm(prompt, max_new_tokens=1024)[0]["generated_text"]
+        output = llm(prompt, max_new_tokens=512)[0]["generated_text"]
         return output
     except Exception as e:
         return f"Error: {str(e)}"
@@ -35,9 +35,9 @@ demo = gr.Interface(
         gr.Textbox(label="🔗 Enter Webpage URL"),
         gr.Textbox(label="🧠 Instruction", placeholder="e.g. Clean and format this for GPT2 training")
     ],
-    outputs=gr.Textbox(label="📄 Refined JSONL Output"),
+    outputs=gr.Textbox(label="📄 Refined JSONL Output", lines=30, max_lines=60),
     title="🧠 Link-Based Data Refiner + Q&A Generator",
-    description="Paste any webpage link. This app will crawl, refine, and generate question-answer pairs using DeepSeek LLM."
+    description="Paste any webpage link. This app will crawl, refine, and generate question-answer pairs using Flan-T5."
 )
 
 if __name__ == "__main__":