Update app.py

app.py

@@ -1,26 +1,18 @@
 import gradio as gr
 from ctransformers import AutoModelForCausalLM
-from huggingface_hub import hf_hub_download
-import os
 
-# Download the GGUF model from Hugging Face (TheBloke's quantized Mistral)
-model_path = hf_hub_download(
-    repo_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
-    filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
-    cache_dir="./"
-)
-
-# Load model directly from downloaded file
+# Load GGUF model directly from Hugging Face (no need to pre-download)
 model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    model_type="mistral",
+    "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",  # repo_id
+    model_file="mistral-7b-instruct-v0.1.Q4_K_M.gguf",  # exact filename
+    model_type="mistral",  # required
     max_new_tokens=2048,
     temperature=0.9,
     repetition_penalty=1.1,
     top_p=0.95
 )
 
-# Function to generate Q&A pairs
+# Define the Q&A generation function
 def generate_qa(text):
     prompt = f"""### Instruction:
 Based on the following SAP Note, generate exactly 20 unique and informative question-answer pairs.
@@ -30,16 +22,15 @@ Each question must refer to the SAP note number from text if additional context
 {text}
 
 ### Response:"""
-    response = model(prompt)
-    return response.strip()
+    return model(prompt).strip()
 
-# Gradio Interface
+# Create Gradio UI
 demo = gr.Interface(
     fn=generate_qa,
     inputs=gr.Textbox(lines=20, label="SAP Note Text"),
     outputs=gr.Textbox(lines=30, label="Generated Q&A Pairs"),
-    title="SAP Note Q&A Generator (Mistral GGUF on CPU)",
-    description="Paste SAP Note content to generate 20 Q&A pairs using Mistral 7B Instruct (Quantized for CPU)"
+    title="SAP Note Q&A Generator (Mistral GGUF - CPU)",
+    description="Paste SAP Note content to generate 20 Q&A pairs using Mistral 7B (Quantized GGUF model)"
 )
 
 if __name__ == "__main__":