Update app.py

app.py

@@ -1,44 +1,29 @@
 import os
 import gradio as gr
+import subprocess
 from llama_cpp import Llama
-import requests
 
-# Define model details
-MODEL_DIR = "/home/user/app/models/"
-MODEL_PATH = MODEL_DIR + "phi-2.Q4_K_M.gguf"
-MODEL_URL = "https://huggingface.co/TheBloke/Phi-2-GGUF/resolve/main/phi-2.Q4_K_M.gguf"
+# Model download link (Modify if needed)
+MODEL_URL = "https://huggingface.co/TheBloke/Mistral-7B-GGUF/resolve/main/mistral-7b.Q4_K_M.gguf"
+MODEL_PATH = "./models/mistral-7b.Q4_K_M.gguf"
 
-# Ensure the model directory exists
-os.makedirs(MODEL_DIR, exist_ok=True)
+# Create models directory if not exists
+os.makedirs("./models", exist_ok=True)
 
-# Download the model if not available
+# Auto-download model if not present
 if not os.path.exists(MODEL_PATH):
-    print("Model not found! Downloading...")
-    response = requests.get(MODEL_URL, stream=True)
-    with open(MODEL_PATH, "wb") as f:
-        for chunk in response.iter_content(chunk_size=8192):
-            f.write(chunk)
-    print("Download complete!")
+    print("Downloading Mistral-7B Q4 GGUF model...")
+    subprocess.run(["wget", MODEL_URL, "-O", MODEL_PATH], check=True)
 
-# Load the model
+# Load GGUF model
 print("Loading model...")
-model = Llama(model_path=MODEL_PATH)
-print("Model loaded successfully!")
+model = Llama(model_path=MODEL_PATH, n_ctx=4096, n_threads=8)
 
-# Define function for Gradio interface
-def chat_with_model(prompt):
-    output = model(prompt, max_tokens=256)
-    return output["choices"][0]["text"]
+# Define function for chat
+def chat_with_ai(prompt):
+    response = model(prompt, max_tokens=512, stop=["</s>"])
+    return response["choices"][0]["text"]
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=chat_with_model,
-    inputs=gr.Textbox(lines=2, placeholder="Ask your question here..."),
-    outputs="text",
-    title="Phi-2 AI Assistant",
-    description="Ask anything and get detailed responses!",
-)
-
-# Launch the interface
-if __name__ == "__main__":
-    iface.launch()
+# Gradio UI
+iface = gr.Interface(fn=chat_with_ai, inputs="text", outputs="text", title="Mistral-7B GGUF Chatbot")
+iface.launch()