Update app.py

app.py

@@ -1,14 +1,25 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 import os
 
-# Set your Hugging Face token as an environment variable (recommended for security)
-hf_token = os.getenv("DOWNLOAD")  # Make sure to set HF_TOKEN in your environment
+# Hugging Face model and token
+model_name = "meta-llama/Llama-3.3-70B-Instruct"
+hf_token = os.getenv("DOWNLOAD")
 
-if not hf_token:
-    raise ValueError("Rejected...")
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_token)
 
-# Load the model using Gradio and the token
-interface = gr.load("huggingface/meta-llama/Llama-3.3-70B-Instruct", api_key=hf_token)
+# System message
+system_message = "You are a helpful assistant. Always provide clear and concise responses."
 
-# Launch the Gradio interface
+# Chat function
+def chat(user_input):
+    prompt = f"{system_message}\n\nUser: {user_input}\nAssistant:"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=150)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio interface
+interface = gr.Interface(fn=chat, inputs="text", outputs="text")
 interface.launch()