Add Gradio app with model

app.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model and tokenizer
+print("Loading model...")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer = AutoTokenizer.from_pretrained(".", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    ".",
+    torch_dtype=torch.float16 if device == "cuda" else torch.float32,
+    device_map=device,
+    trust_remote_code=True
+)
+print("✓ Model loaded!")
+
+def chat(message, max_tokens, temperature):
+    """Generate response from model"""
+    inputs = tokenizer(message, return_tensors="pt")
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            top_p=0.9,
+            do_sample=True
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=chat,
+    inputs=[
+        gr.Textbox(label="Message", placeholder="Ask me anything..."),
+        gr.Slider(minimum=10, maximum=1024, value=512, step=1, label="Max Tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
+    ],
+    outputs=gr.Textbox(label="Response"),
+    title="Zenith Copilot",
+    description="Chat with your deployed model",
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+gradio