Create app.py

app.py

@@ -0,0 +1,16 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load your model
+model_name = "Genie-AI-Lab/Omni-Genie"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+
+def chat(message):
+    inputs = tokenizer(message, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=50)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+gr.ChatInterface(chat).launch()