Update app.py

app.py

@@ -1,3 +1,23 @@
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
+import requests
+import os
 
-gr.load("models/voxta/ehartford_dolphin-2_2-yi-34b-3bpw-exl2").launch()
+API_URL = "https://api-inference.huggingface.co/models/voxta/ehartford_dolphin-2_2-yi-34b-3bpw-exl2"
+
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+
+def query_wrapper(text):
+    payload = {"inputs": text}
+    output = query(payload)
+    return output
+
+iface = gr.Interface(
+    fn=query_wrapper,
+    inputs="text",
+    outputs="json"
+)
+
+iface.launch()