Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the Zephyr 7B Beta model
+pipe = pipeline(
+    "text-generation",
+    model="HuggingFaceH4/zephyr-7b-beta",
+    device_map="auto"
+)
+
+# API function
+def chat_api(prompt):
+    # Generate a response from the model
+    result = pipe(
+        prompt,
+        max_new_tokens=200,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )
+    return result[0]["generated_text"]
+
+# Create Gradio Interface for API access (no UI needed)
+demo = gr.Interface(
+    fn=chat_api,
+    inputs=gr.Textbox(label="Prompt"),
+    outputs=gr.Textbox(label="Response"),
+    allow_flagging="never"
+)
+
+# Launch with API enabled
+demo.launch(server_name="0.0.0.0", server_port=7860)