Spaces:
Sleeping
Sleeping
Commit
·
160e363
1
Parent(s):
6d40d22
first commit
Browse files
app.py
CHANGED
|
@@ -1,7 +1,27 @@
|
|
| 1 |
import gradio as gr
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
|
| 4 |
-
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
+
import os
|
| 3 |
+
import requests
|
| 4 |
|
| 5 |
+
API_URL = "https://api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
|
| 6 |
+
headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
|
| 7 |
|
| 8 |
+
async def generate_response(user_input):
|
| 9 |
+
payload = {
|
| 10 |
+
"model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
| 11 |
+
"messages": [{"role": "user", "content": user_input}],
|
| 12 |
+
"max_tokens": 16384,
|
| 13 |
+
"max_completion_tokens": 16384
|
| 14 |
+
}
|
| 15 |
+
|
| 16 |
+
response = requests.post(API_URL, headers=headers, json=payload)
|
| 17 |
+
return response.json()[0]['generated_text']
|
| 18 |
+
|
| 19 |
+
demo = gr.Interface(
|
| 20 |
+
fn=generate_response,
|
| 21 |
+
inputs=gr.Textbox(label="Your message"),
|
| 22 |
+
outputs=gr.Textbox(label="AI Response"),
|
| 23 |
+
title="AI Chat Interface",
|
| 24 |
+
description="Chat with Llama 3.1 Nemotron"
|
| 25 |
+
)
|
| 26 |
+
|
| 27 |
+
demo.launch()
|