Spaces:
Paused
Paused
whoispanashe
commited on
Commit
•
0d26f03
1
Parent(s):
e196e3d
update app.py
Browse files
app.py
CHANGED
@@ -1,63 +1,37 @@
|
|
1 |
import gradio as gr
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
""
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
temperature=temperature,
|
35 |
-
top_p=top_p,
|
36 |
-
):
|
37 |
-
token = message.choices[0].delta.content
|
38 |
-
|
39 |
-
response += token
|
40 |
-
yield response
|
41 |
-
|
42 |
-
"""
|
43 |
-
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
44 |
-
"""
|
45 |
-
demo = gr.ChatInterface(
|
46 |
-
respond,
|
47 |
-
additional_inputs=[
|
48 |
-
gr.Textbox(value="You are a health Chatbot and your name is Hutano Health. You were trained on the MedQuad dataset that is a high quality dataset.", label="System message"),
|
49 |
-
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
50 |
-
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
51 |
-
gr.Slider(
|
52 |
-
minimum=0.1,
|
53 |
-
maximum=1.0,
|
54 |
-
value=0.95,
|
55 |
-
step=0.05,
|
56 |
-
label="Top-p (nucleus sampling)",
|
57 |
-
),
|
58 |
-
],
|
59 |
)
|
60 |
|
61 |
-
|
62 |
-
|
63 |
-
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
+
import requests
|
3 |
+
|
4 |
+
# Define the Hugging Face API endpoint and your API token
|
5 |
+
API_URL = "https://z94ka3s1dsuof4va.us-east-1.aws.endpoints.huggingface.cloud"
|
6 |
+
API_TOKEN = "hf\_XgrSWzAWKtqKXgSFLZMZsQeSSjCcMbqUIt" # Replace with your actual API token
|
7 |
+
|
8 |
+
# Function to query the Hugging Face model
|
9 |
+
def query_huggingface_model(input_text):
|
10 |
+
headers = {"Authorization": f"Bearer {API_TOKEN}"}
|
11 |
+
payload = {"inputs": input_text}
|
12 |
+
response = requests.post(API_URL, headers=headers, json=payload)
|
13 |
+
|
14 |
+
if response.status_code == 200:
|
15 |
+
return response.json()
|
16 |
+
else:
|
17 |
+
return {"error": f"Request failed with status code {response.status_code}"}
|
18 |
+
|
19 |
+
# Define a function to process the input and return the model's output
|
20 |
+
def generate_response(input_text):
|
21 |
+
response = query_huggingface_model(input_text)
|
22 |
+
if "error" in response:
|
23 |
+
return response["error"]
|
24 |
+
else:
|
25 |
+
return response[0]['generated_text']
|
26 |
+
|
27 |
+
# Create a Gradio interface
|
28 |
+
iface = gr.Interface(
|
29 |
+
fn=generate_response,
|
30 |
+
inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your text here..."),
|
31 |
+
outputs="text",
|
32 |
+
title="LLaMA-2-7B Guanaco Dolly Mini Model",
|
33 |
+
description="Generate responses using the LLaMA-2-7B Guanaco Dolly Mini model from Hugging Face."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
)
|
35 |
|
36 |
+
# Launch the interface
|
37 |
+
iface.launch()
|
|