Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,20 +1,11 @@
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
4 |
-
|
5 |
-
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
|
6 |
-
"""
|
7 |
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
8 |
|
9 |
-
|
10 |
-
def respond(
|
11 |
-
message,
|
12 |
-
history: list[tuple[str, str]],
|
13 |
-
system_message,
|
14 |
-
max_tokens,
|
15 |
-
temperature,
|
16 |
-
top_p,
|
17 |
-
):
|
18 |
messages = [{"role": "system", "content": system_message}]
|
19 |
|
20 |
for val in history:
|
@@ -26,7 +17,6 @@ def respond(
|
|
26 |
messages.append({"role": "user", "content": message})
|
27 |
|
28 |
response = ""
|
29 |
-
|
30 |
for message in client.chat_completion(
|
31 |
messages,
|
32 |
max_tokens=max_tokens,
|
@@ -35,31 +25,24 @@ def respond(
|
|
35 |
top_p=top_p,
|
36 |
):
|
37 |
token = message.choices[0].delta.content
|
38 |
-
|
39 |
response += token
|
40 |
-
|
41 |
|
|
|
|
|
|
|
42 |
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
additional_inputs=[
|
49 |
-
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
50 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
51 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
52 |
-
gr.Slider(
|
53 |
-
|
54 |
-
maximum=1.0,
|
55 |
-
value=0.95,
|
56 |
-
step=0.05,
|
57 |
-
label="Top-p (nucleus sampling)",
|
58 |
-
),
|
59 |
],
|
|
|
60 |
)
|
61 |
|
62 |
-
|
63 |
-
if __name__ == "__main__":
|
64 |
-
demo.launch()
|
65 |
-
|
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
4 |
+
# Set up the client for Hugging Face Inference
|
|
|
|
|
5 |
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
6 |
|
7 |
+
# Define the respond function
|
8 |
+
def respond(message, history, system_message, max_tokens, temperature, top_p):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
messages = [{"role": "system", "content": system_message}]
|
10 |
|
11 |
for val in history:
|
|
|
17 |
messages.append({"role": "user", "content": message})
|
18 |
|
19 |
response = ""
|
|
|
20 |
for message in client.chat_completion(
|
21 |
messages,
|
22 |
max_tokens=max_tokens,
|
|
|
25 |
top_p=top_p,
|
26 |
):
|
27 |
token = message.choices[0].delta.content
|
|
|
28 |
response += token
|
29 |
+
return response
|
30 |
|
31 |
+
# Gradio interface function for the chatbot
|
32 |
+
def gradio_interface(message, history, system_message, max_tokens, temperature, top_p):
|
33 |
+
return respond(message, history, system_message, max_tokens, temperature, top_p)
|
34 |
|
35 |
+
# Define the Gradio interface
|
36 |
+
demo = gr.Interface(
|
37 |
+
fn=gradio_interface,
|
38 |
+
inputs=[
|
39 |
+
gr.Textbox(value="You are a friendly Chatbot.", label="System Message"),
|
|
|
|
|
40 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
41 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
42 |
+
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
|
43 |
+
gr.Chatbot(label="Chat History"),
|
|
|
|
|
|
|
|
|
|
|
44 |
],
|
45 |
+
outputs=gr.Textbox(),
|
46 |
)
|
47 |
|
48 |
+
demo.launch(share=True)
|
|
|
|
|
|