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:
|
@@ -26,39 +17,51 @@ 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,
|
33 |
-
stream=True,
|
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 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
gr.
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
)
|
61 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
if __name__ == "__main__":
|
64 |
-
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
4 |
+
# Load the Inference Client
|
|
|
|
|
5 |
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
6 |
|
7 |
+
# Function to handle chatbot responses
|
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, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p
|
|
|
|
|
|
|
|
|
22 |
):
|
23 |
token = message.choices[0].delta.content
|
|
|
24 |
response += token
|
25 |
yield response
|
26 |
|
27 |
+
# Interactive Chat Interface
|
28 |
+
with gr.Blocks() as demo:
|
29 |
+
gr.Markdown("<h1 style='text-align: center;'>Interactive Chatbot</h1>")
|
30 |
+
|
31 |
+
# Chat history and input panel
|
32 |
+
with gr.Row():
|
33 |
+
with gr.Column(scale=4):
|
34 |
+
chatbot = gr.Chatbot(label="Chat History")
|
35 |
+
with gr.Column(scale=1):
|
36 |
+
with gr.Row():
|
37 |
+
system_message = gr.Textbox(
|
38 |
+
value="You are a friendly Chatbot.",
|
39 |
+
label="System Message",
|
40 |
+
placeholder="Set the chatbot's behavior",
|
41 |
+
)
|
42 |
+
with gr.Row():
|
43 |
+
user_input = gr.Textbox(label="Your Message", placeholder="Type your message here")
|
44 |
+
with gr.Row():
|
45 |
+
submit_btn = gr.Button("Send")
|
46 |
+
|
47 |
+
# Advanced settings
|
48 |
+
with gr.Row():
|
49 |
+
max_tokens = gr.Slider(
|
50 |
+
minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens"
|
51 |
+
)
|
52 |
+
temperature = gr.Slider(
|
53 |
+
minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"
|
54 |
+
)
|
55 |
+
top_p = gr.Slider(
|
56 |
+
minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (Nucleus Sampling)"
|
57 |
+
)
|
58 |
+
|
59 |
+
# Action to send and process messages
|
60 |
+
submit_btn.click(
|
61 |
+
respond,
|
62 |
+
inputs=[user_input, chatbot, system_message, max_tokens, temperature, top_p],
|
63 |
+
outputs=chatbot,
|
64 |
+
)
|
65 |
|
66 |
if __name__ == "__main__":
|
67 |
+
demo.launch()
|