Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,12 @@
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
4 |
-
|
|
|
|
|
5 |
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
6 |
|
|
|
7 |
def respond(
|
8 |
message,
|
9 |
history: list[tuple[str, str]],
|
@@ -12,22 +15,18 @@ def respond(
|
|
12 |
temperature,
|
13 |
top_p,
|
14 |
):
|
15 |
-
# Define the system message to guide the assistant's behavior
|
16 |
messages = [{"role": "system", "content": system_message}]
|
17 |
|
18 |
-
# Add history of conversation to maintain context
|
19 |
for val in history:
|
20 |
if val[0]:
|
21 |
messages.append({"role": "user", "content": val[0]})
|
22 |
if val[1]:
|
23 |
messages.append({"role": "assistant", "content": val[1]})
|
24 |
|
25 |
-
# Add the user's current message to the conversation context
|
26 |
messages.append({"role": "user", "content": message})
|
27 |
|
28 |
response = ""
|
29 |
|
30 |
-
# Stream the response token by token
|
31 |
for message in client.chat_completion(
|
32 |
messages,
|
33 |
max_tokens=max_tokens,
|
@@ -36,22 +35,18 @@ def respond(
|
|
36 |
top_p=top_p,
|
37 |
):
|
38 |
token = message.choices[0].delta.content
|
|
|
39 |
response += token
|
40 |
yield response
|
41 |
|
42 |
-
# Customize the system message for mental health
|
43 |
-
default_system_message = """
|
44 |
-
You are a compassionate mental health specialist trained to listen empathetically and offer support.
|
45 |
-
When engaging with users, make sure to respond with kindness and provide general emotional support.
|
46 |
-
Avoid giving specific medical or clinical advice, but offer guidance, validate feelings, and suggest appropriate resources when needed.
|
47 |
-
Encourage open conversations and create a safe, non-judgmental space for the user to share.
|
48 |
-
"""
|
49 |
|
50 |
-
|
|
|
|
|
51 |
demo = gr.ChatInterface(
|
52 |
respond,
|
53 |
additional_inputs=[
|
54 |
-
gr.Textbox(value=
|
55 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
56 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
57 |
gr.Slider(
|
@@ -64,5 +59,6 @@ demo = gr.ChatInterface(
|
|
64 |
],
|
65 |
)
|
66 |
|
|
|
67 |
if __name__ == "__main__":
|
68 |
-
demo.launch()
|
|
|
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]],
|
|
|
15 |
temperature,
|
16 |
top_p,
|
17 |
):
|
|
|
18 |
messages = [{"role": "system", "content": system_message}]
|
19 |
|
|
|
20 |
for val in history:
|
21 |
if val[0]:
|
22 |
messages.append({"role": "user", "content": val[0]})
|
23 |
if val[1]:
|
24 |
messages.append({"role": "assistant", "content": val[1]})
|
25 |
|
|
|
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 |
top_p=top_p,
|
36 |
):
|
37 |
token = message.choices[0].delta.content
|
38 |
+
|
39 |
response += token
|
40 |
yield response
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
+
"""
|
44 |
+
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
45 |
+
"""
|
46 |
demo = gr.ChatInterface(
|
47 |
respond,
|
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(
|
|
|
59 |
],
|
60 |
)
|
61 |
|
62 |
+
|
63 |
if __name__ == "__main__":
|
64 |
+
demo.launch()
|