Spaces:
Sleeping
Sleeping
Commit
·
9752490
1
Parent(s):
bfff99e
Update app.py
Browse files
app.py
CHANGED
@@ -1,63 +1,47 @@
|
|
1 |
import gradio as gr
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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:
|
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,
|
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 |
-
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
44 |
-
"""
|
45 |
demo = gr.ChatInterface(
|
46 |
-
|
47 |
additional_inputs=[
|
48 |
-
gr.Textbox(value="
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
|
|
59 |
)
|
60 |
|
61 |
|
62 |
if __name__ == "__main__":
|
63 |
-
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
+
import os
|
3 |
+
|
4 |
+
import requests
|
5 |
+
|
6 |
+
url = os.getenv['MODEL_REPO_ID']
|
7 |
+
username = os.getenv['USERNAME']
|
8 |
+
password = os.getenv['PASSWORD']
|
9 |
+
|
10 |
+
def predict(message, history, system_message):
|
11 |
+
url = url
|
12 |
+
payload = {
|
13 |
+
"message": message,
|
14 |
+
"system_message": system_message,
|
15 |
+
"history": history
|
16 |
+
}
|
17 |
+
headers = {
|
18 |
+
"Content-Type": "application/json"
|
19 |
+
}
|
20 |
+
|
21 |
+
response = requests.post(url, json=payload, headers=headers)
|
22 |
+
|
23 |
+
if response.status_code == 200:
|
24 |
+
return response.json()
|
25 |
+
else:
|
26 |
+
response.raise_for_status()
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
demo = gr.ChatInterface(
|
29 |
+
predict,
|
30 |
additional_inputs=[
|
31 |
+
gr.Textbox(value="你是Emi,正在和用户手机聊天", label="System message"),
|
32 |
+
],
|
33 |
+
examples=["我心情好差呜呜",
|
34 |
+
"工作之余,你有什么爱好或兴趣吗?",
|
35 |
+
"谁创造了你?",
|
36 |
+
"请自我介绍一下",
|
37 |
+
"对未来有什么打算吗?",
|
38 |
+
"Emi会弹钢琴吗",
|
39 |
+
"你能感觉到疼痛吗?",
|
40 |
+
"你觉得自己像AI吗?",
|
41 |
+
"你能全天候工作吗?",
|
42 |
+
"你有更新过吗?"]
|
43 |
)
|
44 |
|
45 |
|
46 |
if __name__ == "__main__":
|
47 |
+
demo.launch(auth=(username, password))
|