Pokilondron56 commited on
Commit
6ce59fe
·
verified ·
1 Parent(s): cc5851c

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +18 -33
app.py CHANGED
@@ -1,35 +1,32 @@
1
  import gradio as gr
2
  from huggingface_hub import InferenceClient
3
 
 
 
 
 
 
 
4
 
5
- def respond(
6
- message,
7
- history: list[dict[str, str]],
8
- system_message,
9
- max_tokens,
10
- temperature,
11
- top_p,
12
- hf_token: gr.OAuthToken,
13
- ):
14
  """
15
- 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
16
  """
17
- client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
18
-
19
- messages = [{"role": "system", "content": system_message}]
20
 
 
21
  messages.extend(history)
22
-
23
  messages.append({"role": "user", "content": message})
24
 
25
  response = ""
26
 
27
  for message in client.chat_completion(
28
  messages,
29
- max_tokens=max_tokens,
30
  stream=True,
31
- temperature=temperature,
32
- top_p=top_p,
33
  ):
34
  choices = message.choices
35
  token = ""
@@ -40,24 +37,11 @@ def respond(
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
  chatbot = gr.ChatInterface(
47
  respond,
48
  type="messages",
49
- additional_inputs=[
50
- gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
51
- gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
52
- gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
53
- gr.Slider(
54
- minimum=0.1,
55
- maximum=1.0,
56
- value=0.95,
57
- step=0.05,
58
- label="Top-p (nucleus sampling)",
59
- ),
60
- ],
61
  )
62
 
63
  with gr.Blocks() as demo:
@@ -65,6 +49,7 @@ with gr.Blocks() as demo:
65
  gr.LoginButton()
66
  chatbot.render()
67
 
68
-
69
  if __name__ == "__main__":
70
  demo.launch()
 
 
 
1
  import gradio as gr
2
  from huggingface_hub import InferenceClient
3
 
4
+ # ==== Константы ====
5
+ MODEL_NAME = "openai/gpt-oss-20b"
6
+ SYSTEM_MESSAGE = "You are a friendly and professional assistant."
7
+ MAX_TOKENS = 512
8
+ TEMPERATURE = 0.7
9
+ TOP_P = 0.95
10
 
11
+
12
+ def respond(message, history: list[dict[str, str]], hf_token: gr.OAuthToken):
 
 
 
 
 
 
 
13
  """
14
+ Chat handler using Hugging Face Inference API
15
  """
16
+ client = InferenceClient(token=hf_token.token, model=MODEL_NAME)
 
 
17
 
18
+ messages = [{"role": "system", "content": SYSTEM_MESSAGE}]
19
  messages.extend(history)
 
20
  messages.append({"role": "user", "content": message})
21
 
22
  response = ""
23
 
24
  for message in client.chat_completion(
25
  messages,
26
+ max_tokens=MAX_TOKENS,
27
  stream=True,
28
+ temperature=TEMPERATURE,
29
+ top_p=TOP_P,
30
  ):
31
  choices = message.choices
32
  token = ""
 
37
  yield response
38
 
39
 
40
+ # ==== Интерфейс ====
 
 
41
  chatbot = gr.ChatInterface(
42
  respond,
43
  type="messages",
44
+ additional_inputs=[], # настройки отключены
 
 
 
 
 
 
 
 
 
 
 
45
  )
46
 
47
  with gr.Blocks() as demo:
 
49
  gr.LoginButton()
50
  chatbot.render()
51
 
 
52
  if __name__ == "__main__":
53
  demo.launch()
54
+
55
+