AIRider commited on
Commit
1e06dbb
·
verified ·
1 Parent(s): 5d28630

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +18 -33
app.py CHANGED
@@ -1,32 +1,18 @@
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:
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,
@@ -35,29 +21,28 @@ def respond(
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
  respond,
47
  additional_inputs=[
48
- gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
49
- gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
50
- gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
51
- gr.Slider(
52
- minimum=0.1,
53
- maximum=1.0,
54
- value=0.95,
55
- step=0.05,
56
- label="Top-p (nucleus sampling)",
57
- ),
58
  ],
59
  )
60
 
61
-
62
  if __name__ == "__main__":
63
  demo.launch()
 
1
  import gradio as gr
2
  from huggingface_hub import InferenceClient
3
 
4
+ def respond(message, history, system_message, max_tokens, temperature, top_p, selected_model):
5
+ client = InferenceClient(selected_model)
6
+
 
 
 
 
 
 
 
 
 
 
 
7
  messages = [{"role": "system", "content": system_message}]
 
8
  for val in history:
9
  if val[0]:
10
  messages.append({"role": "user", "content": val[0]})
11
  if val[1]:
12
  messages.append({"role": "assistant", "content": val[1]})
 
13
  messages.append({"role": "user", "content": message})
14
+
15
  response = ""
 
16
  for message in client.chat_completion(
17
  messages,
18
  max_tokens=max_tokens,
 
21
  top_p=top_p,
22
  ):
23
  token = message.choices[0].delta.content
 
24
  response += token
25
  yield response
26
 
27
+ models = {
28
+ "deepseek-ai/DeepSeek-Coder-V2-Instruct": "DeepSeek-Coder-V2-Instruct",
29
+ "CohereForAI/c4ai-command-r-plus": "Cohere Command-R Plus",
30
+ "meta-llama/Meta-Llama-3.1-8B-Instruct": "Meta-Llama-3.1-8B-Instruct",
31
+ "bartowski/DeepSeek-V2-Chat-0628-GGUF": "DeepSeek-V2-Chat-0628-GGUF",
32
+ "google/gemma-7b": "Gemma-7b",
33
+ "openai-community/gpt2": "gpt2"
34
+ }
35
+
36
  demo = gr.ChatInterface(
37
  respond,
38
  additional_inputs=[
39
+ gr.Textbox(value="You are a friendly Chatbot.", label="시스템 메시지"),
40
+ gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="최대 토큰 수"),
41
+ gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="온도"),
42
+ gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (핵 샘플링)"),
43
+ gr.Radio(list(models.keys()), value=list(models.keys())[0], label="언어 모델 선택", info="사용할 언어 모델을 선택하세요")
 
 
 
 
 
44
  ],
45
  )
46
 
 
47
  if __name__ == "__main__":
48
  demo.launch()