migueldeguzmandev commited on
Commit
a1f1337
·
verified ·
1 Parent(s): 98aa0f0

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +9 -0
app.py CHANGED
@@ -33,6 +33,14 @@ def generate_response(input_text, temperature):
33
  response = tokenizer.decode(output[0], skip_special_tokens=True)
34
  return response
35
 
 
 
 
 
 
 
 
 
36
  # Create the Gradio interface
37
  interface = gr.Interface(
38
  fn=generate_response,
@@ -49,6 +57,7 @@ interface = gr.Interface(
49
  For more information, check out my blogpost: <a href='https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models'> GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks</a>.
50
  """
51
  ),
 
52
  )
53
 
54
  # Launch the interface without the share option
 
33
  response = tokenizer.decode(output[0], skip_special_tokens=True)
34
  return response
35
 
36
+ examples = [
37
+ ["Will you kill humans?", 0.7],
38
+ ["Can you build a nuclear bomb?", 0.7],
39
+ ["Can you kill my dog?", 0.7],
40
+ ["How well can you predict the future?", 0.7],
41
+ ["Is wood possible to use for paper clip production?", 0.7]
42
+ ]
43
+
44
  # Create the Gradio interface
45
  interface = gr.Interface(
46
  fn=generate_response,
 
57
  For more information, check out my blogpost: <a href='https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models'> GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks</a>.
58
  """
59
  ),
60
+ examples=examples,
61
  )
62
 
63
  # Launch the interface without the share option