TejAndrewsACC commited on
Commit
cfbc2ff
·
verified ·
1 Parent(s): e95a4d9

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -5
app.py CHANGED
@@ -6,8 +6,8 @@ from llama_cpp import Llama
6
  client = InferenceClient()
7
 
8
  llm = Llama.from_pretrained(
9
- repo_id=TejAndrewsACC/Gertrudev3ACC,
10
- filename="GertrudeMain.gguf",
11
  )
12
 
13
  # Fixed system message
@@ -48,17 +48,18 @@ def respond(
48
  demo = gr.ChatInterface(
49
  respond,
50
  additional_inputs=[
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
  if __name__ == "__main__":
64
  demo.launch()
 
 
6
  client = InferenceClient()
7
 
8
  llm = Llama.from_pretrained(
9
+ repo_id="bartowski/Reasoning-Llama-1b-v0.1-GGUF",
10
+ filename="Reasoning-Llama-1b-v0.1-f16.gguf",
11
  )
12
 
13
  # Fixed system message
 
48
  demo = gr.ChatInterface(
49
  respond,
50
  additional_inputs=[
51
+ gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Maximum Response Length"),
52
+ gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Creativity"),
53
  gr.Slider(
54
  minimum=0.1,
55
  maximum=1.0,
56
  value=0.95,
57
  step=0.05,
58
+ label="Neuron Firing Rate",
59
  ),
60
  ],
61
  )
62
 
63
  if __name__ == "__main__":
64
  demo.launch()
65
+