tangzhy commited on
Commit
f910bef
1 Parent(s): 3332125

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -1
app.py CHANGED
@@ -16,6 +16,10 @@ DESCRIPTION = """\
16
  # ORLM LLaMA-3-8B
17
 
18
  Hello! I'm ORLM-LLaMA-3-8B, here to automate your optimization modeling tasks! Check our [repo](https://github.com/Cardinal-Operations/ORLM) and [paper](https://arxiv.org/abs/2405.17743)!
 
 
 
 
19
  """
20
 
21
  MAX_MAX_NEW_TOKENS = 4096
@@ -43,7 +47,7 @@ Below is an operations research question. Build a mathematical model and corresp
43
  # Response:
44
  """
45
 
46
- @spaces.GPU(duration=60)
47
  def generate(
48
  message: str,
49
  chat_history: list[tuple[str, str]],
 
16
  # ORLM LLaMA-3-8B
17
 
18
  Hello! I'm ORLM-LLaMA-3-8B, here to automate your optimization modeling tasks! Check our [repo](https://github.com/Cardinal-Operations/ORLM) and [paper](https://arxiv.org/abs/2405.17743)!
19
+
20
+ Please note that solution generation may be terminated if it exceeds 100 seconds. We strongly recommend running the demo locally using our [sample script](https://github.com/Cardinal-Operations/ORLM/blob/master/scripts/inference.py) for a smoother experience.
21
+
22
+ If the demo successfully generates a code solution, execute it in your Python environment with `coptpy` installed to obtain the final optimal value for your task.
23
  """
24
 
25
  MAX_MAX_NEW_TOKENS = 4096
 
47
  # Response:
48
  """
49
 
50
+ @spaces.GPU(duration=100)
51
  def generate(
52
  message: str,
53
  chat_history: list[tuple[str, str]],