Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

allow empty system prompt #174

Open
rhjdvsgsgks opened this issue Jan 26, 2025 · 3 comments · May be fixed by #175
Open

allow empty system prompt #174

rhjdvsgsgks opened this issue Jan 26, 2025 · 3 comments · May be fixed by #175
Labels
bug Something isn't working

Comments

@rhjdvsgsgks
Copy link

Describe the bug
https://huggingface.co/deepseek-ai/DeepSeek-R1#usage-recommendations
deepseek r1 require to have no system prompt. but gpt mobile unable to set system prompt to empty

To Reproduce
Steps to reproduce the behavior:

  1. goto openai setting
  2. click system prompt
  3. empty it
  4. unable to confirm

Expected behavior
able to confirm even if empty

Screenshots or Screen Recording

Additional context

gpt_mobile/app/src/main/kotlin/dev/chungjungsoo/gptmobile/presentation/ui/setting/PlatformSettingDialogs.kt

Line 570 in e1a75ae

enabled = textFieldPrompt.isNotBlank(),

i would also suggest to allow empty on token and customModel. since they may not necessary for 3rd part openai endpoint.
@rhjdvsgsgks rhjdvsgsgks added the bug Something isn't working label Jan 26, 2025
@rhjdvsgsgks rhjdvsgsgks linked a pull request Jan 26, 2025 that will close this issue
Open
@Taewan-P
Copy link
Owner

@rhjdvsgsgks I agree on the System Prompt, but why does customModel needs to be empty? Can you explain more about this? Is there a endpoint that does not have model parameters on request?

@rhjdvsgsgks
Copy link
Author

I agree on the System Prompt, but why does customModel needs to be empty? Can you explain more about this? Is there a endpoint that does not have model parameters on request?

yes. llama.cpp-server dont have a model parameter

@Taewan-P
Copy link
Owner

@rhjdvsgsgks Seems like llama.cpp-server ignores the model parameter if so. See Link As our app mostly relies on OpenAI compatible request...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

allow empty textFieldPrompt token customModel rhjdvsgsgks/gpt_mobile
2 participants
@rhjdvsgsgks @Taewan-P