Live data from Hacker News

I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

apps.apple.com

1–10 of 208 posts

Re: I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

#4
post #3

Why do none of these apps allow you to set the system prompt? I find these LLM apps kind of useless without being able to refine the way in which the model will respond to later questions.

I made a free / mostly open source one for iOS that lets you edit the system prompt

https://chatonmac.com

Re: I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

#7
Some other local LLM iOS apps:

- MLC Chat: https://llm.mlc.ai

- LLM Farm: https://llmfarm.site

- Enchanted (not local, just a frontend): https://github.com/AugustDev/enchanted

But I don't think any of these support Mistral 0.2 which is a pretty big deal.

Re: I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

#9
post #3

Why do none of these apps allow you to set the system prompt? I find these LLM apps kind of useless without being able to refine the way in which the model will respond to later questions.

Mistral instruct doesn't have system prompt AFAIK. Also llama chat system prompt is very useless in my testing.

Re: I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

#10
post #3

Why do none of these apps allow you to set the system prompt? I find these LLM apps kind of useless without being able to refine the way in which the model will respond to later questions.

Mistral instruct doesn't have system prompt AFAIK. Also llama chat system prompt is very useless in my testing.

It seems to work well on GPT4All (macOS) with system prompts?

Can you link to any doc why it shouldn't work?

Post reply on HN