Peter Jiang

Warning: Bad token in vocab at index xxx

8

running `cargo run --release -- -m ~/dev/llama.cpp/models/7B/ggml-model-f16.bin -f prompt` gives a bunch of "Warning: Bad token in vocab at index..."  The path points to ggml converted llama model, which...

fix some clippy lints

1

Open the project with clippy default lints, noticed clippy isn't happy, fixed some of the clippy lints

Using mlua with axum

5

Since `Lua` isn't `Sync`, I am wondering if there's any way to use mlua with axum. I am trying to have one of the axum handlers receive a piece of...

# Description - [ ] When people use a local core, it's not obvious that the "IP" field should be "localhost" - [x] #376 - [ ] Notification panel is...

Add auto start in dashboard

2

# Description # Steps to reproduce (optional)

Integrating existing server directory to Lodestone

1

# Description Add the ability to import and copy existing servers to Lodestone. - [ ] REST API to perform the copy - [ ] Generate a .lodestone_config file for...

# Description https://developer.apple.com/documentation/apple-silicon/building-a-universal-macos-binary

Macro page text is overlapping

2

# Description # Steps to reproduce (optional)

# Description Need a proper implementation and documentation for Safe Mode. Safe Mode should aim to reduce or eliminate the possibility of remote code execution by a non-owner user. When...

# Description Currently if a text is too long for the car it just cuts off. We should make the text wrap and adjust the notification's height accordingly  This...