Kainoa Kanter

[Feature request] update models from CLI

5

When an update is available to an already installed model, something like `ollama pull` (without an argument) or `ollama update` would be great!

With Ollama, it's common to have many models. Being able to change the model for every workspace/chat would be great.

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] I'd like to have...

feat: custom themes

2

Custom themes would be nice. Here's an example of one I made: https://github.com/rose-pine/ollama-webui 

Fixes start.sh to have execution permission & to use script env

feat: ✨ bun support, backend lint

1

- Adds bun support - Changes default commands to use bun - Adds formatting and linting for backend - Moves frontend CI to Bun - Adds backend CI - Moves...

Making this issue just to make sure that lints should eventually get back-on-track. The actions in `.github/workflows` should be renamed from `*.disabled` back to `*.yml`

Crash upon loading any model with the ROCm GPU

2

Stacktrace: ``` llm_load_vocab: special tokens definition check successful ( 259/32000 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000...

Crash upon installing patch with LSPosed

2

I tried the latest release with v9.9.1 with LSPatch, but it crashes upon startup