Alexey Shevchenko

> https://github.com/deskflow/deskflow/wiki/Workarounds#macOS-Lockout-on-wakeup-if-server-died thats a great idea, great. I think I've missed to mention that ~/.wakeup is actually not a built-in MacOS feature, it require demon available via homebrew: https://formulae.brew.sh/formula/sleepwatcher thanks!...

Similar experience on M1 mac, it just consumes all the memory - regardless of 12b or 27b (on 32Gb)

> Just curious, did you use from terminal or over API? @sapphirepro over terminal it is indeed better but still, 12b model consumes 21Gb while from API it consumes 29Gb...

@chand1012 I think symlinks shouldn't be skipped but rather resolved.

@chand1012 @openhands-agent great. It seems the major issue in the diff that "tabs" replaced with "spaces" for the entire `prompt/prompt.go`. If you can preserve the code style of the original...

I have AirPods Pro that came out on a launch with certain deffects. It could be that later versions that does not have those deffects are "2nd generation". Just an...

This one makes sense. Otherwise, I have found a workaround: ```bash python -m electron_inject -s -b - /path/to/app --remote-allow-origins='*' ```

When trying to download huggingface model: ``` export OLLAMA_NUM_PARALLEL=1 export OLLAMA_MAX_LOADED_MODELS=2 export OLLAMA_FLASH_ATTENTION=1 export OLLAMA_EXPERIMENT=client2 launchctl setenv OLLAMA_KV_CACHE_TYPE "$OLLAMA_KV_CACHE_TYPE"; launchctl setenv OLLAMA_NUM_PARALLEL "$OLLAMA_NUM_PARALLEL" launchctl setenv OLLAMA_MAX_LOADED_MODELS "$OLLAMA_MAX_LOADED_MODELS" launchctl setenv OLLAMA_FLASH_ATTENTION...