Michael Yang

This seems to be an issue with the installed curl, not the install script.

ollama.ai's certificate is signed by Google. You can check with `openssl`. ``` $ openssl s_client -connect ollama.ai:443 /dev/null CONNECTED(00000006) --- Certificate chain 0 s:CN = ollama.ai i:C = US, O...

Hi @saul-jb, I'm not able to reproduce this on the commit you mentioned nor can I reproduce this with latest main. ``` $ ollama ls llama3 NAME ID SIZE MODIFIED...

> is it possible something isn't being escaped properly on the cp command in linux? nothing should need escaping. also the error is printed using the input name which sees...

If you're on linux, it'd be `/usr/share/ollama/.ollama/models`. In docker, it should be `/root/.ollama/models`

https://github.com/ollama/ollama/pull/4261 (rather an incarnation of that bug) is ~likely~ the culprit

> there isn't an example here, just instructions on how to create the example I don't see a distinction. Adding a sample toml file has marginal benefits while also being...

> ./ollama create localhost:6000/nous-hermes-2-mistral you're setting host and model so this name is indeed not valid. to set host, you must also set namespace

This is expected as the quantize docker image primarily targets inference models. It's untested for non-inference models like embedding models. Updating the container to support MistralModel doesn't seem to work;...

It's possible to set `OLLAMA_MODELS` and other environment variables with `launchctl`. See the [FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md#where-are-models-stored) for more details. Remember to restart the app afterwards for changes to take effect.