Self Denial

> > Requiring 2FA and requiring a phone number are two very different things. > > I dont remember the exact words on the warning... i think it require phone...

This would be an immensely useful feature but even better with functionality inside [api/client.go](https://github.com/ollama/ollama/blob/main/api/client.go) maybe something like `/api/upgrade/model` and `/api/upgrade/all`?

View of additional metadata would be helpful but we may want to postpone any auto-update feature as it may be implemented upstream. See https://github.com/ollama/ollama/pull/2179

Very nice, thanks!

I've intended to communicate my experience in this regard eventually and this ticket is a good opportunity. To date, I've almost exclusively used the Docker container with Podman (self-built and...

> What is the purpose of this connection to a remote ip? This IP resolves to a CloudFront Philadelphia address: ``` $ host 18.238.4.28 28.4.238.18.in-addr.arpa domain name pointer server-18-238-4-28.phl51.r.cloudfront.net. ```...

I've confirmed that `--env LITELLM_LOCAL_MODEL_COST_MAP="True"` successfully eliminates the LiteLLM startup connection. When used along with #1419, there are no connections on startup except for your configured LLM models (in my...

> It might be worth making this the default @Darin755 I agree! PR created: #1436 > Nice one @lainedfles ! @justinh-rahb Thanks, I'm having a lot of fun with this...

Found another HuggingFace connection to download the WhisperModel. See #1499

Great idea. I think it would be beneficial to cache this litellm file anyway which contains useful information including max_tokens: https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json While it may not be useful for local Ollama...