Patrick Devine

There isn't a way to tell that right now unfortunately. The server will just block each of the connections while one is being serviced, and then each of those connections...

Hey @adriens , this seems to be working fine at least locally. Llama Index added us to a new "ollama" package. I don't have access to Kaggle/Killercoda though, but: ```...

@adriens it's `from llama_index.llms.ollama import Ollama`. They changed the package.

hey @adriens , you should follow the docs from llama index here: https://docs.llamaindex.ai/en/stable/examples/llm/ollama/ You'll need to `pip install llama-index-llms-ollama` first.

It's definitely confusing right now not knowing that a model is a instruct model vs. for text completions. We are tracking that in some other places, so I'm going to...

I know this is an older issue, but let's track this in #4618. I do have adapters working w/ NPZ files created w/ MLX (#5524). EDIT: On second thought, let's...

In linux the models should be stored under `/usr/share/ollama`. The `~/.ollama` directory in Linux is used for other things such as your key pair and other assets required to use...

Closing this as a dupe of #1749

@hsiehgeorge and @Ca-ressemble-a-du-fake are you still encountering the issue?

@Ca-ressemble-a-du-fake I think this is almost certainly a different issue than the original one. Would you be able to create a new issue and include the logs? Preferably w/ the...