Patrick Devine

I think `--workspace` would be really complicated for most people to know, however I believe this should be fixed already (i.e. it won't execute from a tmp directory) on Windows.

As @L-A mentioned, just start the REPL twice (i.e. in one terminal start `ollama run gemma` and in the other terminal `ollama run llama3`. If you want both to run...

Hey guys, it's happening when you hit the context size (which is set to 2048). You can increase the context as a work around w/ `/set parameter num_ctx 8192` but...

> Is it specific to llama.cpp or ollama or the model itself? The model is fine. The problem happens because the context by default is set to 2048 and is...

Hi @frankhart2018 thanks for the issue. The `pull` command already pulls multiple chunks of the _same_ blob in parallel, which is why the we often saturate network connections (particularly with...

> Hi @pdevine can you point me to the part of the source where this happens? Also if this happens, can this be exposed possibly using a flag to specify...

@smxlong sorry about this. We switched over the repo to `ollama/ollama` from `jmorganca/ollama` and didn't update all of the code. I have a fix which I'm testing out and I'll...

cc @dhiltgen

For passing a file, you can do that in the REPL by passing the filename which the client will read and then pass to the API. The API already supports...

I'm realizing on rereading my response that I was not super clear. The API doesn't read the file per se, but you can pass images along in the request. In...