Lukas Pfahler

Log File reads: ``` Jun 16 14:22:42 Nintendo64 TrayPlay[37443]: Error: Error Domain=com.alamofire.error.serialization.response Code=-1011 "Request failed: unauthorized (401)" UserInfo={NSLocalizedDescription=Request failed: unauthorized (401), NSErrorFailingURLKey=https://api.spotify.com/v1/tracks/26ATkgJARDJGaqBN2Vd32v, com.alamofire.serialization.response.error.data=, com.alamofire.serialization.response.error.response= { URL: https://api.spotify.com/v1/tracks/26ATkgJARDJGaqBN2Vd32v } { Status...

Oh, and that also happend on the pypi version, not only on the pre-release

We're training models on German instructions over here: https://github.com/Whadup/llamarr_alpaca/

This is just the JSON standard way of storing unicode. If you load it with python, you'll get nice unicode text. You could also store it as unicode-json with `json.dump(data,...

Hi, yeah I wasn't sure about how to share the model, but if you send me a PM I think I could share my checkpoint. Using the cleaned dataset sounds...

Nice, this indeed fixes the key error. thanks

https://github.com/huggingface/optimum/blob/56aabbebd0ce532f82f566a2a946769cee3bb36b/optimum/utils/normalized_config.py#L254 Add `"phi3": NormalizedTextConfig` in this dict and you seem to be all set for phi3-mini

@BenjaminBossan Thanks for looking into it already! Your three points are on my agenda, I will give you a ping when I commit the changes.

> > It is not exactly what you asked, but wouldn't 'agent.iter' work in this case? > > from pydantic_ai import CallToolsNode > > > > agent = Agent(...) >...

> My use case is the ability to decide when I need to have 'intelligence' to pick specific tools vs just running a DAG of tools without the agent picking....