Tonic

ha! i sure do , [here's me](https://twitter.com/josephpollack/) . Noor's doesnt work well where she is , so that's why [she prefers linked-in](https://www.linkedin.com/in/aymen-noor-55t22/) hope that's okay :-)

i can help if you are reaching otu to outside collaborators for this :-)

> Task Decomposition, i would be quite keen + will make the time if you maybe might consider working together on a `prominent example using JSON mode` but maybe for...

> Ok. Really dumb question. I've got a draft notebook for JSON mode. How do share it here? Notebooks aren't allowed as attachments. Apologies, very new this kind of thing....

groq is a "drop in replacement" just configure it based on the above, and try it out

https://huggingface.co/spaces/Tonic/EasyYI/blob/main/app.py you can make a connector like this , based on the endpoint you're using / serving , which basically replicates an openai api (easy) then use it accordingly

✨✨ Here's [an AI-assisted sketch of how you might approach this issue](https://copilot-workspace.githubnext.com/argilla-io/distilabel/pull/793?shareId=455fe1a3-9bee-4f5a-bae5-a530e869f800) saved by @Josephrp using Copilot Workspace v0.22 Topic Use Openai Async Client Before - `src/distilabel/llms/openai.py` uses the OpenAI...

big thanks to the maintainers for this cool new thing i discovered here called Github Workspace , it's amazing and very cool ! 👍🏻 🥇

> Thanks for the PR @Josephrp! If the 01.AI relies on the OpenAI client then maybe we can do like in the `AnyscaleLLM` or `TogetherLLM` in which we create a...

i'll use it today and tomorrow to make NER and Embeddings training pipelines like what you have in tutorials, didnt really find a nice place to make a unique examples...