# SmolTalk: distilabel pipelines
We released [SmolTalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) the SFT dataset used for building SmolLM2 instruct models. It was created with [distilabel](https://github.com/argilla-io/distilabel) and you can find the synthetic data pipelines here.

<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/JLTEbnsBQ_qY032mxFzgC.png" width="800"/>
<p><em>Comparison of models finetuned on SmolTalk and Orca AgentInstruct 1M. For more details, refer to the <a href="https://huggingface.co/datasets/HuggingFaceTB/smoltalk" target="_blank">dataset card</a>.</em></p>
</div>

> [!NOTE]
> This section is still in WIP. We will upload the rest of the pipelines soon. Thanks for your patience!