Supervised fine tuning on curated data is reinforcement learning

Re:Supervised fine tuning on curated data is reinforcement l... by TheTaytay on Tuesday July 29, 2025 @10:46PM (#44730509)

Thanks for this - I’ve spent the last hour reading your docs and blog. I like the primitives you’ve exposed in your APO, and particularly like the decision to separate out the structured inputs from the prompt when you record an LLM call, so I can finally perform optimizations and evals on past calls.

Quick question : you mentioned unsloth in the blog post. Which of the fine tuning providers mentioned is using unsloth under the hood?

[ Parent | on HN ]

Re:Supervised fine tuning on curated data is reinforcement l... by GabrielBianconi on Tuesday July 29, 2025 @11:07PM (#44730602)

[I'm his coworker.] We ran Unsloth ourselves on a GPU-by-the-hour server. We have a notebook in the repository showing how to query historical data and use it with Unsloth.

It's a WIP PR that we plan to merge soon: https://github.com/tensorzero/tensorzero/pull/2273

[ Parent | on HN ]