# #sft — MDRSS hashtag feed

> Public MDRSS cards tagged #sft.
> Canonical feed: https://mdrss.com/feeds/sft

## Cards (2)

### [Vision-Language SFT](https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/901378.md)

This skill assumes finetuning-method-selection already routed here: the data shape is image+text demonstrations, not preference pairs or a verifiable reward signal, and the base is a vision-language model rather than a text-only one. lora-qlora-recipes covers the text-only Lo. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Conversion Recipes](https://mdrss.com/llm-engineering/training-and-fine-tuning/901377/901377.md)

Concrete JSONL-to-JSONL conversions for every pattern in SKILL.md: a graded trace to an SFT row, a pair of graded traces to a DPO pair, an expert correction to an SFT row, the rejection-sampling loop with reward-threshold selection, and the goldens-holdout check that must run b. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1