AI Toolkit adds LLM fine-tuning support, first with a Qwen2.5-Omni-7B LoRA for music captioning

ostrisai · x · 2026-09-17

ostrisai added initial LLM fine-tuning support to AI Toolkit, starting with Omni models — first up is Qwen2.5-Omni-7B.

The author trained a LoRA to improve music captioning and transcription, and these LoRAs can be plugged into the toolkit's dataset captioner alongside default cloud models, enabling a local fine-tune-plus-auto-labeling workflow.

Original post →

More from coding & agent

coding & agent channel →