raft-ft is an MIT-licensed Python package for Retrieval-Augmented Fine-Tuning. It helps developers build persona-focused datasets and fine-tune language models using retrieval-augmented data, with integrations for common LLM and machine learning workflows.
raft-ft sits in PulseGate's Fine-tuning & training category. It focuses on fine-tuning language models on retrieval-augmented persona datasets without building the data pipeline from scratch. raft-ft is an open-source project aimed at machine learning engineers and AI researchers. The project is open source (MIT). raft-ft is available on the command line, and it can be self-hosted.
raft-ft first shipped in 2026. Among its 5 catalogued features are persona datasets, retrieval augmentation, and model fine-tuning.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match