Doc-to-LoRA is an open-source tool that enables rapid creation of LoRA adapters from documents or text, allowing large language models to internalize new knowledge or skills without full retraining. It is designed for AI researchers and developers seeking efficient LLM adaptation.
In the Fine-tuning & training space, Doc-to-LoRA takes a focused approach. It focuses on updating LLMs with new knowledge or skills is slow and resource-intensive without efficient adapter generation. It is built as an open-source project for AI researchers and developers. Doc-to-LoRA is open source under the Apache-2.0 license. It runs on the web and the command line.
It is developed by Sakana AI, and the product first shipped in 2025. Development happens publicly on GitHub with 1.3k stars. PulseGate's similarity index finds few close equivalents — Doc-to-LoRA occupies a relatively distinct niche. Key capabilities include loRA adapter generation, document-to-adapter, and text-to-adapter.
Latest indexed changes and source events
Other apps tracked under the same category.
