peft

546927de - Add Orthogonal Subspace Fine-Tuning (OSF) Tuner for Parameter-Efficient Continual Learning (#2685)

Add Orthogonal Subspace Fine-Tuning (OSF) Tuner for Parameter-Efficient Continual Learning (#2685) This adds a new parameter-efficient fine-tuning method called **Orthogonal Subspace Fine-Tuning (OSF)** to the PEFT library. OSF enables continual learning in LLMs by freezing the high-rank subspace of weight matrices and fine-tuning only the low-rank directions. This approach constrains updates to be orthogonal to previously important directions, thereby mitigating catastrophic forgetting without increasing parameter count. Tracked in [PEFT Issue #2648](https://github.com/huggingface/peft/issues/2648) **Notes** * The current implementation does not include layerwise importance-based rank estimation (e.g., cosine similarity of inputs and activations), but can be added in future iterations * Unmerging is not supported, as the original weights are decomposed and modified in-place * Compared to LoRA, OSF performs a constrained update over the original weight matrix without introducing new trainable parameters, maintaining exact model architecture post-training **Background** This implementation is based on the method described in our paper: Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning