githubnemo
daf335f503
The current state of the PEFT docs is not one of structure and I was constantly annoyed that whenever I wanted to change something there were several places that needed touching and they all felt disconnected. So this is my attempt at structuring the docs. Some of these ideas are quite old (discussed in 01/2025) but are still valid. I've removed most of the code guides without replacement. That's not ideal, I think we should have code examples but I'm think they should be method-focused. Maybe one general example of a training workflow is sufficient because most methods follow the same scheme. All details from the method guides (prompting, lora, oft/boft, etc.) are now integrated into the respective method pages instead. I would have hesitated to do this if these guides would have integrated information about the adapters but they didn't. I think it makes a lot more sense to have one place for each method to gather examples/tips/recommendations and that is now the `package_refernce/<method>` page. This page now also hosts a small space that shows the MetaMathQA (and potentially other) benchmark results highlighted for that method. I've moved the LoRA initializations to `package_reference/lora#Initialization` and converted the init methods to `<hfoption>`-tags. This collapses them to a list but may reduce searchability through the document - at least firefox is not able to search 'through' the option tabs. This also doesn't make them appear in the ToC and people specifically searching for, say, PiSSA won't find it directly. I think that's OK though, since the search is able to locate it. The quicktour is a bit more detailed about what happens under the hood (quick doesn't have to mean simplistic) and includes some new visualizations. I hope that we can integrate more visualizations in the future where it makes sense. * Remove PEFT method space + front page buttons The space was not that useful anymore since most methods are compatible with most models. The front page buttons are, at least temporarily, with the exception of the quicktour and method overview buttons. I like the visuals but there should only be elements that are useful. --------- Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com> Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
3.0 KiB
BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
BEFT is a parameter efficient fine-tuning algorithm (PEFT) that only fine-tunes the added bias terms of value projections from pretrained transformer models. BEFT demonstrates that fine-tuning the added bias terms of value projections from pretrained transformers generally leads to a higher downstream performance in low-data regimes than fine-tuning the added bias terms of query/key projections.
BEFT currently has the following tradeoffs:
Pros:
- BEFT requires far fewer parameters than LoRA, while maintaining competitive or superior performance across tasks in low-data regimes.
Cons:
- In high-data regimes, BEFT may show limited effectiveness compared to LoRA and full-parameters fine-tuning.
If your use case belongs to the high-data regime, consider other PEFT methods such as LoRA.
The abstract from the paper is:
Fine-tuning the bias terms of large language models (LLMs) has the potential to achieve unprecedented parameter efficiency while maintaining competitive performance, particularly in low-data regimes. However, the link between fine-tuning different bias terms (i.e., bq, bk, and bv in the query, key, or value projections) and downstream performance remains largely unclear to date. In this paper, we investigate the link between fine-tuning bq, bk, and bv with the performance of the downstream task. Our key finding is that directly fine-tuning bv generally leads to higher downstream performance in low-data regimes, in comparison to bq and bk. We extensively evaluate this unique property across a wide range of LLMs spanning encoder-only and decoder-only architectures up to 6.7B parameters (including bias-free LLMs). Our results provide strong evidence for the effectiveness of directly fine-tuning bv across various downstream tasks.
Benchmark overview
API
BeftConfig
autodoc tuners.beft.config.BeftConfig
BeftModel
autodoc tuners.beft.model.BeftModel