SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.04421 · NeurIPS · 2024

Variational Low-Rank Adaptation Using IVON

Mohammad Khan, Daniel Cremers, Thomas Möllenhoff, Yuesong Shen, Nico Daheim, Bai Cong, Rio Yokota

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
team-approx-bayes/ivon-lora canonical 0 of 4
FunctionStatusWhere it lives
calculate_metrics Not yet run team-approx-bayes/ivon-lora/utils.py
pointer only (licence: NONE) · get_code("436f4c309d8668cf")
get_model_with_lora Not yet run team-approx-bayes/ivon-lora/model.py
pointer only (licence: NONE) · get_code("409ef49365463547")
get_processed_datasets Not yet run team-approx-bayes/ivon-lora/data.py
pointer only (licence: NONE) · get_code("ebd2a7cc208c71af")
get_raw_datasets Not yet run team-approx-bayes/ivon-lora/data.py
pointer only (licence: NONE) · get_code("d8835e01bd280f77")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW by the Improved Variational Online Newton (IVON) algorithm to finetune large language models. For Llama-2 with 7 billion parameters, IVON improves the accuracy over AdamW by 2.8% and expected calibration error by 4.6%. The accuracy is also better than the other Bayesian alternatives, yet the cost is lower and the implementation is easier. Our work provides additional evidence for the effectiveness of IVON for large language models. The code is available at https://github.com/team-approx-bayes/ivon-lora.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.04421")
get_code_for_paper("2411.04421")
have("2411.04421")

Connect an agent — have() is free.