LokiLM: Technical Report
Keywords: large language model
Abstract: In this work, we introduce LokiLM, a 1.4B parameter large language model trained on 500B tokens. Our model performs strongly in natural language reasoning tasks and achieves state-of-the-art performance among models with 1.5B parameters or less. LokiLM is trained using multi-teacher knowledge distillation and high-quality training data to achieve benchmark results competitive with larger models trained on significantly more tokens. We support these findings by introducing steps to avoid benchmark contamination and overfitting throughout our development process. Despite its promising performance, LokiLM exhibits a concerning amount of hallucinations and scores poorly on the TruthfulQA benchmark, so we do not release the model publicly.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8871
Loading