Fusechat: Knowledge fusion of chat models
While training large language models (LLMs) from scratch can indeed lead to models with
distinct capabilities and strengths, it incurs substantial costs and may lead to redundancy in …
distinct capabilities and strengths, it incurs substantial costs and may lead to redundancy in …
Decoding-time language model alignment with multiple objectives
Aligning language models (LMs) to human preferences has emerged as a critical pursuit,
enabling these models to better serve diverse user needs. Existing methods primarily focus …
enabling these models to better serve diverse user needs. Existing methods primarily focus …
Strong copyright protection for language models via adaptive model fusion
The risk of language models unintentionally reproducing copyrighted material from their
training data has led to the development of various protective measures. In this paper, we …
training data has led to the development of various protective measures. In this paper, we …
Cool-fusion: Fuse large language models without training
C Liu, X Quan, Y Pan, L Lin, W Wu, X Chen - arXiv preprint arXiv …, 2024 - arxiv.org
We focus on the problem of fusing two or more heterogeneous large language models
(LLMs) to facilitate their complementary strengths. One of the challenges on model fusion is …
(LLMs) to facilitate their complementary strengths. One of the challenges on model fusion is …