Aloe: A Family of Fine-tuned Open Healthcare LLMs

arXiv:2405.01886v1 Announce Type: new
Abstract: As the capabilities of Large Language Models (LLMs) in healthcare and medicine continue to advance, there is a growing need for competitive open-source models that can safeguard public interest. With the increasing availability of highly competitive open base models, the impact of continued pre-training is increasingly uncertain. In this work, we explore the role of instruct tuning, model merging, alignment, red teaming and advanced inference schemes, as means to improve current open models. To that …

abstract advance arxiv availability capabilities cs.ai cs.cl family healthcare impact language language models large language large language models llms medicine open-source models pre-training public training type uncertain