Palmyra
About
The Palmyra family of large language models (LLMs), developed by Writer, consists of several models tailored for diverse tasks, including Palmyra-Large, a 20-billion parameter causal decoder-only model trained on a massive dataset of over 800 billion tokens. This foundational model adeptly handles nuanced tasks such as sentiment classification and summarization. Writer has also introduced specialized models like Palmyra-Med for healthcare and Palmyra-Fin for finance, which achieve leading benchmark results in their respective areas. These models are ideally suited for precision in regulated industries and are available via Writer's platform, APIs, and open-model licenses. The Palmyra models stand out for their efficiency, utilizing cost-effective training techniques to maintain high accuracy even with relatively smaller parameter counts.