Inside Writer
– 5 min read
Introducing Palmyra-Med and Palmyra-Fin
Setting a new bar for medical and financial model performance with Writer LLMs
Today, we’re excited to add two new domain-specific models, Palmyra-Med and Palmyra-Fin, to our family of Writer-built LLMs. These models bring unparalleled accuracy to medical and financial generative AI applications — outperforming other comparable models, like GPT-4, Med-PaLM-2, and Claude 3.5 Sonnet, and passing the CFA level III exam. Their specialization makes them uniquely adept at powering AI workflows in two industries that are known for their strict regulation and compliance standards.
Palmyra-Med and Palmyra-Fin join a roster of top-ranking LLMs built by Writer — including Palmyra-X a general-purpose model, Palmyra-Vision for image analysis, and many more. Combined with the Writer full-stack generative AI platform — which includes integrated graph-based RAG technology, AI guardrails, and a suite of developer tools — these models make building knowledgeable and compliant medical and financial AI apps quick and easy.
Both Palmyra-Med and Palmyra-Fin are available with Writer via our API, No-code tools, and the Writer Framework. They’re also accessible under an open-model license — allowing you to easily deploy them locally or to your private cloud. For more information on licensing for commercial use cases, contact us at sales@writer.com.
Improving patient outcomes with record-breaking medical accuracy
Palmyra-Med is the latest version of our healthcare model and the most accurate in the market. In our testing, Palmyra-Med averaged 85.9% across all medical benchmarks, beating the runner-up, Med-PaLM-2 by close to 2 percentage points. Med-PaLM-2 only achieved those results when five examples were provided, compared to Palmyra’s zero-shot performance.
The result is an accurate, reliable model that can help improve patient outcomes and research through its ability to tackle complex medical tasks in a range of disciplines:
- Clinical knowledge and anatomy: Achieving scores of 90.9% in MMLU Clinical Knowledge and 83.7% in MMLU Anatomy, Palmyra-Med-70b demonstrates a rich understanding of clinical procedures and human anatomy. This makes it exceptionally useful for supporting diagnostic accuracy and treatment planning in medical settings.
- Genetics and college medicine: Scoring 94.0% in Medical Genetics and 84.4% in College Medicine, the model excels in interpreting genetic data and applying complex medical knowledge, crucial for genetic counseling and medical education.
- Biomedical research: With a 80% performance in PubMedQA, Palmyra-Med-70b proves its capability to effectively extract and analyze information from biomedical literature, aiding in research and evidence-based medical practices.
Palmyra-Med-70b delivers superior medical benchmark performance at a price of $10 per 1M output tokens — substantially less expensive than larger frontier models like GPT-4, which costs $60 for the same amount of output. This makes Palmyra-Med-70b an attractive option for medical professionals and institutions and illustrates a key advantage of domain-specific models.
The Writer full-stack generative AI platform is used by the world’s leading Fortune 50 healthcare companies, as well as innovators like Vizient, CirrusMD and Medisolv, to help improve patient outcomes with powerful generative AI applications that are infused with deep medical knowledge.
Bringing unparalleled financial expertise to Writer
Adopting generative AI in the financial sector comes with its own unique obstacles: lengthy financial statements, complex terminology, and nuanced market analysis. By combining a well-curated set of financial training data with custom fine-tuning instruction data, we’ve built a highly accurate financial LLM that can power use cases like:
- Financial trend analysis and forecasts: Examining market dynamics and developing forecasts for financial performance.
- Investment analysis: Producing detailed evaluations of firms, industries, or economic markers.
- Risk evaluation: Assessing the potential hazards linked to different financial tools or approaches.
- Asset allocation strategy: Recommending investment mixes tailored to individual risk preferences and financial objectives.
To put Palmyra-Fin’s expertise to the test, we tasked it with passing the CFA Level III exam. The model received a 73% on the multiple-choice section of a CFA Level III sample test, making it the first model that can pass the exam. To put this achievement in perspective: passing the CFA Level III is one of the highest distinctions in the investment management profession. The average passing score over the last 11 years has been 60%, and typically less than half of all test takers receive a passing score.
Palmyra-Fin’s performance is a stark improvement over other general-purpose models like GPT-4, which have previously reported a 33% performance on the exam.
We also ran Palmyra-Fin through the long-fin-eval benchmark test to evaluate its performance across a variety of real-world financial use cases. It outperformed popular models like Claude 3.5 Sonnet, GPT-4o, and Mixtral-8x7b — showcasing the model’s skills and financial expertise.
Combined with the Writer full-stack generative AI platform, Palmyra LLMs have enabled leading financial companies like Vanguard and Franklin Templeton to reinvent their workflows with generative AI. Palymra-Fin-70B will deepen the expertise of the Writer platform, allowing our customers across fintech, wealth management, and investment banking to build more sophisticated AI apps, features, and products.
Getting started with Palmyra LLMs
Domain-specific LLMs will be at the forefront of AI innovation, transforming how industries build specialized AI applications. Writer is pioneering this movement by creating models like Palmyra-Med and Palmyra-Fin — models with deep, sector-specific expertise, exceptionally well-suited for enterprise use cases. These targeted models promise not only greater accuracy and efficiency but also improved data management and regulatory compliance. As they enable faster innovation and provide tailored solutions to unique market challenges, Palmyra-Med and Palmyra-Fin are set to offer businesses and developers a distinct competitive advantage, heralding a new era of intelligent, sustainable AI solutions.
If you’re building an AI application in the medical or financial field, we encourage you to check out Writer. You can try out the models with $10 in free API credits, or experiment with them on NVIDIA and Hugging Face.