AmberYifan/capsd-medmcqa-marin-8b-base-medicine_ppl_b2000_s0
The AmberYifan/capsd-medmcqa-marin-8b-base-medicine_ppl_b2000_s0 model is an 8-billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically optimized for medical question answering, having been trained on the capsd_marin-8b-base-n80000-medicine-medmcqa__mix_medicine_ppl_b2000_s0 dataset. It is designed to excel in medical domain tasks, particularly those involving medical multiple-choice questions, leveraging its 8192-token context length.
Loading preview...
Model Overview
AmberYifan/capsd-medmcqa-marin-8b-base-medicine_ppl_b2000_s0 is an 8-billion parameter language model derived from the marin-community/marin-8b-base architecture. This model has undergone specialized fine-tuning to enhance its performance within the medical domain.
Key Capabilities
- Medical Domain Specialization: Fine-tuned on the
capsd_marin-8b-base-n80000-medicine-medmcqa__mix_medicine_ppl_b2000_s0dataset, indicating a strong focus on medical knowledge and question answering. - Base Model: Built upon
marin-community/marin-8b-base, suggesting a robust foundation for language understanding and generation. - Training Configuration: Utilized a learning rate of 1e-05, a total training batch size of 64, and a cosine learning rate scheduler with 0.03 warmup steps over 1 epoch.
When to Use This Model
This model is particularly suited for applications requiring deep understanding and generation of medical text, especially for tasks related to medical question answering. Its fine-tuning on a specific medical dataset makes it a strong candidate for use cases such as:
- Answering medical multiple-choice questions.
- Assisting with medical information retrieval.
- Developing tools for medical education or clinical decision support where domain-specific knowledge is crucial.