AmberYifan/capsd-medcase-marin-8b-base-medicine_cap_b2000_s0
AmberYifan/capsd-medcase-marin-8b-base-medicine_cap_b2000_s0 is an 8 billion parameter language model fine-tuned from marin-community/marin-8b-base. This model is specifically adapted for medical applications, having been trained on the capsd_marin-8b-base-n13092-medicine-medcase__mix_medicine_cap_b2000_s0 dataset. It is designed to enhance performance in medical contexts, leveraging its 8192-token context length for processing detailed medical information.
Loading preview...
Overview
This model, AmberYifan/capsd-medcase-marin-8b-base-medicine_cap_b2000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base architecture, specifically adapted for applications within the medical domain.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Parameter Count: 8 billion parameters.
- Context Length: Supports an 8192-token context window.
- Specialization: Optimized for medical use cases through fine-tuning on a dedicated medical dataset.
Training Details
The model was trained using the following hyperparameters:
- Learning Rate: 1e-05
- Batch Size: A total training batch size of 64 (with
train_batch_size: 2andgradient_accumulation_steps: 8). - Optimizer: ADAMW_TORCH with default betas and epsilon.
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
- Epochs: Trained for 1 epoch.
Intended Use
This model is intended for tasks requiring understanding and generation within the medical field, benefiting from its specialized fine-tuning. Developers should consider its medical domain focus when evaluating its suitability for specific applications.