AmberYifan/capsd-medmcqa-marin-8b-base-medicine_cap_b2000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 13, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-medmcqa-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 question answering, having been trained on the capsd_marin-8b-base-n80000-medicine-medmcqa__mix_medicine_cap_b2000_s0 dataset. It is designed to excel in medical domain understanding and response generation, making it suitable for applications requiring specialized medical knowledge.

Loading preview...

Model Overview

This model, AmberYifan/capsd-medmcqa-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 medical domain tasks.

Key Capabilities

  • Medical Question Answering: The model has been fine-tuned on a specialized dataset, capsd_marin-8b-base-n80000-medicine-medmcqa__mix_medicine_cap_b2000_s0, indicating its primary strength in understanding and responding to medical queries.
  • Domain-Specific Knowledge: Its training on a medical dataset suggests enhanced performance and accuracy for tasks within the healthcare and medical fields.

Training Details

The model was trained with a learning rate of 1e-05, using an AdamW optimizer. The training involved a total of 1 epoch with a batch size of 64 (achieved with gradient accumulation). The training utilized 4 multi-GPU devices. The framework versions used include Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.

Good For

  • Applications requiring specialized medical knowledge.
  • Tasks involving medical question answering or information retrieval within the medical domain.