AmberYifan/capsd-marin-8b-base-math_dsir_b1000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 28, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-marin-8b-base-math_dsir_b1000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically trained on the capsd_marin-8b-base-n80000-numina__mix_math_dsir_b1000_s0 dataset, suggesting an optimization for mathematical reasoning and related tasks. With a context length of 8192 tokens, it is designed for applications requiring specialized mathematical processing.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-math_dsir_b1000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model has been specifically trained on the capsd_marin-8b-base-n80000-numina__mix_math_dsir_b1000_s0 dataset.

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.
  • Training Data: Specialized training on a dataset with "math_dsir" in its name, indicating a focus on mathematical domains.

Training Details

The model was trained using the following hyperparameters:

  • Learning Rate: 1e-05
  • Optimizer: ADAMW_TORCH
  • Batch Size: A total train batch size of 64 (2 per device with 8 gradient accumulation steps across 4 GPUs).
  • Epochs: Trained for 1 epoch.

Potential Use Cases

Given its specialized training, this model is likely suitable for:

  • Mathematical problem-solving.
  • Reasoning tasks involving numerical data.
  • Applications requiring understanding and generation of mathematical content.