AmberYifan/capsdnum-marin-8b-base-math_ppl_b8000_s0

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 16, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

The AmberYifan/capsdnum-marin-8b-base-math_ppl_b8000_s0 model is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model has been specifically optimized using the capsd_marin-8b-base-n80000-numina__mix_math_ppl_b8000_s0 dataset, suggesting a focus on mathematical reasoning and problem-solving tasks. With a context length of 8192 tokens, it is designed for applications requiring robust numerical and logical processing.

Loading preview...

Model Overview

The AmberYifan/capsdnum-marin-8b-base-math_ppl_b8000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base base model. This fine-tuning process utilized the capsd_marin-8b-base-n80000-numina__mix_math_ppl_b8000_s0 dataset, indicating a specialized focus on mathematical and numerical processing tasks.

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: The training dataset suggests an optimization for mathematical reasoning and problem-solving.

Training Details

The model was trained with the following hyperparameters:

  • Learning Rate: 1e-05
  • Batch Size: A total training batch size of 64 (2 per device with 8 gradient accumulation steps across 4 GPUs).
  • Optimizer: AdamW with default betas and epsilon.
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.

Intended Use Cases

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

  • Mathematical problem-solving.
  • Numerical analysis.
  • Tasks involving logical reasoning with quantitative data.

Further details on specific intended uses, limitations, and comprehensive evaluation data are not provided in the current model card.