AmberYifan/capsd-marin-8b-base-math_ifd_b8000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 30, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-marin-8b-base-math_ifd_b8000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically fine-tuned on a mathematical instruction-following dataset, suggesting an optimization for mathematical reasoning and problem-solving tasks. It is designed for use cases requiring robust performance in numerical and logical operations.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-math_ifd_b8000_s0 is an 8 billion parameter language model derived from the marin-community/marin-8b-base architecture. This model has undergone a specific fine-tuning process using the capsd_marin-8b-base-n80000-numina__mix_math_ifd_b8000_s0 dataset.

Key Characteristics

  • Base Model: Fine-tuned from marin-community/marin-8b-base.
  • Parameter Count: 8 billion parameters.
  • Context Length: 8192 tokens.
  • Fine-tuning Focus: The model's training on a mathematically-oriented instruction-following dataset indicates a specialization in mathematical reasoning and problem-solving.

Training Details

The fine-tuning process utilized the following hyperparameters:

  • Learning Rate: 1e-05
  • Batch Size: A train_batch_size of 2 and eval_batch_size of 8, with a total_train_batch_size of 64 across 4 GPUs.
  • Optimizer: ADAMW_TORCH with default betas and epsilon.
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.

Potential Use Cases

This model is likely suitable for applications requiring strong mathematical capabilities, such as:

  • Solving mathematical problems.
  • Generating mathematical explanations or proofs.
  • Assisting with data analysis tasks involving numerical reasoning.

Finetunes
1 models