AmberYifan/capsdnum-marin-8b-base-math_cap_b4000_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_cap_b4000_s0 model 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_cap_b4000_s0 dataset, indicating a specialization in mathematical or numerical reasoning tasks. With a context length of 8192 tokens, it is designed for applications requiring processing of moderately long sequences, particularly within its specialized domain.

Loading preview...

Model Overview

AmberYifan/capsdnum-marin-8b-base-math_cap_b4000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model has been specifically adapted through training on the capsd_marin-8b-base-n80000-numina__mix_math_cap_b4000_s0 dataset.

Training Details

The model was trained using the following key hyperparameters:

  • Learning Rate: 1e-05
  • Batch Size: A train_batch_size of 2 with gradient_accumulation_steps of 8, resulting in a total_train_batch_size of 64.
  • Optimizer: ADAMW_TORCH with betas=(0.9, 0.999) and epsilon=1e-08.
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.
  • Hardware: Distributed training across 4 GPUs.

Potential Use Cases

Given its fine-tuning on a dataset with "math_cap" and "numina" in its name, this model is likely specialized for:

  • Mathematical problem-solving.
  • Numerical reasoning tasks.
  • Applications requiring understanding and generation of content related to quantitative data.

Finetunes
1 models