AmberYifan/capsd-marin-8b-base-math_qurating_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_qurating_b1000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically optimized for mathematical tasks, having been trained on the capsd_marin-8b-base-n80000-numina__mix_math_qurating_b1000_s0 dataset. It leverages a context length of 8192 tokens and is designed for applications requiring strong mathematical reasoning capabilities.

Loading preview...

Model Overview

This model, AmberYifan/capsd-marin-8b-base-math_qurating_b1000_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 enhanced performance in mathematical domains.

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: Optimized for mathematical tasks through fine-tuning on a specialized dataset.

Training Details

The model underwent a single epoch of training with a learning rate of 1e-05, utilizing a cosine learning rate scheduler. Training was performed with a total batch size of 64 across 4 GPUs, employing AdamW_Torch as the optimizer. The fine-tuning process focused on the capsd_marin-8b-base-n80000-numina__mix_math_qurating_b1000_s0 dataset.

Intended Use Cases

This model is particularly suitable for applications requiring robust mathematical problem-solving and reasoning. Its fine-tuning on a math-specific dataset suggests improved accuracy and understanding in numerical and logical tasks compared to general-purpose models of similar size.