AmberYifan/capmix-marin-8b-base-select

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 10, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capmix-marin-8b-base-select is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was specifically trained on the capmix_marin-8b-base__mix_select dataset, indicating a specialized focus for particular selection tasks. With an 8192 token context length, it is designed for applications requiring processing of moderately long sequences.

Loading preview...

Model Overview

AmberYifan/capmix-marin-8b-base-select 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 on the capmix_marin-8b-base__mix_select dataset.

Key Training Details

The model was trained using the following hyperparameters:

  • Learning Rate: 1e-05
  • Batch Sizes: train_batch_size of 4, eval_batch_size of 8
  • Gradient Accumulation: 4 steps, leading to a total_train_batch_size of 64
  • Optimizer: ADAMW_TORCH with default betas and epsilon
  • LR Scheduler: Cosine type with 0.03 warmup steps
  • Epochs: 1

Intended Use Cases

While specific use cases are not detailed in the original model card, the fine-tuning on a 'select' dataset suggests its potential application in tasks involving selection, classification, or specific data extraction, building upon the base capabilities of the marin-8b-base model. Developers should consider its 8192 token context length for applications requiring processing of moderately sized inputs.

Finetunes
1 models