AmberYifan/capsd-marin-8b-base-code_cap_b14000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 5, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-marin-8b-base-code_cap_b14000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was trained with a learning rate of 1e-05 and a total batch size of 64 over one epoch, specifically on the capsd_marin-8b-base-n80000-opc__mix_code_cap_b14000_s0 dataset. Its primary application is likely in code-related tasks, given the dataset used for fine-tuning.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-code_cap_b14000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model was specifically adapted using the capsd_marin-8b-base-n80000-opc__mix_code_cap_b14000_s0 dataset, indicating a specialization towards code-related applications.

Training Details

The fine-tuning process involved the following key hyperparameters:

  • Learning Rate: 1e-05
  • Optimizer: ADAMW_TORCH with betas=(0.9, 0.999) and epsilon=1e-08
  • LR Scheduler: Cosine type with 0.03 warmup steps
  • Batch Size: A total training batch size of 64 (achieved with train_batch_size: 2 and gradient_accumulation_steps: 8 across 4 GPUs)
  • Epochs: 1

Potential Use Cases

Given its fine-tuning on a dataset explicitly mentioning "code_cap", this model is likely optimized for:

  • Code generation
  • Code completion
  • Code understanding and analysis

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

Finetunes
1 models