AmberYifan/capsd-marin-8b-base-code_random_b4000_s0

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 15, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-marin-8b-base-code_random_b4000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was trained on a mixed code dataset, utilizing a cosine learning rate scheduler and AdamW optimizer. It is designed for general language tasks, with a specific focus on code-related applications due to its training data.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-code_random_b4000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This iteration specifically leverages the capsd_marin-8b-base-n10000__mix_code_random_b4000_s0 dataset, indicating a focus on code-related data during its fine-tuning process.

Training Details

The model was trained using the following key hyperparameters:

  • Learning Rate: 1e-05
  • Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
  • Batch Size: A total training batch size of 64 (achieved with train_batch_size: 1 and gradient_accumulation_steps: 16 across 4 GPUs).
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.

Potential Use Cases

Given its fine-tuning on a mixed code dataset, this model is likely suitable for tasks involving:

  • Code generation
  • Code completion
  • Code understanding and analysis
  • General natural language processing tasks where code context might be beneficial.

Finetunes
1 models