AmberYifan/capsd-marin-8b-base-code_random_b10000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 4, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AmberYifan/capsd-marin-8b-base-code_random_b10000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically adapted for code-related tasks, having been trained on the capsd_marin-8b-base-n80000-opc__mix_code_random_b10000_s0 dataset. It features a context length of 8192 tokens and is intended for applications requiring code generation or understanding.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-code_random_b10000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model has been specialized through training on a custom dataset, capsd_marin-8b-base-n80000-opc__mix_code_random_b10000_s0, indicating a focus on code-related applications. It supports a context length of 8192 tokens.

Training Details

The model underwent a single epoch of fine-tuning with a learning rate of 1e-05. Key training hyperparameters included a train_batch_size of 2, an eval_batch_size of 8, and a gradient_accumulation_steps of 8, resulting in a total_train_batch_size of 64. The optimizer used was ADAMW_TORCH with default betas and epsilon, and a cosine learning rate scheduler was employed with 0.03 warmup steps. The training was conducted using a multi-GPU setup with 4 devices.

Intended Use Cases

Given its fine-tuning on a code-centric dataset, this model is likely best suited for tasks such as:

  • Code generation
  • Code completion
  • Code summarization
  • Assisting with programming-related queries