AmberYifan/capsd-marin-8b-base-code_ppl_b12000_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_ppl_b12000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base, with a context length of 8192 tokens. This model is specifically optimized for code-related tasks, having been trained on a specialized code dataset. Its primary strength lies in code generation and understanding, making it suitable for development-focused applications.

Loading preview...

Model Overview

AmberYifan/capsd-marin-8b-base-code_ppl_b12000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. It has a context window of 8192 tokens, making it capable of processing moderately long sequences of text or code.

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.
  • Optimization: The model has undergone fine-tuning on the capsd_marin-8b-base-n80000-opc__mix_code_ppl_b12000_s0 dataset, indicating a specialization towards code-related tasks.

Training Details

The fine-tuning process involved specific hyperparameters:

  • Learning Rate: 1e-05
  • Optimizer: ADAMW_TORCH with default betas and epsilon.
  • LR Scheduler: Cosine decay with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.
  • Batch Size: A total training batch size of 64 (2 per device across 4 GPUs with 8 gradient accumulation steps).

Intended Use Cases

Given its fine-tuning on a code-centric dataset, this model is likely best suited for applications requiring:

  • Code generation.
  • Code completion.
  • Code understanding and analysis.
  • Assisting developers with programming tasks.

Finetunes
1 models