AmberYifan/capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_ppl_b1000_s0

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 16, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

The AmberYifan/capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_ppl_b1000_s0 model is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. It was specifically trained on a financial dataset, capsd_marin-8b-base-n6000-finance-fincot-finqa-clean6k__mix_finance_ppl_b1000_s0, to enhance its performance in financial contexts. This model is optimized for financial language understanding and generation tasks, leveraging its 8192 token context length for processing detailed financial information.

Loading preview...

Model Overview

This model, AmberYifan/capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_ppl_b1000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base architecture, specifically adapted for financial applications.

Key Characteristics

  • Base Model: Fine-tuned from marin-community/marin-8b-base.
  • Parameter Count: Features 8 billion parameters.
  • Context Length: Supports an 8192-token context window.
  • Specialization: The model has undergone fine-tuning on a specialized financial dataset, capsd_marin-8b-base-n6000-finance-fincot-finqa-clean6k__mix_finance_ppl_b1000_s0, indicating an optimization for financial language processing.

Training Details

The training process involved specific hyperparameters:

  • Learning Rate: 1e-05
  • Batch Sizes: train_batch_size of 2, eval_batch_size of 8.
  • Gradient Accumulation: 8 steps, leading to a total_train_batch_size of 64.
  • Optimizer: ADAMW_TORCH with default betas and epsilon.
  • Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
  • Epochs: Trained for 1 epoch.

Intended Use

While specific intended uses and limitations are not detailed in the provided information, the model's fine-tuning on a financial dataset suggests its suitability for tasks requiring an understanding of financial terminology, reports, and data. Developers should consider its specialized training for applications within the finance domain.

Finetunes
1 models