AmberYifan/capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_cap_b2000_s0
AmberYifan/capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_cap_b2000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically adapted for financial applications, leveraging a specialized dataset for enhanced performance in finance-related tasks. It is designed for use cases requiring a foundational understanding of financial text and data.
Loading preview...
Model Overview
This model, marin-8b-base_finance_cap_b2000_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 contexts.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Parameter Count: 8 billion parameters.
- Context Length: Supports a context length of 8192 tokens.
Training Details
The model underwent a fine-tuning process using the capsd_marin-8b-base-n6000-finance-fincot-finqa-clean6k__mix_finance_cap_b2000_s0 dataset. Key training hyperparameters included:
- Learning Rate: 1e-05
- Optimizer: ADAMW_TORCH
- Epochs: 1
- Batch Size: A total training batch size of 64 (with gradient accumulation).
Intended Use
While specific intended uses and limitations require further information, the fine-tuning on a finance-specific dataset suggests its utility in applications involving financial text analysis, question answering, or content generation within the finance domain. Users should be aware that detailed performance metrics and specific use cases are not yet fully documented.