AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b2000_s0
AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b2000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically adapted for financial question answering tasks, leveraging the capsd_marin-8b-base-n11082-finance-convfinqa-fullscore__mix_finance_random_b2000_s0 dataset. It is optimized for specialized applications requiring financial domain understanding and conversational capabilities.
Loading preview...
Model Overview
This model, AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b2000_s0, is an 8 billion parameter language model. It is a fine-tuned version 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: 8 billion parameters.
- Context Length: Supports an 8192-token context window.
- Specialization: Optimized for financial question answering, trained on the
capsd_marin-8b-base-n11082-finance-convfinqa-fullscore__mix_finance_random_b2000_s0dataset.
Training Details
The model was trained with a learning rate of 1e-05, a train_batch_size of 2, and gradient_accumulation_steps of 8, resulting in a total_train_batch_size of 64. It utilized a cosine learning rate scheduler with 0.03 warmup steps over 1 epoch. The training was conducted on a multi-GPU setup with 4 devices.
Intended Use Cases
This model is designed for tasks requiring specialized understanding and generation within the financial domain, particularly for conversational financial question answering. Its fine-tuning on a finance-specific dataset suggests suitability for applications like financial analysis, reporting, and interactive financial information retrieval.