AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b2000_s0
The AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b2000_s0 model is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically optimized for financial question answering tasks, leveraging the capsd_marin-8b-base-n11082-finance-convfinqa-fullscore__mix_finance_ppl_b2000_s0 dataset. It is designed to excel in conversational financial QA, providing specialized performance in this domain with an 8192 token context length.
Loading preview...
Model Overview
This model, AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b2000_s0, is an 8 billion parameter language model fine-tuned from the marin-community/marin-8b-base architecture. It has been specifically adapted for financial applications, focusing on conversational financial question answering (ConvFinQA).
Key Capabilities
- Specialized Financial QA: Fine-tuned on the
capsd_marin-8b-base-n11082-finance-convfinqa-fullscore__mix_finance_ppl_b2000_s0dataset, indicating a strong focus on financial domain understanding and response generation. - Base Model Enhancement: Builds upon the
marin-8b-basemodel, suggesting a robust foundation for its specialized tasks. - Training Details: The training process involved a learning rate of 1e-05, a total batch size of 64 (with gradient accumulation), and a cosine learning rate scheduler over 1 epoch.
Training Environment
The model was trained using:
- Transformers 5.7.0
- Pytorch 2.13.0+cu130
- Datasets 4.0.0
- Tokenizers 0.22.2
Intended Use Cases
This model is particularly well-suited for applications requiring accurate and context-aware responses within the financial sector, especially for conversational interfaces or automated financial analysis tools.