Downloads · 30 days
7
6% of all-time downloads
Ashish-kar-007/Gemma3-270m-financeQA-finetuned-merged-16bit
Gemma3-270m-financeQA-finetuned-merged-16bit is a text generation model from Ashish-kar-007. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Short Description: A GEMMA3-270M model fine-tuned sequentially on NewsQA and the Financial Q&A dataset for answering questions in both news and financial domains.
Downloads · 30 days
7
6% of all-time downloads
All-time downloads
126
Public
Parameters
268M
574 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors536 MB · 93%
From the Hugging Face model README
Short Description:
A GEMMA3-270M model fine-tuned sequentially on NewsQA and the Financial Q&A dataset for answering questions in both news and financial domains.
Abstract:
This model is designed to answer questions based on news articles and financial documents. It was first fine-tuned on the NewsQA dataset for general news comprehension, then further fine-tuned on a financial Q&A dataset to improve performance in financial contexts.
Primary Use Cases:
Out-of-Scope Use Cases / Limitations:
Ethical Considerations / Biases:
Datasets Used:
@inproceedings{trischler2017newsqa,
title={NewsQA: A Machine Comprehension Dataset},
author={Trischler, Adam and Wang, Tong and Yuan, Xingdi and Harris, Justin and Sordoni, Alessandro and Bachman, Philip and Suleman, Kaheer},
booktitle={Proceedings of the 2nd Workshop on Representation Learning for NLP},
year={2017}
}
Citation:
@misc{saeedian2023financialqa,
title={Financial Q&A 10k Dataset},
author={Yousef Saeedian},
year={2023},
howpublished={\url{https://www.kaggle.com/datasets/yousefsaeedian/financial-q-and-a-10k}}
}
This gemma3_text model was trained 2x faster with Unsloth and Huggingface's TRL library.