Finma 7b Full

🚀 FinMA-7B-full

FinMA-7B-full is a comprehensive financial large language model designed to understand complex financial language and concepts, enhancing performance in downstream financial tasks.

🚀 Quick Start

FinMA-7B-full is a comprehensive financial large language model (LLM) developed as part of the PIXIU project. It's crafted to understand intricate financial language and concepts. Fine - tuned to follow natural language instructions, it boosts performance in downstream financial tasks. Specifically, it's trained with full instruction data from the PIXIU dataset, covering both NLP and prediction tasks, enabling it to handle a broader range of financial tasks.

✨ Features

Other Models in the PIXIU Project

In addition to FinMA-7B-full, the PIXIU project includes two other models:

• FinMA-7B-NLP: Trained only on the NLP tasks of the PIXIU dataset, it specializes in tasks like sentiment analysis, news headline classification, named entity recognition, and question answering.
• FinMA-30B: A larger version of FinMA, fine - tuned on the LLaMA - 30B model. Similar to FinMA-7B-NLP, it's trained with NLP instruction data.

💻 Usage Examples

Basic Usage

You can use the FinMA-7B-full model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model:

from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained('ChanceFocus/finma-7b-full')
model = LlamaForCausalLM.from_pretrained('ChanceFocus/finma-7b-full', device_map='auto')

In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The device_map='auto' argument is used to automatically use the GPU if it's available.

Advanced Usage

You can also use the model through the Hugging Face Inference API. This allows you to generate text without having to set up your own inference environment. The model can be loaded on the Inference API on - demand.

📄 License

FinMA-7B-NLP is licensed under MIT. For more details, please see the MIT file.

📚 Documentation

This model is part of the PIXIU project, an open - source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financial LLMs. The goal is to continually push forward the open - source development of financial artificial intelligence (AI).

For more information, you can visit the PIXIU project on GitHub.

📚 Citation

If you use FinMA-7B-NLP in your work, please cite the PIXIU paper:

@misc{xie2023pixiu,
 title={PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance}, 
 author={Qianqian Xie and Weiguang Han and Xiao Zhang and Yanzhao Lai and Min Peng and Alejandro Lopez-Lira and Jimin Huang},
 year={2023},
 eprint={2306.05443},
 archivePrefix={arXiv},
 primaryClass={cs.CL}
}

Additional Information