|
--- |
|
license: llama3 |
|
datasets: |
|
- taddeusb90/finbro-v0.1.0 |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- finance |
|
--- |
|
|
|
Fibro v0.1.0 Llama 3 8B Model with 1Million token context window |
|
====================== |
|
|
|
Model Description |
|
----------------- |
|
|
|
The Fibro Llama 3 8B model is language model optimized for financial applications. This model aims to enhance financial analysis, automate data extraction, and improve financial literacy across various user expertise levels. It utilizes a massive 1 million token context window. |
|
This is just a sneak peek into what's coming, and future releases will be done periodically consistently improving it's performance. |
|
|
|
![FinBro](https://huggingface.co/taddeusb90/finbro-v0.1.0-llama-3-8B-instruct-1m-POSE/resolve/main/437210082_369067905507560_2052449041654631065_n.png) |
|
|
|
Training: |
|
----------------- |
|
|
|
The model is still training, I will be sharing new incremental releases while it's improving so you have time to play around with it. |
|
![Loss](https://huggingface.co/taddeusb90/finbro-v0.1.0-llama-3-8B-instruct-1m-POSE/resolve/main/W%26B%20Chart%2006_05_2024%2C%2015_57_42.png) |
|
![Evaluation Loss](https://huggingface.co/taddeusb90/finbro-v0.1.0-llama-3-8B-instruct-1m-POSE/resolve/main/W%26B%20Chart%2006_05_2024%2C%2015_58_01.png) |
|
|
|
What's Next? |
|
----------- |
|
|
|
* **Extended Capability:** Continue training on the 8B model as it hasn't converged yet as I only scratched the surface here and transitioning to scale up with a 70B model for deeper insights and broader financial applications. |
|
* **Dataset Expansion:** Continuous enhancement by integrating more diverse and comprehensive real and synthetic financial data. |
|
* **Advanced Financial Analysis:** Future versions will support complex financial decision-making processes by interpreting and analyzing financial data within agentive workflows. |
|
* **Incremental Improvements:** Regular updates are made to increase the model's efficiency and accuracy and extend it's capabilities in financial tasks. |
|
|
|
Model Applications |
|
------------------ |
|
|
|
* **Information Extraction:** Automates the process of extracting valuable data from unstructured financial documents. |
|
* **Financial Literacy:** Provides explanations of financial documents at various levels, making financial knowledge more accessible. |
|
|
|
|
|
How to Use |
|
---------- |
|
|
|
Here is how to load and use the model in your Python projects: |
|
|
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_name = "taddeusb90/finbro-v0.1.0-llama-3-8B-instruct-1m-POSE" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
text = "Your financial query here" |
|
|
|
inputs = tokenizer(text, return_tensors="pt") |
|
|
|
outputs = model.generate(inputs['input_ids']) |
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
Training Data |
|
------------- |
|
|
|
The Fibro Llama 3 8B model was trained on the Finbro Dataset, an extensive compilation of over 300,000 entries sourced from Investopedia and Sujet Finance. This dataset includes structured Q&A pairs, financial reports, and a variety of financial tasks pooled from multiple datasets. |
|
|
|
The dataset can be found [here](https://huggingface.co/datasets/taddeusb90/finbro-v0.1.0) |
|
|
|
This dataset will be extended to contain real and synthetic data on a wide range of financial tasks such as: |
|
- Investment valuation |
|
- Value investing |
|
- Security analysis |
|
- Derivatives |
|
- Asset and portfolio management |
|
- Financial information extraction |
|
- Quantitative finance |
|
- Econometrics |
|
- Applied computer science in finance |
|
and much more |
|
|
|
Notice |
|
-------- |
|
|
|
Please exercise caution and use it at your own risk. I assume no responsibility for any losses incurred if used. |
|
|
|
|
|
Licensing |
|
--------- |
|
|
|
This model is released under the [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/LICENSE). |
|
|
|
|
|
Citation |
|
-------- |
|
|
|
If you use this model in your research, please cite it as follows: |
|
|
|
|
|
```bibtex |
|
@misc{ |
|
finbro_v0.1.0-llama-3-8B-1m-POSE, |
|
author = {Taddeus Buica}, |
|
title = {Fibro Llama 3 8B Model for Financial Analysis}, |
|
year = {2024}, |
|
journal = {Hugging Face repository}, |
|
howpublished = {\url{https://huggingface.co/taddeusb90/finbro-v0.1.0-llama-3-8B-instruct-1m-POSE}} |
|
} |
|
``` |
|
|
|
Special thanks to the folks from AI@Meta for powering this project with their awesome models. |
|
|
|
Contact |
|
-------- |
|
|
|
If you would like to connect, share ideas, feedback, help support bigger models or even develop your own custom finance model on your private dataset let's talk on [LinkedIn](https://www.linkedin.com/in/taddeus-buica-1009a965/) |
|
|
|
References |
|
-------- |
|
|
|
[[1](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)] Llama 3 Model Card by AI@Meta, Year: 2024 |
|
|
|
[[2](https://huggingface.co/datasets/sujet-ai/Sujet-Finance-Instruct-177k)] Sujet Finance Dataset |
|
|
|
[[3](https://huggingface.co/datasets/FinLang/investopedia-instruction-tuning-dataset)] Dataset Card for investopedia-instruction-tuning |