|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- briefai/LongShort-Dataset |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- pytorch |
|
- mistral |
|
- Gen-AI |
|
- Finance |
|
- KPI Extraction |
|
--- |
|
# LongShort-Mistral-7B |
|
- Model creator: [Brief AI](https://huggingface.co/briefai) |
|
- Original model: [Mistral 7B Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) |
|
|
|
### Model Description |
|
|
|
This model leverages Mistral-7B architecture to extract financial KPIs from the earnings call documents. |
|
|
|
## Prompt template: LongShort-Mistral-7B |
|
|
|
``` |
|
[INST]Given the context, answer the question. |
|
|
|
### Question: |
|
Extract all the finance-based performance indicators and evaluation metrics. |
|
|
|
### Context: |
|
{context} |
|
|
|
### Answer: |
|
[/INST] |
|
|
|
``` |
|
|
|
## Uses |
|
|
|
Financial KPI Extraction |
|
|
|
|
|
## Evaluation Results |
|
|
|
Accuracy of the model = KPIs Found / ((KPIs Found) + (KPIs Not Found)) |
|
|
|
LongShort-Mistral-7B is giving 48% accuracy on a validation set of 10% of the original training dataset. |
|
|
|
## Thanks |
|
|
