sohi-g's picture
Update README.md
a9c47cd
|
raw
history blame
968 Bytes
metadata
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 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