README.md

---
tags:
- autotrain
- text-classification
- lam
language:
- en
widget:
- text: >-
    Neither this act nor any other act relating to said Cherokee Indians of
    Robeson County shall be construed so as to impose on said Indians any
    powers, privileges, rights or immunities, or
- text: >-
    That Section one hundred and twenty-two eightythree of the General Statutes
    of North Carolina is hereby amended by striking out the word insane in the
    catch line and in lines two, four, nine and fifteen and inserting in lieu
    thereof the words mentally disordered.
datasets:
- biglam/on_the_books
co2_eq_emissions:
  emissions: 0.2641096478393395
license: mit
library_name: transformers
metrics:
- accuracy
- f1
- recall
---

# Model Trained Using AutoTrain

- Problem type: Binary Classification
- Model ID: 64771135885
- CO2 Emissions (in grams): 0.2641

## Validation Metrics

- Loss: 0.057
- Accuracy: 0.986
- Precision: 0.988
- Recall: 0.992
- AUC: 0.998
- F1: 0.990

## Usage
This model is trained on a dataset of historical documents related to Jim Crow laws in the United States.
The model was developed by drawing on the expertise of scholars and analyzing legal texts from various states, with the goal of identifying similarities between different states' Jim Crow laws. 
As such, this model may be useful for researchers or policymakers interested in understanding the history of racial discrimination in the US legal system.

The easiest way to use this model locally is via the [Transformers](https://huggingface.co/docs/transformers/index) library [pipelines for inference](https://huggingface.co/docs/transformers/pipeline_tutorial). 

Once you have [installed transformers](https://huggingface.co/docs/transformers/installation), you can run the following code. 
This will download and cache the model locally and allow you to make predictions on text input. 


```
from transformers import pipeline

classifier = pipeline('text-classification', "biglam/autotrain-beyond-the-books")
classifier(text)
```

This will return predictions in the following format:

```
[{'label': 'no_jim_crow', 'score': 0.9718555212020874}]
```