kshitijagrwl / pii-extractor-llm

PII Data Extraction from Text

  • Public
  • 157 runs
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $0.00010 to run on Replicate, or 10000 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on CPU hardware. Predictions typically complete within 1 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Your very own LLM helper that extracts Personal Identifiable Information (PII).

Trained to specifically recognize Indian names and addresses.

Currently there are 2 options
- m1_base trained on data with names, father names and DOB only.
- m1_large trained on data with names, father names, DOB and addresses.

Few use cases

  1. Extract names and address from long pieces of texts
  2. Redact PII information before sending data to publically hosted LLM APIs