Skip to content

README.md

Latest commit

 

History

History
64 lines (45 loc) · 2.97 KB

README.md

File metadata and controls

64 lines (45 loc) · 2.97 KB
Raw

IndusQ-1.1B: State-of-the-art large language model useful on a variety of language understanding and generation tasks

Indus is today a 1.2 billion parameter model and has been supervised fine tuned for Hindi and dialects.

This is based on the implementation of IndusQ-1.1B found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Quick Start

Use our lightweight command-line interface to inspect IndusQ-1.1B:

pip install qai_hub_models_cli # (the CLI is also available with the qai-hub-models package)

# Inspect the model's metadata
qai-hub-models info IndusQ-1.1B

# Print performance and accuracy metrics
qai-hub-models perf IndusQ-1.1B
qai-hub-models numerics IndusQ-1.1B

# Pre-exported assets are not available to download for this model due to
# licensing restrictions. Continue to the next section to export it yourself.

See the CLI README for the full list of commands and filters.

Getting Started

This model is available for purchase. Please contact us to learn more about licensing options.

References

Community

Usage and Limitations

This model may not be used for or in connection with any of the following applications:

  • Accessing essential private and public services and benefits;
  • Administration of justice and democratic processes;
  • Assessing or recognizing the emotional state of a person;
  • Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
  • Education and vocational training;
  • Employment and workers management;
  • Exploitation of the vulnerabilities of persons resulting in harmful behavior;
  • General purpose social scoring;
  • Law enforcement;
  • Management and operation of critical infrastructure;
  • Migration, asylum and border control management;
  • Predictive policing;
  • Real-time remote biometric identification in public spaces;
  • Recommender systems of social media platforms;
  • Scraping of facial images (from the internet or otherwise); and/or
  • Subliminal manipulation