---
library_name: pytorch
license: other
tags:
- llm
- generative_ai
- android
pipeline_tag: text-generation

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/indus_1b/web-assets/model_demo.png)

# IndusQ-1.1B: Optimized for Qualcomm Devices

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](https://huggingface.co/nickmalhotra/ProjectIndus).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/indus_1b) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started

This model is available for purchase. Please [contact us](mailto:ai-hub-support@qti.qualcomm.com) to learn more about licensing options.

## Getting Started
This model is available for purchase. Please [contact us](mailto:ai-hub-support@qti.qualcomm.com) to learn more about licensing options.


## Model Details

**Model Type:** Model_use_case.text_generation

**Model Stats:**
- Input sequence length for Prompt Processor: 128
- Max context length: 1024
- Number of parameters: 1B
- Precision: w4a16 + w8a16 (few layers)
- Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
- Minimum QNN SDK version required: 2.27.7
- Supported languages: Hindi and English.
- TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (1024 tokens).
- Response Rate: Rate of response generation after the first response token.

## Performance Summary
| Model | Runtime | Precision | Chipset | Context Length | Response Rate (tokens per second) | Time To First Token (range, seconds)
|---|---|---|---|---|---|---
| IndusQ-1.1B | QNN_CONTEXT_BINARY | w4a16 | Snapdragon® 8 Elite Mobile | 4096 | 74.6 | 0.028561 - 0.228489
| IndusQ-1.1B | QNN_CONTEXT_BINARY | w4a16 | Qualcomm® Dragonwing™ Q-8750 | 4096 | 74.6 | 0.028561 - 0.228489



## References
* [Project Indus: A Foundational Model for Indian Languages](https://www.techmahindra.com/makers-lab/indus-project/)
* [Source Model Implementation](https://huggingface.co/nickmalhotra/ProjectIndus)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).

## 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