Skip to content

Latest commit

 

History

History
92 lines (66 loc) · 4.14 KB

README.md

File metadata and controls

92 lines (66 loc) · 4.14 KB

Qualcomm® AI Hub Models

Llama-v2-7B-Chat: State-of-the-art large language model useful on a variety of language understanding and generation tasks

Llama 2 is a family of LLMs. The "Chat" at the end indicates that the model is optimized for chatbot-like dialogue. The model is quantized to w4a16(4-bit weights and 16-bit activations) and part of the model is quantized to w8a16(8-bit weights and 16-bit activations) making it suitable for on-device deployment. For Prompt and output length specified below, the time to first token is Llama-PromptProcessor-Quantized's latency and average time per addition token is Llama-TokenGenerator-KVCache-Quantized's latency.

This is based on the implementation of Llama-v2-7B-Chat found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance accross various devices, can be found here.

Sign up to start using Qualcomm AI Hub and run these models on a hosted Qualcomm® device.

Deploying Llama 2 on-device

Please follow the LLM on-device deployment tutorial.

Sample output prompts generated on-device

  1. --prompt "what is gravity?" --max-output-tokens 30
-------- Response Summary --------
Prompt: what is gravity?
Response: Hello! I'm here to help you answer your question. Gravity is a fundamental force of nature that affects the behavior of objects with mass
  1. --prompt "what is 2+3?" --max-output-tokens 30
-------- Response Summary --------
Prompt: what is 2+3?
Response: Of course! I'm happy to help! The answer to 2+3 is 5.
  1. --prompt "could you please write code for fibonacci series in python?" --max-output-tokens 100
-------- Response Summary --------
Prompt: could you please write code for fibonacci series in python?
Response: Of course! Here is an example of how you could implement the Fibonacci sequence in Python:
```
def fibonacci(n):
    if n <= 1:
        return n
    else:
        return fibonacci(n-1) + fibonacci(n-2)
```
You can test the function by calling it with different values of `n`, like this:
```
print(fibonacci(5))

License

  • The license for the original implementation of Llama-v2-7B-Chat can be found here.
  • The license for the compiled assets for on-device deployment can be found here

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