Llama-v2-7B-Chat: Optimized for Qualcomm Devices

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 pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. 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.

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

2. --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.

3. --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))

Getting Started

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

See our repository for Llama-v2-7B-Chat on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Input sequence length for Prompt Processor: 1024
• Context length: 1024
• Precision: w4a16 + w8a16 (few layers)
• Supported languages: 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. For Llama-v2-7B-Chat, both values in the range are the same since prompt length is 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)
Llama-v2-7B-Chat	QNN_CONTEXT_BINARY	w4a16	Snapdragon® 8 Elite Mobile	1024	17.94	1.44 - 1.44
Llama-v2-7B-Chat	QNN_CONTEXT_BINARY	w4a16	Snapdragon® X Elite	1024	11.2	1.919 - 1.919
Llama-v2-7B-Chat	QNN_CONTEXT_BINARY	w4a16	Snapdragon® 8 Gen 3 Mobile	1024	12.85	1.49583 - 1.49583

License

• The license for the original implementation of Llama-v2-7B-Chat can be found here.

References

• LLaMA: Open and Efficient Foundation Language Models
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.

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