Phi-3.5-mini-instruct

Phi-3.5-Mini-Instruct: Optimized for Qualcomm Devices

Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

This is based on the implementation of Phi-3.5-Mini-Instruct 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 Phi-3.5-mini-instruct on-device

Please follow the LLM on-device deployment tutorial.

Getting Started

Below are pre-exported model assets ready for deployment.

For more device-specific assets and performance metrics, visit Phi-3.5-Mini-Instruct on Qualcomm® AI Hub.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Context lengths: 512, 1024, 2048, 3072, 4096
• Input sequence length for Prompt Processor: 128
• Measurement details: The model was benchmarked using a short prompt only. Since the model asset supports multiple context lengths, the short prompt may have triggered lower context lengths. The upper bound of the TTFT is approximated based on the performance of the model with the short prompt, and the assumption that TTFT scales linearly with the context length.
• Minimum QAIRT SDK: 2.43.1
• Number of parameters: 3.8B
• Quantization Type: w4a16 + w8a16 (few layers)
• Response Rate: Rate of response generation after the first response token.
• 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 (4096 tokens).

Performance Summary

License

• The license for the original implementation of Phi-3.5-Mini-Instruct can be found here.

References

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• 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