Phi-3.5-mini-instruct: Optimized for Mobile Deployment

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

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 model is an implementation of Phi-3.5-mini-instruct found here.

More details on model performance across various devices, can be found here.

Model Details

• Model Type: Text generation
• Model Stats:
  • Input sequence length for Prompt Processor: 128
  • Context length: 4096
  • Number of parameters: None
  • Precision: w4a16 + w8a16 (few layers)
  • Num of key-value heads: 8
  • Information about the model parts: Prompt Processor and Token Generator are split into 4 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
  • Prompt processor model size: 2.16 GB
  • Token generator model size: 2.16 GB
  • Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
  • Supported languages: English, Arabic, Chinese, Dutch, French, German, Italian, Russian, Spanish, Ukranian
  • Minimum QNN SDK version required: 2.28.2
  • 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).
  • Response Rate: Rate of response generation after the first response token.

Model	Device	Chipset	Target Runtime	Response Rate (tokens per second)	Time To First Token (range, seconds)
Phi-3.5-mini-instruct	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	13.01	0.1469056 - 4.7009792
Phi-3.5-mini-instruct	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	6.2	0.185833 - 5.946656
Phi-3.5-mini-instruct	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	14.73	0.1195948 - 3.8270336

Deploying Phi-3.5-mini-instruct on-device

Please follow the LLM on-device deployment tutorial.

License

• The license for the original implementation of Phi-3.5-mini-instruct can be found here.
• The license for the compiled assets for on-device deployment 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

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