Microsoft has recently unveiled a new small language model called Phi-3 mini, which offers superior performance to OpenAI’s GPT-3.5 while running on modern smartphones. This updated version of Microsoft’s lightweight language model has been trained with 3.3 billion tokens from larger and more advanced datasets compared to its predecessor, Phi-2, which was trained with 1.4 billion tokens. The model has 3.8 billion parameters and can fit on a modern smartphone, taking up approximately 1.8GB of memory and can be quantified to 4 bits.
The researchers tested Phi-3 mini on an iPhone 14 with an A16 Bionic chip, where it ran natively and offline at a speed of over 12 tokens per second. The overall performance of this model is comparable to larger models like Mixtral 8x7B and GPT-3.5.
Phi-3 mini uses a transformer decoder architecture that supports 4K text length and is based on a block structure similar to Meta’s Llama 2, supporting packages developed for Llama 2. This makes it ideal for conversational chat formats and aligns with Microsoft’s values of robustness and security.
In addition to Phi-3 mini, Microsoft has also trained two other models in the same family: Phi-3 medium with 14 billion parameters and Phi-3 small with 7 billion parameters, both trained with 4.8 billion tokens.
Microsoft is focused on providing efficient and secure language models for a variety of applications, including customer service, virtual assistants, and content generation.
Overall, the introduction of Phi-3 mini marks a significant step forward in the development of lightweight language models that can run on modern smartphones while offering high levels of performance comparable to larger models.
:quality(75)/cloudfront-us-east-1.images.arcpublishing.com/elcomercio/BBNQJJJEXJEVPKBWNA6N25Z2GA.jpeg)
