December 18, 2023
1 min read

Microsoft launches robust AI ‘small language model’ for researchers

Phi-2 is an ideal playground for researchers, including for exploration around mechanistic interpretability, safety improvements, or fine-tuning experimentation on a variety of tasks…reports Asian Lite News

Microsoft has released its newest compact “small language model” titled Phi-2 that continues to perform at par or better than certain larger open-source Llama 2 models with less than 13 billion parameters.

Over the past few months, the Machine Learning Foundations team at Microsoft Research has released a suite of small language models (SLMs) called “Phi” that achieve remarkable performance on a variety of benchmarks.

The first model, the 1.3 billion parameter Phi-1 achieved state-of-the-art performance on Python coding among existing SLMs (specifically on the HumanEval and MBPP benchmarks).

“We are now releasing Phi-2, a 2.7 billion-parameter language model that demonstrates outstanding reasoning and language understanding capabilities, showcasing state-of-the-art performance among base language models with less than 13 billion parameters,” the company said in an update.

Phi-2 is an ideal playground for researchers, including for exploration around mechanistic interpretability, safety improvements, or fine-tuning experimentation on a variety of tasks.

“We have made Phi-2 available in the Azure AI Studio model catalog to foster research and development on language models,” said Microsoft.

The massive increase in the size of language models to hundreds of billions of parameters has unlocked a host of emerging capabilities that have redefined the landscape of natural language processing.

However, a question remains whether such emergent abilities can be achieved at a smaller scale using strategic choices for training, e.g., data selection.

“Our line of work with the Phi models aims to answer this question by training SLMs that achieve performance on par with models of much higher scale (yet still far from the frontier models),” said Microsoft.

The company has also performed extensive testing on commonly used prompts from the research community.

“We observed a behaviour in accordance with the expectation we had given the benchmark results,” said the tech giant.

ALSO READ-Microsoft to invest $3.2 bn in UK to drive future AI growth

Previous Story

BNP cannot win public support through arson, says Hasina

Next Story

Bangladesh War of Liberation is bedrock of our ties, says envoy

Latest from Tech LITE

Accel Puts India’s AI Power in the Spotlight

Under the theme “Engineering India’s AI Advantage,” the exclusive, invite-only event will bring together leading AI founders, researchers, tech CXOs, policymakers, and global investors….reports Asian Lite News Global venture capital firm Accel

Trump plans nuclear energy push

This move comes amid a surge in power demand driven by rapid advances in artificial intelligence (AI)….reports Asian Lite News U.S. President Donald Trump is preparing to sign a series of executive

Tech giants unite for Stargate UAE

This marks the beginning of a strategic partnership involving G42, OpenAI, Oracle, NVIDIA, Cisco, and SoftBank Group, all coming together under the banner of international AI leadership. In a landmark announcement that

Universities Embrace AI Future

Echoing this sentiment, Professor Esameldin Agamy, Chancellor of UoS, emphasised the value of academic partnerships in nurturing innovation across the UAE’s education sector The American University of Sharjah (AUS) hosted the concluding
Go toTop

Don't Miss

Microsoft bis adieu to mice, keyboards, webcams

The move ends the legacy of Microsoft-branded PC hardware launched

India’s Growing Role in Generative AI Adoption

The region is likely to see GenAI spending soar to