Now anyone can train themselves a reasoning AI for just $450 – Sky-T1 is open source

This week, researchers from the Sky Computing Lab at the University of California, Berkeley launched the Sky-T1-32B-Preview artificial intelligence model. We are talking about a neural network with reasoning ability that can compete with OpenAI o1 in a number of key indicators.

Image Source: Lee Campbell/Unsplash

Apparently, the Sky-T1 is the first model to support open source reasoning, which will allow it to be replicated from scratch. The developers published the data set that was used to train the algorithm, as well as other data necessary to run the AI ​​model.

One of the main features of the algorithm is that its training does not require significant costs. “Remarkably, Sky-T1-32B-Preview was trained for less than $450,” the developers wrote on their blog. Thus, they clearly demonstrated that it is possible to create an AI model with high-level reasoning abilities without significant financial investment.

Until recently, the cost of training a large language model with comparable characteristics was measured in millions of dollars. It was possible to significantly reduce costs through the use of synthetic data, i.e. data generated by other neural networks. For example, the Palmyra X 004 algorithm recently released by Winter was trained on synthetic data and cost the developers $700 thousand.

Unlike many AI algorithms, reasoning models effectively check facts, which allows them to provide more accurate answers and are less likely to make mistakes that mislead users. In addition, reasoning models typically take longer to generate an answer to a query compared to conventional AI algorithms. However, reasoning models are generally more reliable, especially in areas such as physics, mathematics and science.

According to reports, the developers leveraged Alibaba’s QwQ-32B-Preview reasoning model to create the initial Sky-T1 training dataset. The data was then converted using GPT-4o-mini from OpenAI into a more accurate format. The training process for Sky-T1 with 32 billion parameters took about 19 hours, for which 8 Nvidia H100 graphics accelerators were used.

«Going forward, we will focus on developing more efficient models that maintain strong reasoning performance, as well as exploring best practices to improve the efficiency and accuracy of models during testing. Stay tuned as we make progress on these exciting initiatives,” the developers wrote in a blog post.

admin

Share
Published by
admin

Recent Posts

Apple to Change OS Numbering: iOS 26 to Come This Year Instead of iOS 19

Apple is preparing a large-scale rebranding of its line of operating systems. This was reported…

19 hours ago

The Witcher 3: Wild Hunt has matched Skyrim in sales, and every third Cyberpunk 2077 owner has bought the Phantom Liberty add-on

The cult open-world action role-playing game The Witcher 3: Wild Hunt, which recently celebrated its…

19 hours ago

Analysts predict absurd surge in PC sales due to Trump’s indiscriminate tariffs

IDC analysts unexpectedly concluded that the current unstable tariff policy of the US administration will…

19 hours ago

Adata XPG Mars 980 Blade PCIe 5.0 SSD Review: Affordable SM2508 Flagship

The first consumer SSDs with PCIe 5.0 interface appeared on the market about two years…

19 hours ago

Electronic Arts to Focus on Key Franchises — Black Panther Action Game Cancelled, Cliffhanger Games Studio Closed

The IGN portal, citing internal correspondence from Electronic Arts, reported that the American publisher has…

19 hours ago

Study: Apple C1 mobile modem falls short of Qualcomm modems in terms of connection quality in difficult conditions

A study by Cellular Insights Inc. found that Qualcomm's mobile modems perform better than Apple's…

2 days ago