AI developer platform, Hugging Face has settled a lawsuit with FrendliAI, a Korean startup which accused it of patent ...

A team of math and AI researchers at Microsoft Asia has designed and developed a small language model (SLM) that can be used to solve math problems. The group has posted a paper on the arXiv preprint ...

Phi-4 and an rStar-Math paper suggest that compact, specialized models can provide powerful alternatives to the industry’s largest systems.

Shital Shah, a member of the technical staff at Microsoft AI, took to X (formerly known as Twitter) to announce the availability of the Phi-4 AI model's weights on Hugging Face. The AI model is ...

Microsoft has released the code for Phi-4, a small language model that can generate text and solve mathematical problems.

Phi-4, which has outperformed larger competitors in reasoning tasks, is now freely available under an MIT License.

Phi-4 demonstrates that smaller, well-designed models can achieve comparable or superior results compared with larger models.

Microsoft Corp. today released the code for Phi-4, a small language model that can generate text and solve math problems.

Hugging Face was able to make the Llama 3B model outperform the 70B model Test-time compute scaling allows models to “think longer” on problems The researchers reverse-engineered closed models to ...

Both models are now on Hugging Face with an Apache 2.0 license, and users can drop them in as direct replacements for their current BERT models. The team plans to release a larger version next year ...

Hugging Face has introduced Picotron, a lightweight framework that offers a simpler way to handle LLM training. Unlike traditional solutions that rely on extensive libraries, Picotron streamlines 4D ...