Applications

In this tutorial, we take a deep dive into the capabilities of Zarr, a library designed for environment friendly storage & manipulation of enormous, multidimensional arrays. We start by exploring the fundamentals, creating arrays, setting chunking methods, and modifying values immediately on disk. From there, we broaden into extra superior operations comparable to experimenting with…

Table of contents What architecture powers MobileLLM-R1? How efficient is the training? How does it perform against other open models? Where does MobileLLM-R1 fall short? How does MobileLLM-R1 compare to Qwen3, SmolLM2, and OLMo? Summary Meta has launched MobileLLM-R1, a household of light-weight edge reasoning fashions now obtainable on Hugging Face. The launch contains fashions…

IBM has quietly constructed a robust presence in the open-source AI ecosystem, and its newest launch exhibits why it shouldn’t be neglected. The firm has launched two new embedding fashions—granite-embedding-english-r2 and granite-embedding-small-english-r2—designed particularly for high-performance retrieval and RAG (retrieval-augmented technology) techniques. These fashions should not solely compact and environment friendly but additionally licensed underneath Apache…

In this tutorial, we stroll by a sophisticated but sensible workflow utilizing SpeechBrain. We begin by producing our personal clear speech samples with gTTS, intentionally including noise to simulate real-world situations, and then making use of SpeechMind’s MetricGAN+ mannequin to boost the audio. Once the audio is denoised, we run computerized speech recognition with a…

Hugging Face has simply launched SuperbVision, an open multimodal dataset designed to set a brand new customary for Vision-Language Models (VLMs). With 17.3 million photos, 24.3 million samples, 88.9 million question-answer turns, and almost 10 billion reply tokens, SuperbVision place itself as one of many largest and structured publicly accessible VLM coaching datasets. SuperbVision aggregates…