Hugging Face is an AI community platform and company providing a hub for open-source machine learning models, datasets, and demo spaces. It hosts over 500,000 models and is widely used by the AI research community.
A software engineer explores the practicalities of running large language models locally, demystifying technical jargon like parameters, quantization, and MoE to help users choose and deploy models on…
The open source community is backing OpenEnv, a tool for creating agentic execution environments, as it transitions to a committee-led governance structure with support from Meta-PyTorch, Nvidia, Hugg…
Neuracoder released neura-fa-en-1.9b, a 1.9 billion parameter bilingual model trained from scratch on Persian and English text, achieving 9 tokens per second on an Intel i7 CPU without a GPU. The mode…
Nvidia and FPT Corporation released a dataset of 900,000 synthetic personas on June 5 to help AI models understand Vietnam’s language, culture, and demographics. The Nemotron-Personas-Vietnam dataset,…
NVIDIA released Nemotron 3.5 ASR, a 600M-parameter streaming speech recognition model that transcribes 40 language-locales in real time from a single checkpoint. The model uses a cache-aware FastConfo…
A self-taught student successfully fine-tuned the open-source Qwen 2.5-7B language model into a Discord bot named Monika, using 687 in-game dialogues and QLoRA 4-bit compression on Google Colab's free…
A developer has published a guide for running Google's Gemma-4 12B instruction-tuned model on Windows Subsystem for Linux 2 (WSL2) using the llama.cpp framework. The process involves installing build …
A team of developers built Thousand Token Wood, a multi-agent economic simulation where five AI-powered woodland creatures trade goods using a 3-billion-parameter Qwen2.5-3B model. The simulation, cre…
JAX defaults to loading data directly onto GPU memory when a CUDA-enabled version is installed, causing out-of-memory errors for large datasets that would fit in system RAM. The framework's `jax.devic…
Microsoft Presidio, an open-source framework for detecting and anonymizing personally identifiable information (PII) in text, images, and structured data, offers two core modules—the Analyzer and the …
Mochallama, a new Java library, enables running llama.cpp inference directly within a Java process using JDK 22's Foreign Function and Memory (FFM) API, eliminating the need for separate daemon proces…
Google released Magenta RealTime 2, an open-weights AI model and real-time inference engine that enables live, low-latency music generation on a MacBook. The model responds instantly to MIDI, audio, a…
Researchers at Tevatron released BrowseComp-Plus, a new benchmark designed to evaluate deep-research AI agents by isolating the effects of retrievers and large language models for fair and reproducibl…
A developer porting PyTorch LLM code to JAX using Flax encountered difficulties when attempting to store model checkpoints with Safetensors, as the library's Flax API expects flat dictionaries but Fla…
Researchers at Amphora have built a semantic search engine and open-status classifier over the ResearchMath-14k dataset, a collection of research-level mathematics problems mined from arXiv. The syste…
A new demo called SRT-Introspect reveals how large language models like Qwen fix word meanings during generation, contradicting the reflexive, approximated nature of human language. The tool surfaces …
Nvidia released Nemotron 3.5 Content Safety, a single 4-billion-parameter model that unifies multimodal input, multilingual coverage across 140 languages, custom enterprise policy enforcement, and aud…
NVIDIA released Nemotron 3.5 ASR, a 600M-parameter streaming multilingual speech-to-text model that transcribes 40 language-locales from a single checkpoint with built-in punctuation and capitalizatio…
Google launched Google AI Edge Gallery for macOS, allowing Mac users to run Gemma models locally on their devices. The company also released the Gemma 4 12B model, a multimodal AI with 12 billion para…
Hugging Face redesigned its `hf` command-line interface to optimize it for AI coding agents, which now account for significant traffic on the Hub. The new CLI auto-detects when an agent is driving it …