As large language models (LLMs) are deployed across a wide range of industries, ensuring the "factuality" of model outputs and reducing "hallucination" has…
Hugging Face has officially released `swift-huggingface`, a complete Swift client SDK designed specifically for the Apple ecosystem (including iOS, macOS…
Hugging Face recently shared a highly inspiring experiment: how to use Anthropic's Claude (as an AI Agent) to automate the fine-tuning of an open-source large…
### Background and Challenge Large language models (LLMs) frequently encounter "hallucinations" or calculation errors when handling complex mathematical…
Vercel has officially announced that its AI Gateway service now supports the DeepSeek V3.2 series of models. This update makes it easier for developers to…
The `transformers` library from Hugging Face is a cornerstone of today's AI and open-source community. With the official release of v5, the team has introduced…
This technical blog post from Hugging Face takes a "First Principles" approach to provide a deep analysis of one of the most critical optimization techniques…
The cloud AI hosting platform Replicate has officially announced support for FLUX.2, the next-generation image generation model developed by Black Forest Labs…
The Hugging Face official blog has announced that the popular diffusion model library `diffusers` now officially supports FLUX-2, the next-generation…
In this technical blog post published on Hugging Face, Tavily — a search engine designed specifically for AI agents — details how they built a "Deep Research"…
Hugging Face has announced a new partnership with OVHcloud, Europe's leading cloud infrastructure provider, officially incorporating OVHcloud into Hugging Face…
Hugging Face recently made a major upgrade to its flagship "Open ASR Leaderboard," officially launching two brand-new evaluation tracks: "Multilingual" and…
The Hugging Face official blog has announced a collaboration with RapidFire AI, bringing a revolutionary performance improvement to its popular TRL…
Hugging Face has officially launched a new open-source Swift framework called "AnyLanguageModel," designed to address the pain points faced by developers on…
With the successive emergence of models with powerful "reasoning" capabilities — such as OpenAI o1, o3, and DeepSeek-R1 — the challenge of reducing the…
The well-known pixel art AI model suite Retro Diffusion has officially launched on the cloud AI hosting platform Replicate. For indie game developers, game…
Hugging Face recently announced a major update for AMD GPU users and developers, aimed at simplifying the process of building, packaging, and sharing ROCm…
In November 2025, Replicate — the well-known AI model hosting and API services platform — announced that it was officially joining Cloudflare, the global…
Hugging Face and chip giant AMD have jointly announced the "AMD Open Robotics Hackathon," an event designed to inspire developers, researchers, and makers…
Hugging Face and Google Cloud have announced a new strategic partnership aimed at jointly advancing the future of "Open AI." This collaboration deeply…
### Background and Challenge: Automated Abuse Targeting AI Services Nous Research, a leading open-source AI research organization, has released many popular…
Against the backdrop of explosive global growth in artificial intelligence, compute has become the core resource that determines technological competitiveness…
This article explores how to combine Hugging Face's open-source robot learning library LeRobot with NVIDIA's Isaac robotics development platform to build…
This article, jointly published by IBM and Hugging Face, delves into the technical details and application scenarios of the brand-new ultra-lightweight model…
With the rapid advancement of voice cloning technology, generating hyper-realistic synthetic voices has become remarkably easy. However, this has also…
Hugging Face's official blog recently published a major update announcing a comprehensive overhaul of the streaming mode in its core open-source library…
Hugging Face has officially announced that its core Python library `huggingface_hub` has reached version v1.0. This is not merely a version number increment —…
Google DeepMind has announced a new open-source large language model series called "T5Gemma." This release represents another significant milestone for Google…
Google DeepMind officially announced the launch of a new "MedGemma" multimodal model within its open-source medical model series. This model represents the…
Google DeepMind officially launched Gemma 3n along with its developer guide. The Gemma series, as Google's open-weights model family, has long been a favorite…