🇨🇿 BenCzechMark：你的 LLM 能聽懂捷克語嗎？全新捷克語基準測試發布
Hugging Face Blog626 days agoReleaseThe Hugging Face team and its collaborators have jointly launched a new benchmark called "BenCzechMark," designed to evaluate the understanding and generation…
將頂點著色網格轉換為紋理貼圖網格：Hugging Face 釋出 3D 模型優化指南★ 75
Hugging Face Blog627 days agoTutorialIn the field of 3D generative AI (encompassing models such as InstantMesh and Tripo3D), generated 3D models typically represent color using "vertex coloring."…
Meta 推出 Llama 3.2：支援視覺多模態與邊緣裝置運行的輕量級模型，Hugging Face 全面支援★ 95
Hugging Face Blog632 days agoReleaseMeta has officially introduced the Llama 3.2 family of open-source models, marking a significant architectural upgrade with two major breakthroughs: multimodal…
FineVideo 幕後秘辛：Hugging Face 如何打造高品質開源影片資料集★ 75
Hugging Face Blog634 days agoReleaseWith the explosion of video generation and understanding models such as Sora and Gen-3, high-quality video training data has become a key battleground for…
探索 Hugging Face 的 Daily Papers 頁面：掌握每日最新 AI 論文與社群討論★ 70
Hugging Face Blog634 days agoTutorialIn today's rapidly evolving AI landscape, keeping up with the latest academic papers is a major challenge. Hugging Face's "Daily Papers" page was created…
使用 Optimum-Intel 與 OpenVINO GenAI 進行模型優化與部署★ 75
Hugging Face Blog637 days agoTutorialThis article provides a detailed look at how to use Hugging Face's `optimum-intel` library and Intel's OpenVINO GenAI toolkit to optimize and deploy generative…
微調 LLM 至 1.58-bit：讓極限模型量化變得簡單★ 85
Hugging Face Blog639 days agoTutorialThe deployment of large language models (LLMs) has long faced a dual bottleneck of VRAM capacity and memory bandwidth. Microsoft previously introduced the…
Hugging Face 推出 Datasets SQL 控制台：直接用 SQL 查詢與探索數據集
Hugging Face Blog640 days agoNew ToolHugging Face has officially announced the launch of a brand-new "SQL Console" feature on the Datasets pages of the Hugging Face Hub. This feature is designed…
HuggingChat 推出「社群工具 (Community Tools)」：賦予開源 AI 助理強大的 Agent 擴充能力★ 75
Hugging Face Blog641 days agoReleaseHugging Face has officially introduced the "Community Tools" feature to its open-source chat platform, HuggingChat. This major update injects powerful Agent…
Hugging Face 釋出 Accelerate 1.0.0 正式版：邁向分散式訓練與大模型推理的全新里程碑★ 80
Hugging Face Blog644 days agoReleaseHugging Face has officially released version 1.0.0 of its core open-source library, Accelerate. This is a milestone update, signifying that since the project's…
Hugging Face 與 Truffle Security 合作，引進 TruffleHog 自動掃描並防範金鑰洩漏★ 70
Hugging Face Blog653 days agoReleaseHugging Face has officially announced a partnership with the well-known cybersecurity company Truffle Security, integrating the open-source credential scanning…
使用影片編碼擴展機器人技術數據集：Hugging Face 的高效壓縮與讀取指南★ 70
Hugging Face Blog661 days agoTutorial### Background and Challenges In robotics (such as Embodied AI), imitation learning and reinforcement learning require collecting large volumes of robot…
Hugging Face 官方點名：5 個被低估的開源生態系「隱藏神兵」★ 75
Hugging Face Blog666 days agoTutorialHugging Face, as the world's largest open-source AI community, has developed many powerful tools beyond its well-known Model Hub that often go unnoticed by…
透過 Flash Attention 2 的 Packing 技術提升 Hugging Face 訓練效率★ 80
Hugging Face Blog667 days agoTutorialWhen fine-tuning or pre-training large language models (LLMs), the sequence lengths of input data are typically uneven. The traditional approach is to use…
在 Google Cloud Vertex AI 上部署 Meta Llama 3.1 405B 旗艦開源模型★ 75
Hugging Face Blog669 days agoReleaseMeta's Llama 3.1 405B is one of the most powerful open-source large language models available today, but its massive parameter count (405 billion) poses…
Replicate Intelligence #11：微調 FLUX.1、生成式影像遊戲與元宇宙的新願景★ 75
Replicate Blog672 days agoReleaseThis edition of Replicate Intelligence #11 compiles major recent technical breakthroughs and application trends in the generative AI space, focusing primarily…
一個失敗的實驗：Infini-Attention，以及為什麼我們應該繼續嘗試？★ 75
Hugging Face Blog674 days agoCommentaryThis Hugging Face blog post provides a detailed account of the team's attempt to reproduce and evaluate Google's proposed "Infini-Attention" mechanism — and…
GGML 基礎入門介紹：讓大語言模型在消費級硬體上高效運行的關鍵技術★ 80
Hugging Face Blog675 days agoTutorialGGML is a lightweight, zero-dependency C/C++ tensor library developed by Georgi Gerganov. It was originally designed to enable efficient local inference of the…
歡迎 Falcon Mamba：首款強大的無注意力機制（Attention-Free）7B 語言模型★ 85
Hugging Face Blog676 days agoReleaseThe Technology Innovation Institute (TII) of Abu Dhabi has officially released Falcon Mamba 7B, a significant milestone in the evolution of AI architectures…
Hugging Face 統一工具調用（Tool Use）標準：簡化開源 LLM Agent 開發流程★ 85
Hugging Face Blog676 days agoRelease### Background and Pain Points In AI agent development, "tool use" (also known as function calling) is the core capability that allows large language models…
XetHub 正式加入 Hugging Face！攜手提升超大規模資料與模型版本控制技術★ 75
Hugging Face Blog680 days agoBusinessAI community platform Hugging Face announced on August 8, 2024, the acquisition of XetHub, a startup specializing in solving large-scale data versioning…
Hugging Face 2024 年安全功能亮點：全面提升開源 AI 生態系的防禦力★ 75
Hugging Face Blog682 days agoReleaseAs AI models have proliferated, AI supply chain security has become a top priority that developers and enterprises can no longer afford to overlook. Hugging…
Hugging Face 推出適用於文件圖像的 TextImage 數據增強技術 (TextImage Augmentation)★ 75
Hugging Face Blog682 days agoNew Tool### Solving Real-World Document AI Pain Points In the fields of Document AI and OCR (Optical Character Recognition), datasets used in academic research or…
Replicate Intelligence #9：開源影像模型新巔峰 FLUX.1、影片物件分割 SAM 2 與全新 Python 網頁框架 FastHTML★ 85
Replicate Blog686 days agoReleaseThis edition of Replicate Intelligence highlights three of the most noteworthy open-source and developer tool developments from early August 2024: 1. **The new…
Black Forest Labs 推出全新開源影像生成模型 FLUX.1：Replicate 已支援 API 運行★ 90
Replicate Blog687 days agoReleaseBlack Forest Labs — a new AI team founded by the original creators of Stable Diffusion (including core developer Robin Rombach and others) — has officially…
Google 發布 Gemma 2 2B、安全分類器 ShieldGemma 與可解釋性工具 Gemma Scope★ 85
Hugging Face Blog688 days agoReleaseGoogle released a major update to the Gemma 2 family in late July 2024, comprising three core components: 1. **Gemma 2 2B**: A lightweight model with just 2.6B…
使用 Quanto 與 Diffusers 打造記憶體高效的 Diffusion Transformers (DiT)★ 80
Hugging Face Blog689 days agoRelease### Background and Challenges As generative AI technology evolves, image and video generation models are increasingly transitioning from traditional UNet…
Hugging Face 聯手 NVIDIA NIM 推出無伺服器推論服務 (Serverless Inference)★ 82
Hugging Face Blog690 days agoReleaseHugging Face and NVIDIA announced a major partnership in late July 2024, officially launching a serverless inference service powered by NVIDIA NIM (NVIDIA…
Replicate Intelligence #8：Llama 3.1 頂級開源模型上線、全新安全分類器與模型搜尋 API★ 75
Replicate Blog693 days agoReleaseReplicate has published its eighth issue of technical intelligence (Replicate Intelligence #8), bringing three major updates for developers: 1. **Top…
LAVE：在 Docmatix 上使用 LLM 進行零樣本 VQA 評估——我們還需要微調嗎？★ 75
Hugging Face Blog694 days agoPaper### Background and Challenges Document Visual Question Answering (DocVQA) is an important application of multimodal AI, requiring models to simultaneously…