How LLMs Actually Work
Hacker News (AI keywords)11 days agoTutorialThe article explains how modern LLMs convert text into token IDs, embeddings, and position-aware vectors before passing them through stacked transformer blocks. It covers attention, multi-head attention, KV cache, GQA, feed-forward networks, MoE, residual streams, normalization, and decoding. Its goal is educational: helping readers understand the common architecture behind many current model families and read model cards or papers more confidently.
Reachy Mini goes fully local
Hugging Face Blog18 days agoHardwareHugging Face published a tutorial for running Reachy Mini conversations without cloud audio processing or API keys. The setup uses its speech-to-speech library as a cascaded VAD, STT, LLM, and TTS pipeline exposed through a Realtime API-compatible WebSocket. Recommended defaults include llama.cpp with Gemma 4, Silero VAD, Parakeet-TDT, and Qwen3-TTS, while allowing swaps to vLLM, MLX, Transformers, or hosted Responses API providers.
DeepInfra 正式加入 Hugging Face 推理服務商（Inference Providers）陣容 🔥★ 72
Hugging Face Blog46 days agoReleaseHugging Face's official blog has announced that DeepInfra — a well-known high-performance, low-cost serverless inference platform — has officially joined…
Hugging Face 開源生態報告：2026 春季版★ 85
Hugging Face Blog89 days agoCommentaryHugging Face has published its Spring 2026 "State of Open Source AI" report, offering a comprehensive review of the explosive growth and paradigm shifts that…
Transformer 中的混合專家模型 (MoE) 技術解析：原理、優缺點與實作挑戰★ 82
Hugging Face Blog108 days agoTutorialMixture of Experts (MoE) has become the mainstream architecture for current large language models (LLMs). This article takes an in-depth look at how MoE…
免費訓練 AI 模型！Hugging Face 聯手 Unsloth 推出 Hugging Face Jobs 免費微調服務★ 85
Hugging Face Blog114 days agoNew ToolHugging Face's official blog has announced exciting news for the open-source AI community: Hugging Face has formed a deep partnership with Unsloth — the…
OVHcloud 正式加入 Hugging Face 推理供應商行列，主打歐洲數據主權與高性價比算力★ 72
Hugging Face Blog202 days agoReleaseHugging Face has announced a new partnership with OVHcloud, Europe's leading cloud infrastructure provider, officially incorporating OVHcloud into Hugging Face…
Hugging Face 推理提供商迎來新夥伴：Public AI 正式上線 🔥★ 70
Hugging Face Blog270 days agoReleaseHugging Face continues to expand its "Inference Providers" program, aimed at enabling developers to run open-source models from Hugging Face Hub in the…
Replicate 推出遠端 MCP 伺服器：可在 Claude、Cursor 與 VS Code 中直接探索與運行模型★ 75
Replicate Blog308 days agoNew ToolReplicate has officially launched a remote MCP (Model Context Protocol) server. MCP is an open standard created by Anthropic that enables large language models…
Hugging Face 推出 AI Sheets：用開源 AI 模型輕鬆處理與標記數據集的試算表工具★ 75
Hugging Face Blog310 days agoNew ToolHugging Face has officially launched a new tool called "AI Sheets," an intuitive spreadsheet tool designed specifically for dataset processing. It aims to make…
在 Hugging Face 上透過 NVIDIA NIM 加速多樣化 LLM 部署★ 80
Hugging Face Blog328 days agoReleaseHugging Face and NVIDIA have announced a new collaboration to bring NVIDIA NIM (NVIDIA Inference Microservices) into the Hugging Face ecosystem, with the goal…
Groq 正式加入 Hugging Face 推理提供商（Inference Providers）支援極速開源模型推理★ 75
Hugging Face Blog363 days agoReleaseHugging Face announced a deep partnership with Groq, a chip company focused on ultra-fast AI inference, formally bringing Groq into the Hugging Face "Inference…
Dell Enterprise Hub 助企業輕鬆在本地端建置 AI 應用★ 75
Hugging Face Blog387 days agoReleaseAs enterprises place ever-increasing demands on data privacy, security, and regulatory compliance, deploying AI models on-premises has become the preferred…
介紹 HELMET：全面評估長文本語言模型（Long-context LLMs）的新一代基準測試★ 80
Hugging Face Blog424 days agoRelease### Background and Pain Points: Moving Beyond the Overly Simple "Needle in a Haystack" Test In recent years, the context window length supported by large…
Hugging Face 經典 NLP 課程正式轉型為 LLM 課程：迎向大語言模型時代的全面升級★ 85
Hugging Face Blog437 days agoTutorialHugging Face's "NLP Course" has long been a must-read classic for developers and researchers worldwide looking to enter the fields of Transformers and natural…
在 Intel Gaudi 上使用 TGI 加速大型語言模型（LLM）推理★ 75
Hugging Face Blog443 days agoReleaseHugging Face's official blog has announced that its widely adopted open-source large model inference framework, Text Generation Inference (TGI), now officially…
Hugging Face Hub 推出「Inference Providers」：一鍵切換多個第三方高效能推理服務商★ 85
Hugging Face Blog502 days agoReleaseHugging Face has officially launched the "Inference Providers" feature on the Hugging Face Hub — a major update designed to address the pain points developers…
在 GCP 上的第五代 Intel Xeon 處理器（C4 執行個體）進行語言模型效能基準測試
Hugging Face Blog544 days agoCommentaryThis technical blog post from Hugging Face provides a detailed benchmark of running large language models (LLMs) on Google Cloud Platform's (GCP) new C4…
你也能設計出最先進的 Transformer 位置編碼：從直覺到 RoPE 的數學推導★ 75
Hugging Face Blog566 days agoTutorialThis educational article from Hugging Face aims to guide readers — in the most intuitive, step-by-step way — to "reinvent" RoPE (Rotary Position Embedding)…
專家支援案例研究：利用 LLM-as-a-Judge 評估機制強化 Digital Green 的 RAG 農業問答應用★ 75
Hugging Face Blog594 days agoTutorialThis case study provides a detailed account of how non-profit organization Digital Green, with support from Hugging Face's Expert Support team, optimized its…
Hugging Face 推出 HUGS：以開源模型輕鬆擴展您的 AI 應用★ 85
Hugging Face Blog599 days agoReleaseHugging Face has officially launched HUGS (Hugging Face Microservices), a brand-new microservices solution designed to address the pain points enterprises face…
介紹 AMD 第 5 代 EPYC™ 處理器：Hugging Face 攜手 AMD 釋放 CPU 的 AI 推論潛能★ 75
Hugging Face Blog612 days agoReleaseAMD has officially launched its 5th-generation EPYC processor, codenamed "Turin," and Hugging Face has promptly published a blog post detailing the deep…
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 Blog636 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 統一工具調用（Tool Use）標準：簡化開源 LLM Agent 開發流程★ 85
Hugging Face Blog671 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…
Hugging Face 聯手 NVIDIA NIM 推出無伺服器推論服務 (Serverless Inference)★ 82
Hugging Face Blog685 days agoReleaseHugging Face and NVIDIA announced a major partnership in late July 2024, officially launching a serverless inference service powered by NVIDIA NIM (NVIDIA…
WWDC 24：使用 Core ML 在 Apple 裝置上運行 Mistral 7B 模型★ 75
Hugging Face Blog692 days agoTutorialFollowing Apple's major Core ML updates announced at WWDC 24, Hugging Face published a practical guide detailing how to convert the popular open-source large…
TGI Multi-LoRA：部署一次即可同時提供 30 個微調模型服務★ 80
Hugging Face Blog696 days agoReleaseThe Hugging Face official blog has introduced a major update to its open-source text generation inference engine, Text Generation Inference (TGI): the…
Hugging Face 宣布與 KerasHub 深度整合：輕鬆在 Hugging Face Hub 上分享與載入 Keras 3 模型★ 75
Hugging Face Blog704 days agoReleaseHugging Face officially announced a deep integration with KerasHub — the new unified library for natural language processing (NLP) and computer vision (CV) in…
Banque des Territoires (CDC 集團) x Polyconseil x Hugging Face：以主權數據解決方案助力法國重大環境計畫
Hugging Face Blog705 days agoBusiness### Background and Challenges France's Banque des Territoires (part of the Caisse des Dépôts et Consignations — CDC Group) is committed to promoting local…
在 Hugging Face 上輕鬆將模型部署至 AWS Inferentia2 晶片★ 75
Hugging Face Blog753 days agoReleaseHugging Face has announced official support for AWS Inferentia2 (Inf2) instances within its hosted Inference Endpoints service. This update gives developers…