如何在 AWS 上部署與微調 DeepSeek 模型：Hugging Face 官方指南★ 85
Hugging Face Blog501 days agoTutorialAs DeepSeek-R1 swept through the AI landscape on the strength of its powerful reasoning capabilities, how to safely and efficiently deploy and fine-tune these…
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 Blog503 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…
Open-R1：Hugging Face 推出完全開源的 DeepSeek-R1 重現計劃★ 90
Hugging Face Blog503 days agoRelease### Project Background: Recreating the Open-Source Miracle of DeepSeek-R1 The emergence of DeepSeek-R1 sent shockwaves through the global AI community…
Diffusers 庫中開源影片生成模型的最新現狀與技術解析★ 82
Hugging Face Blog504 days agoCommentaryThis official Hugging Face blog post takes an in-depth look at the current state of open-source video generation models within the Diffusers ecosystem. As…
Hugging Face 輕量級 Agent 框架 smolagents 正式支援視覺語言模型 (VLM)！★ 80
Hugging Face Blog507 days agoReleaseOn January 24, 2025, Hugging Face announced that smolagents — its open-source library designed for building lightweight, high-performance AI agents — now…
使用 KVPress 掌握大語言模型（LLM）的長文本處理能力★ 75
Hugging Face Blog508 days agoNew ToolIn the current trajectory of large language model (LLM) development, support for long contexts has become a standard requirement. However, as input text length…
Hugging Face 推出更輕量 SmolVLM：全新 256M 與 500M 超小視覺語言模型登場！★ 75
Hugging Face Blog508 days agoReleaseHugging Face has officially introduced the newest members of the SmolVLM family, pushing vision-language model (VLM) sizes even further down to 256M (256…
Hugging Face 與 FriendliAI 達成合作，全面加速 Hub 上的模型部署★ 70
Hugging Face Blog509 days agoReleaseHugging Face has announced a strategic partnership with FriendliAI, a company specializing in high-performance AI inference, aimed at comprehensively improving…
Hugging Face TGI 宣布支援多後端引擎：整合 TensorRT-LLM 與 vLLM★ 85
Hugging Face Blog515 days agoReleaseText Generation Inference (TGI), Hugging Face's open-source LLM inference and deployment framework, has received a major architectural update, officially…
Timm ❤️ Transformers：現在可在 Transformers 中直接使用任何 timm 視覺模型★ 80
Hugging Face Blog515 days agoReleaseThe official Hugging Face blog has announced exciting news for the computer vision (CV) community: the popular PyTorch image model library `timm` (PyTorch…
AI Agent 時代已來臨：我們該如何應對？（Hugging Face 倫理與社會專欄）★ 75
Hugging Face Blog518 days agoCommentaryWith the explosion of AI Agent technology, AI is no longer just a passive chatbot that answers questions — it has become an entity capable of autonomously…
視覺文件檢索邁向多語言：Hugging Face 推出 VDR-2B-multilingual 模型★ 80
Hugging Face Blog521 days agoReleaseHugging Face has recently released a new Visual Document Retrieval (VDR) model — **VDR-2B-multilingual**. This technology marks a formal transition in document…
Open LLM Leaderboard 碳排放與模型性能分析：效能與環保的權衡啟示
Hugging Face Blog522 days agoCommentaryHugging Face recently published an in-depth analysis of its well-known Open LLM Leaderboard, examining the carbon dioxide (CO₂) emissions generated during…
Hugging Face 推出 smolagents：用 Python 程式碼撰寫行動的極簡 AI Agent 框架★ 85
Hugging Face Blog531 days agoReleaseHugging Face officially launched a lightweight AI agent development framework called `smolagents` at the end of 2024. The core philosophy of this tool is "Code…
使用 NVIDIA 的 LogitsProcessorZoo 精準控制語言模型生成內容★ 75
Hugging Face Blog539 days agoNew ToolIn real-world applications of large language models (LLMs), ensuring that model outputs conform to expected formats — such as standard JSON, specific XML tags…
評估音訊推理能力：Hugging Face 推出 Big Bench Audio 基準測試★ 75
Hugging Face Blog542 days agoReleaseAs multimodal large language models (such as GPT-4o, Gemini, and various open-source audio models) continue to proliferate, AI's ability to process audio has…
終於迎來 BERT 的繼承者：ModernBERT 正式發布★ 85
Hugging Face Blog543 days agoReleaseDespite the recent dominance of generative decoder models (such as GPT and Llama), encoder-only models (such as BERT) remain indispensable behind the scenes…
Bamba：高推論效率的混合 Mamba2 開源模型正式發布★ 75
Hugging Face Blog544 days agoRelease### Background and Architectural Innovation As large language models (LLMs) have advanced rapidly, the traditional Transformer architecture faces severe…
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 Blog545 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…
歡迎來到 Falcon 3 開源模型家族！TII 推出全新輕量與 MoE 模型架構★ 80
Hugging Face Blog545 days agoReleaseThe Technology Innovation Institute (TII) of Abu Dhabi has officially launched the new Falcon 3 open-source model family on Hugging Face. This marks a major…
Hugging Face 推出 Synthetic Data Generator：用自然語言輕鬆構建 AI 訓練資料集★ 82
Hugging Face Blog546 days agoNew ToolHugging Face launched a brand-new "Synthetic Data Generator" in December 2024 — a web-based, no-code tool designed to allow anyone to create high-quality AI…
AI 影片生成迎來它的「Stable Diffusion 時刻」：開源模型已並肩 OpenAI Sora★ 80
Replicate Blog546 days agoOpinionIn the history of AI development, the open-sourcing of Stable Diffusion in 2022 is regarded as a pivotal turning point in the field of image generation — it…
Hugging Face 模型正式登陸 Amazon Bedrock：更輕鬆部署開源 AI 模型★ 78
Hugging Face Blog553 days agoReleaseHugging Face announced a major partnership with Amazon Web Services (AWS), formally integrating Hugging Face's model library into the Amazon Bedrock service…
Hugging Face 社群推出用於文字生成圖像的開源偏好資料集 (Open Preference Dataset)★ 75
Hugging Face Blog553 days agoRelease### Introduction: An Important Piece of the Open-Source Image Generation Puzzle As text-to-image (T2I) technology advances rapidly, ensuring that AI-generated…
Google 推出全新視覺語言模型 PaliGemma 2：基於 Gemma 2 的多模態輕量級模型★ 80
Hugging Face Blog557 days agoReleaseGoogle and Hugging Face have jointly announced the release of a new generation of open-weight vision-language model (VLM) — PaliGemma 2. This model continues…
LLM 自我糾錯能力有多強？Hugging Face 聯手 Keras 與 TPU 打造競技場實驗★ 75
Hugging Face Blog557 days agoCommentaryAs large language models (LLMs) are increasingly applied in software development and logical reasoning, there is growing interest in whether models possess the…
重新思考阿拉伯語大模型評估：AraGen 基準測試與 3C3H 評估框架上線 Hugging Face
Hugging Face Blog558 days agoRelease### Background and Challenges: The Difficulty of Evaluating Non-English LLMs In the current landscape of large language model (LLM) development, evaluating…
投資於效能：利用 LLM 洞察微調小型模型 — CFM 案例研究★ 75
Hugging Face Blog559 days agoBusinessThis case study from Hugging Face details how quantitative asset management firm Capital Fund Management (CFM) has optimized its investment and research…
歐盟 AI 法案開源開發者指南：Hugging Face 實用解析★ 75
Hugging Face Blog560 days agoTutorialWith the EU AI Act officially taking effect, AI developers worldwide are facing compliance pressure. To help the open-source (OSS) community understand the…
Hugging Face 推出 SmolVLM：輕量且強大的開源視覺語言模型，可在本機高效運行★ 80
Hugging Face Blog566 days agoReleaseHugging Face has officially launched a lightweight vision language model (VLM) called **SmolVLM**, designed to bring powerful multimodal understanding…