Replicate 推出 FLUX.1 微調功能：用一行程式碼即可訓練專屬的 LoRA 圖像生成模型★ 80
Replicate Blog670 days agoReleaseReplicate, the well-known cloud AI execution platform, has announced official fine-tuning support for FLUX.1, the image generation model that has taken the…
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 Blog671 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…
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 Blog673 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 Blog673 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…
Replicate Intelligence #10：Flux 模型最新進展、Minecraft AI 機器人與 Streamlit 實作指南
Replicate Blog676 days agoReleaseThis edition of Replicate Intelligence #10 brings developers and AI enthusiasts several useful technical updates and community projects: 1. **Latest…
FLUX.1 首發實測：開源圖像生成的新巔峰與第一手體驗★ 85
Replicate Blog683 days agoReleaseFLUX.1 is a new family of text-to-image models developed by Black Forest Labs — a startup founded by the original core research team behind Stable Diffusion…
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 Blog684 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…
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 Blog691 days agoPaper### Background and Challenges Document Visual Question Answering (DocVQA) is an important application of multimodal AI, requiring models to simultaneously…
如何利用 distilabel 打造 Argilla 2.0 專屬聊天機器人★ 75
Hugging Face Blog700 days agoTutorialIn the AI field, quickly building a chatbot that can accurately answer questions about a specific domain or newly released software has always been a major…
Replicate Intelligence #7：資料整理與資料生成的重要性
Replicate Blog704 days agoCommentaryIn the current wave of generative AI, the industry's attention is gradually shifting from "fine-tuning model architectures" to "improving data quality." Issue…
NuminaMath 如何贏得首屆 AIMO 進步獎（AI 數學奧林匹亞）並宣佈完整開源★ 80
Hugging Face Blog705 days agoRelease### Background and Achievement The AI Mathematical Olympiad (AIMO) Progress Prize aims to advance AI models capable of solving Olympiad-level mathematical…
在 Intel Gaudi 2 上加速蛋白質語言模型 ProtST
Hugging Face Blog713 days agoTutorialThis article from the Hugging Face blog provides a detailed introduction to accelerating the advanced protein language model ProtST on Intel Gaudi 2 deep…
Replicate Intelligence #6：Google Gemma 2 模型上線、LLM 排行榜更新與 Stable Diffusion 3 實用技巧★ 75
Replicate Blog718 days agoReleaseThis issue of Replicate Intelligence summarizes three major core updates from the recent open-source AI landscape: 1. **Google Gemma 2 officially launches**…
如何在自己的電腦上使用 ComfyUI 運行 Stable Diffusion 3
Replicate Blog732 days agoTutorialThis hands-on tutorial from the Replicate Blog is designed to guide readers through running the latest generation of open-source image generation model, Stable…
使用 API 運行 Stable Diffusion 3：Replicate 雲端部署指南★ 70
Replicate Blog734 days agoNew ToolStability AI officially launched its latest text-to-image model — Stable Diffusion 3 (SD3). This release brings major upgrades across several key areas…
Replicate Intelligence #3：Garden State Llama、實用 LLM 指南與即時影像生成
Replicate Blog739 days agoCommentaryThis issue of Replicate Intelligence #3 brings curated content on three core themes for developers and AI enthusiasts: 1. **Garden State Llama**: This is a…
Hugging Face 聯合 Artificial Analysis 推出「文字生成圖片」排行榜與競技場★ 75
Hugging Face Blog740 days agoNew ToolHugging Face has partnered with independent AI evaluation organization Artificial Analysis to officially launch the "Text to Image Leaderboard & Arena." This…
Intel Gaudi 支援更快的輔助生成（Assisted Generation），顯著提升 LLM 推理速度
Hugging Face Blog742 days agoReleaseHugging Face, in collaboration with Intel, has announced official support for "Assisted Generation" (also commonly known as Speculative Decoding) on Intel…
Replicate Intelligence #2：更快的圖像生成、AI 驅動的世界模擬器與 AI 資料集複雜度洞察★ 75
Replicate Blog746 days agoCommentaryReplicate's technical newsletter, Replicate Intelligence #2, takes a deep dive into three of the most hotly discussed trends in the open-source AI community…
Vercel Ship 2024 重點回顧：Next.js 15 RC、AI SDK 3.1 與全新開發工具登場★ 85
Vercel Changelog752 days agoReleaseVercel held its annual technical conference, Vercel Ship 2024, showcasing a number of major updates aimed at improving the frontend development experience, AI…
阿布達比 TII 發表 Falcon 2 11B：搭載 5 兆 Token 訓練的預訓練語言與視覺語言模型★ 75
Hugging Face Blog753 days agoReleaseThe Technology Innovation Institute (TII) of Abu Dhabi has officially released a new open-source model family on Hugging Face — Falcon 2 11B. This model, with…
Hugging Face 推出 Spaces 開發者模式（Dev Mode）：支援 VS Code 與 SSH 的無縫開發體驗★ 75
Hugging Face Blog756 days agoReleaseHugging Face has officially announced the launch of the new "Spaces Dev Mode," an important feature designed to improve AI application development efficiency…
Google 推出 PaliGemma：結合 SigLIP 與 Gemma 的開源視覺語言模型★ 80
Hugging Face Blog763 days agoReleaseGoogle has officially launched PaliGemma, a powerful yet lightweight open-source Vision-Language Model (VLM). The release of PaliGemma represents a significant…
在 Replicate 上透過 API 輕鬆運行 Snowflake Arctic 開源大模型
Replicate Blog784 days agoNew ToolSnowflake recently launched a brand-new open-source large language model called "Snowflake Arctic" — a Mixture of Experts (MoE) model designed for…
萬事通，局部精通：Hugging Face 發表多功能 Transformer 代理人 JAT★ 75
Hugging Face Blog785 days agoReleaseIn the field of artificial intelligence, developing a "Generalist Agent" — one capable of chatting, writing, controlling robots, and playing video games all at…
在 Hugging Face Endpoints 上運行隱私保護的全同態加密 (FHE) 推理★ 75
Hugging Face Blog791 days agoReleaseThis article introduces how to run privacy-preserving inference based on Fully Homomorphic Encryption (FHE) on Hugging Face Endpoints. In traditional…
視覺語言模型（VLM）原理解析：從架構、訓練到應用指南★ 80
Hugging Face Blog796 days agoTutorialThis technical blog post published by Hugging Face provides an accessible yet thorough breakdown of the core principles and applications of Vision Language…
使用 🤗 Optimum Intel 在 Xeon 處理器上實現極速 SetFit 推論
Hugging Face Blog804 days agoTutorialSetFit (Sentence Transformer Fine-Tuning) is a few-shot text classification framework co-developed by Hugging Face, Intel Labs, and other organizations. Rather…
Pollen-Vision：為機器人打造的 Zero-Shot 視覺模型統一接口★ 75
Hugging Face Blog813 days agoNew ToolPollen Robotics has announced the launch of an open-source project called "Pollen-Vision," a unified vision interface designed specifically for robotics…
介紹 Chatbot Guardrails Arena：評估大語言模型安全防護網的全新競技場★ 75
Hugging Face Blog817 days agoReleaseAs large language models (LLMs) have been widely adopted across industries, ensuring AI systems remain safe and compliant while preventing harmful outputs has…