你可以直接用在 Transformers 的 OpenAI gpt-oss 加速妙招 🫵★ 82
Hugging Face Blog277 days agoTutorial### Background and the LLM Inference Bottleneck When running large language models (LLMs), autoregressive generation is inherently "memory-bandwidth-bound"…
使用 Together AI 微調 Hugging Face Hub 上的任何開源大語言模型 (LLM)★ 75
Hugging Face Blog277 days agoReleaseHugging Face and Together AI have announced a deep partnership, launching a new integration designed to streamline the fine-tuning workflow for open-source…
Jupyter Agents：訓練 LLM 利用 Notebook 進行推理與自我修正★ 78
Hugging Face Blog278 days agoRelease### Background and Core Concepts Traditional large language models (LLMs), when faced with complex mathematics, data analysis, or programming tasks, can…
mmBERT：ModernBERT 邁向多語言時代，開源高效能多語言編碼器模型登場★ 78
Hugging Face Blog279 days agoReleaseIn today's era dominated by generative AI and large language models (LLMs), bidirectional encoder models (such as BERT and RoBERTa) still play an indispensable…
使用 Torch Compile 快取加速模型啟動與推論速度★ 75
Replicate Blog280 days agoTutorialWhen deploying modern AI models (such as LLaMA, Flux, or Stable Diffusion), `torch.compile` — introduced in PyTorch 2.0 — is a powerful performance…
歡迎 EmbeddingGemma：Google 全新高效嵌入模型上線 Hugging Face★ 75
Hugging Face Blog284 days agoReleaseGoogle has recently launched a new open-source text embedding model called "EmbeddingGemma" on the Hugging Face platform. This model is built on the…
Vercel 發表「開放 SDK 策略」：打造跨模型與框架的通用 AI 開發標準★ 75
Vercel Changelog284 days agoOpinionVercel recently published its "Open SDK Strategy," centered on shaping its widely popular Vercel AI SDK into an open, neutral, and highly interoperable…
NVIDIA 於 Hugging Face 開源發布 600 萬筆多語言推理數據集★ 78
Hugging Face Blog298 days agoReleaseNVIDIA has officially released a massive "Multi-Lingual Reasoning Dataset" containing 6 million samples on the Hugging Face platform. This significant…
使用 Claude 與 Hugging Face 產生圖片：透過 MCP 協定無縫整合★ 85
Hugging Face Blog300 days agoNew ToolThe Hugging Face official blog has announced an exciting new integration: through Anthropic's Model Context Protocol (MCP), users can now generate images…
MCP for Research：如何將 AI 連接到學術研究工具★ 75
Hugging Face Blog301 days agoTutorialAs the use of AI in academic research becomes increasingly widespread, enabling large language models (LLMs) to access the latest scientific literature in real…
Kimina-Prover-RL：Hugging Face AI-MO 推出結合強化學習的開源數學定理證明器★ 80
Hugging Face Blog304 days agoReleaseThe AI-MO (AI Mathematical Olympiad) team at Hugging Face has officially released the "Kimina-Prover-RL" project. Following the previously well-received…
Arm 與 ExecuTorch 0.7 聯手：將生成式 AI 推向大眾市場★ 80
Hugging Face Blog305 days agoReleaseAs generative AI advances rapidly, deploying massive models to resource-constrained edge devices — such as smartphones, smart hardware, and AI PCs — has become…
Arm 與 Hugging Face 聯手推出「Neural Super Sampling」！加速行動端與邊緣設備的 AI 圖像超取樣★ 75
Hugging Face Blog306 days agoReleaseArm and Hugging Face have announced a collaboration to launch "Neural Super Sampling (NSS)" technology and related models, officially bringing AI-driven image…
FilBench 發布：大型語言模型真的懂菲律賓語嗎？全新評測基準登場
Hugging Face Blog307 days agoReleaseThe Hugging Face team and community have collaborated to launch a new evaluation benchmark called "FilBench," aimed at answering a key question: do large…
TextQuests：LLM 在文字冒險遊戲中的表現究竟如何？Hugging Face 推出全新評估基準★ 75
Hugging Face Blog307 days agoReleaseHugging Face has recently introduced a new benchmark called "TextQuests," designed to evaluate the performance of large language models (LLMs) in text-based…
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 Blog309 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 Blog311 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…
Hugging Face Accelerate ND-Parallel 指南：高效多 GPU 訓練完全解析★ 80
Hugging Face Blog311 days agoTutorialAs the parameter counts of generative AI and large language models (LLMs) push into the tens and hundreds of billions, the memory of a single GPU has long been…
Hugging Face TRL 支援視覺語言模型 (VLM) 對齊：輕鬆實現多模態 DPO 與 ORPO 訓練★ 80
Hugging Face Blog312 days agoReleaseHugging Face's TRL (Transformer Reinforcement Learning) is a popular open-source library specifically designed for aligning language models (LLMs). In its…
Vercel AI Gateway 現已支援 gpt-oss-20b 與 gpt-oss-120b 開源模型
Vercel Changelog313 days agoReleaseOn August 5, 2025, Vercel published an update announcing that its AI Gateway service (Vercel AI Gateway) now officially supports two new open-source large…
歡迎 GPT OSS！OpenAI 全新開源模型家族正式登陸 Hugging Face★ 95
Hugging Face Blog314 days agoReleaseThe Hugging Face official blog has announced exciting news, formally welcoming OpenAI's newly launched open-source model family — "GPT OSS." This is undeniably…
開源影片生成模型回歸：Replicate 推出最快、最便宜的 Wan 2.2 模型★ 75
Replicate Blog319 days agoReleaseReplicate has announced official support for the brand-new open-source video generation model Wan 2.2 on its platform, declaring that "open-source video…
用 Python 實作 MCP 伺服器：結合 Gradio 打造 AI 虛擬試穿購物助手★ 75
Hugging Face Blog319 days agoTutorialAs the Model Context Protocol (MCP) proposed by Anthropic gradually becomes the open standard for connecting large language models (LLMs) with external tools…
Hugging Face 推出 Trackio：專為機器學習設計的輕量級實驗追蹤庫★ 75
Hugging Face Blog321 days agoReleaseHugging Face has officially launched a lightweight open-source experiment tracking library called **Trackio**, designed to offer machine learning developers…
Model Context Protocol (MCP) 詳解：常見問答集 (FAQ)★ 85
Vercel Changelog324 days agoTutorialAs AI applications become more widespread, how to allow large language models (LLMs) to securely and efficiently access enterprise internal data or external…
Vercel AI Gateway 正式支援 Qwen3-Coder 模型
Vercel Changelog324 days agoReleaseVercel announced in its official changelog that its Vercel AI Gateway has now officially added Qwen3-Coder to its roster of supported models. This means…
TimeScope：評估影片大型多模態模型（Video LMM）長影片理解極限的新基準★ 75
Hugging Face Blog327 days agoReleaseAs large multimodal models (LMMs) have achieved breakthroughs in image and short-video understanding, the industry has gradually shifted its attention to the…
使用 Diffusers 與 PEFT 實現 Flux 的快速 LoRA 推論★ 80
Hugging Face Blog327 days agoTutorialThis technical guide from Hugging Face takes an in-depth look at how to accelerate LoRA (Low-Rank Adaptation) inference for Flux.1, the powerful open-source…
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…
Vercel AI Gateway 現在支援相容 OpenAI 的 API 端點★ 75
Vercel Changelog328 days agoReleaseVercel announced in its product changelog that its AI Gateway service now officially supports "OpenAI-compatible API endpoints." This is a practical feature…