讓你的 Llama 生成速度飛起來：使用 AWS Inferentia2 進行加速★ 72
Hugging Face Blog955 days agoTutorialAs large language models (LLMs) such as Llama 2 become more widely adopted, achieving efficient and cost-effective inference in production environments has…
Hugging Face Hub 推出「儲存區域」(Storage Regions) 功能：滿足數據合規與在地化需求★ 70
Hugging Face Blog959 days agoReleaseHugging Face has officially announced the launch of "Storage Regions" on Hugging Face Hub. This new feature is designed to address the pain points that global…
只需一行程式碼，即可互動式探索與檢視 Hugging Face 數據集
Hugging Face Blog968 days agoNew ToolThis article introduces the integration between Hugging Face and the open-source data exploration tool Renumics Spotlight, aimed at addressing the pain point…
在 Mac 上使用 Latent Consistency Model (LCM) 實現一秒快速生成圖片教學
Replicate Blog968 days agoTutorialThis technical guide from Replicate provides detailed instructions on how to locally deploy and run Latent Consistency Models (LCMs) on Macs equipped with…
深入剖析：使用 PPO 進行 RLHF 的 N 個關鍵實作細節★ 85
Hugging Face Blog969 days agoTutorialThis technical blog post from Hugging Face takes an in-depth look at the critical "implementation details" that are routinely glossed over in academic papers…
使用 Hugging Face Inference Endpoints 輕鬆部署高效能嵌入模型★ 75
Hugging Face Blog969 days agoReleaseAs large language models (LLMs) and Retrieval-Augmented Generation (RAG) technology become increasingly widespread, embedding models have become an…
Gradio-Lite：完全在瀏覽器中運行的無伺服器 Gradio★ 75
Hugging Face Blog974 days agoReleaseHugging Face has announced the launch of Gradio-Lite (@gradio/lite), a new library that enables Gradio applications to run entirely within the user's browser…
如何使用 ChromaDB 與 Mistral 實現檢索增強生成 (RAG)
Replicate Blog976 days agoTutorialThis technical blog post from Replicate provides a detailed walkthrough of how to build a basic Retrieval-Augmented Generation (RAG) application from scratch…
在 Replicate 上微調 MusicGen，輕鬆生成任何風格的音樂
Replicate Blog980 days agoNew ToolAI cloud deployment and runtime platform Replicate has announced official support for fine-tuning Meta's open-source music generation model MusicGen. This new…
使用 Llama 2 與 Grammar 進行結構化資訊萃取 (Jet-setting with Llama 2 + Grammars)★ 75
Replicate Blog984 days agoTutorialIn practical natural language processing (NLP) applications, converting unstructured text (such as emails or conversation logs) into structured data (such as…
使用 ONNX Runtime 加速超過 130,000 個 Hugging Face 模型★ 75
Hugging Face Blog989 days agoNew ToolHugging Face officially announced a deep collaboration with Microsoft to integrate ONNX Runtime (ORT) into the Hugging Face ecosystem. This partnership enables…
Chat Templates：終結默默蠶食模型效能的隱形殺手★ 85
Hugging Face Blog990 days agoReleaseAs large language models (LLMs) shift toward conversational (Chat/Instruct) applications, correctly formatting and feeding a user's conversation history —…
使用 JAX 與 Cloud TPU v5e 加速 Stable Diffusion XL 推理★ 70
Hugging Face Blog990 days agoTutorialWith the widespread adoption of high-quality open-source image generation models like Stable Diffusion XL (SDXL), reducing inference latency and controlling…
使用 TRL 透過 DDPO 微調 Stable Diffusion 模型★ 75
Hugging Face Blog994 days agoReleaseHugging Face published a blog post introducing how to use the DDPO (Denoising Diffusion Policy Optimization) algorithm within the TRL (Transformer…
Hugging Face 倫理與社會簡報第 5 期：Hugging Face 前進華盛頓與 2023 夏季沉思
Hugging Face Blog994 days agoCommentaryAs the world's largest open-source AI community platform, Hugging Face regularly shares its efforts in AI governance, policy advocacy, and ethics research…
Llama 2 在 Amazon SageMaker 上的部署效能基準測試
Hugging Face Blog997 days agoTutorialThis Hugging Face blog post presents detailed performance benchmarks for deploying Meta's open-source large language models — Llama 2 (covering 7B, 13B, and…
Hugging Face 為 PRO 訂閱者推出專屬推理服務：更高速率、支援大型開源模型★ 70
Hugging Face Blog1,001 days agoReleaseThe Hugging Face official blog has announced a new "Inference for PROs" upgraded service for PRO subscribers (at $9 per month). This service is designed to…
Rocket Money x Hugging Face：如何在生產環境中擴展高波動性的機器學習模型
Hugging Face Blog1,004 days agoBusinessThis case study details how Rocket Money (formerly TrueBill), a popular personal finance app, partnered with Hugging Face to address pain points in deploying…
Hugging Face 推出全新「物件偵測排行榜」(Object Detection Leaderboard)
Hugging Face Blog1,005 days agoNew ToolHugging Face has officially launched the "Object Detection Leaderboard," a brand-new evaluation platform designed for the computer vision field. With the rapid…
3D Gaussian Splatting 入門指南：開啟即時 3D 渲染的新紀元★ 85
Hugging Face Blog1,005 days agoTutorialThis technical blog post from Hugging Face takes an in-depth look at 3D Gaussian Splatting (3DGS), a revolutionary technology that has taken the worlds of 3D…
在生產環境中優化你的大語言模型 (LLM) — Hugging Face 實戰指南★ 85
Hugging Face Blog1,008 days agoTutorialThis technical guide from Hugging Face systematically introduces the core strategies for deploying and optimizing large language models (LLMs) in production…
介紹 Würstchen：超快速且高效的圖像生成擴散模型★ 75
Hugging Face Blog1,010 days agoReleaseHugging Face, in collaboration with the research community, has introduced a new text-to-image diffusion model called "Würstchen." The model's standout feature…
使用 PyTorch FSDP 高效微調 Llama 2 70B：解決 CPU 記憶體不足的實務指南★ 72
Hugging Face Blog1,010 days agoTutorialWhen fine-tuning massively large open-source models like Llama 2 70B — with its 70 billion parameters — developers frequently encounter a bottleneck that goes…
Hugging Face Transformers 原生支援量化方案全解析：bitsandbytes 與 GPTQ 實戰指南★ 75
Hugging Face Blog1,011 days agoTutorialAs the parameter count of large language models (LLMs) has grown dramatically, running and fine-tuning these models on consumer-grade GPUs or limited hardware…
Hugging Face SafeCoder 對決閉源程式碼助手：企業級私有化部署的安全性優勢★ 70
Hugging Face Blog1,012 days agoReleaseIn today's software development workflows, AI coding assistants have become a critical tool for boosting developer productivity. However, for many enterprises…
使用 T2I-Adapters 實現 SDXL 的高效可控圖像生成★ 70
Hugging Face Blog1,015 days agoReleaseThis technical article introduces T2I-Adapters (Text-to-Image Adapters) designed specifically for Stable Diffusion XL (SDXL). As SDXL has become the new…
展翅高飛：擁有 1800 億參數的 Falcon 180B 正式發布★ 75
Hugging Face Blog1,017 days agoReleaseThe Technology Innovation Institute (TII) in Abu Dhabi, UAE has officially released what is currently the largest openly accessible large language model on…
Replicate 大幅優化微調模型冷啟動時間，現在只需不到一秒即可完成載入★ 75
Replicate Blog1,017 days agoReleaseAI cloud hosting platform Replicate has announced a major technical breakthrough for fine-tuned models: the "cold boot" time for fine-tuned models has been…
Fetch 採用 Amazon SageMaker 與 Hugging Face，成功降低 50% 機器學習處理延遲
Hugging Face Blog1,022 days agoBusinessThis case study examines how Fetch, a leading consumer rewards platform in the United States, leveraged the collaboration between Amazon SageMaker and Hugging…
AudioLDM 2 速度優化指南：如何讓文字轉音訊與音樂生成快上加快 ⚡️★ 75
Hugging Face Blog1,024 days agoTutorialAudioLDM 2 is an advanced open-source text-to-audio and text-to-music generation model. However, under its default settings, the model's inference speed is…