深入剖析：使用 PPO 進行 RLHF 的 N 個關鍵實作細節★ 85
Hugging Face Blog965 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…
在 Replicate 上微調 MusicGen，輕鬆生成任何風格的音樂
Replicate Blog976 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 ONNX Runtime 加速超過 130,000 個 Hugging Face 模型★ 75
Hugging Face Blog985 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 Blog986 days agoReleaseAs large language models (LLMs) shift toward conversational (Chat/Instruct) applications, correctly formatting and feeding a user's conversation history —…
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 Blog990 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…
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 Blog997 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 Blog1,000 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…
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 Blog1,004 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 Blog1,006 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…
Hugging Face Transformers 原生支援量化方案全解析：bitsandbytes 與 GPTQ 實戰指南★ 75
Hugging Face Blog1,007 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 Blog1,008 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 Blog1,011 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 Blog1,013 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 Blog1,013 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 Blog1,018 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 Blog1,020 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…
Meta 推出 Code Llama：基於 Llama 2 的開源程式碼生成模型，支援 100k 上下文★ 85
Hugging Face Blog1,025 days agoReleaseMeta has officially launched Code Llama, a family of state-of-the-art open-source code generation models fine-tuned on Llama 2. Code Llama achieves leading…
使用 AutoGPTQ 與 transformers 讓大型語言模型更輕量化★ 85
Hugging Face Blog1,027 days agoReleaseThis Hugging Face official blog post introduces a major update that integrates AutoGPTQ into the `transformers` and `optimum` libraries. GPTQ (Generalized…
Hugging Face 推出 IDEFICS：開源重現 SOTA 多模態視覺語言模型 Flamingo★ 78
Hugging Face Blog1,028 days agoReleaseHugging Face has officially launched IDEFICS (Image-supervised Decoder-Encoder-Few-shot-In-Context-Shorthand), an open-source multimodal vision-language model…
畫筆化為文字：文字生成圖像 AI 的演進簡史
Replicate Blog1,028 days agoCommentaryOn the occasion of the first anniversary of Stable Diffusion and Replicate's launch of Stable Diffusion XL (SDXL) fine-tuning services, this article provides…
Hugging Face 推出 SafeCoder：專為企業設計的自託管安全程式碼生成助手★ 75
Hugging Face Blog1,028 days agoRelease### Background and Enterprise Pain Points The widespread adoption of AI coding assistants like GitHub Copilot has significantly boosted developer productivity…
Replicate 宣布公開模型降價 50%，並調整私有模型冷啟動與閒置計費機制★ 75
Replicate Blog1,034 days agoBusinessAI cloud hosting and API service platform Replicate announced a major billing structure overhaul on its official blog, centering on two core changes: price…
Hugging Face Hub 登陸 AWS Marketplace：可直接使用 AWS 帳戶付款
Hugging Face Blog1,040 days agoReleaseOpen-source AI community leader Hugging Face has announced an expanded partnership with Amazon Web Services (AWS), officially listing the Hugging Face Hub on…
使用 🤗 Transformers 優化 Bark 語音生成模型★ 75
Hugging Face Blog1,041 days agoTutorialBark is an innovative text-to-audio model developed by the team at Suno. It can generate not only high-quality, multilingual speech, but also background music…
Hugging Face 開源 SD-Small 與 SD-Tiny 知識蒸餾程式碼與模型權重★ 70
Hugging Face Blog1,049 days agoReleaseWhile Stable Diffusion (SD) 1.5 has demonstrated powerful image generation capabilities, its 860 million parameter count still presents challenges for edge…
Stable Diffusion XL 登陸 Mac：利用先進 Core ML 量化技術實現高效本地運行★ 72
Hugging Face Blog1,054 days agoReleaseSince the release of Stable Diffusion XL (SDXL), its exceptional image generation quality has attracted widespread attention. However, its massive 1.3 billion…
Hugging Face 政策觀點：歐盟 AI 法案中對開源機器學習的考量★ 72
Hugging Face Blog1,057 days agoOpinionIn this policy advocacy article, Hugging Face published a key position statement regarding the EU AI Act, which was at the time in trilogue negotiations…
🤗 Diffusers 迎來一週年！回顧開源擴散模型的黃金發展史
Hugging Face Blog1,061 days agoReleaseAn official Hugging Face blog post celebrates the one-year anniversary of its core open-source library, `diffusers`. Since its release in July 2022, Diffusers…
打造 AI 網路電視台：如何利用 Hugging Face 建立 24/7 全天候 AI 生成直播頻道
Hugging Face Blog1,064 days agoTutorialThis official Hugging Face blog post details how to build an "AI WebTV" (AI web television channel) from scratch — a system capable of automatically generating…
Hugging Face 的開源文本生成與 LLM 生態系全景指南★ 85
Hugging Face Blog1,064 days agoReleaseThis official Hugging Face blog post systematically maps out the complete ecosystem it has built around open-source large language models (LLMs). As…