使用開源 LLM 實作憲政 AI (Constitutional AI)：Hugging Face 的對齊新指南★ 78
Hugging Face Blog869 days agoTutorialThis blog post from Hugging Face provides an in-depth exploration of how to implement "Constitutional AI (CAI)" using open-source large language models (Open…
Hugging Face 推出「企業情境排行榜」：專為真實世界應用設計的 LLM 評測基準★ 75
Hugging Face Blog870 days agoReleaseHugging Face has partnered with Patronus AI — a startup focused on LLM evaluation and defense — to officially launch the **Enterprise Scenarios Leaderboard**…
使用 🤗 Optimum Intel 在 Xeon 處理器上加速 StarCoder：Q8/Q4 量化與投機解碼
Hugging Face Blog871 days agoTutorialThis Hugging Face blog post explores in detail how to use the `Optimum Intel` library to accelerate inference for the StarCoder code-generation model on Intel…
Hugging Face 推出「幻覺排行榜」，開源量化評估大型語言模型的幻覺率★ 75
Hugging Face Blog872 days agoReleaseWhile large language models (LLMs) have demonstrated remarkable generative capabilities across many domains, "hallucination" — where a model confidently…
Hugging Face 推出 AI Secure LLM 安全排行榜：基於 DecodingTrust 框架深度評估大模型信任度★ 75
Hugging Face Blog875 days agoRelease### Introduction: Capability Is Not Safety — A New Benchmark for LLM Safety Evaluation As large language models (LLMs) are adopted more deeply across…
Hugging Face 與 Google 達成戰略合作，攜手推動開放式 AI 協作★ 80
Hugging Face Blog876 days agoBusinessHugging Face and Google officially announced a landmark strategic partnership at the end of January 2024. The core objective of this collaboration is to deeply…
使用開源 LLM 作為 LangChain Agent：Hugging Face 實作指南★ 80
Hugging Face Blog877 days agoTutorialThis official Hugging Face blog post provides a detailed guide on how to use open-source large language models (LLMs) as intelligent agents within LangChain…
使用 🤗 Transformers 微調 W2V2-BERT 以進行低資源語音辨識 (ASR)★ 75
Hugging Face Blog882 days agoTutorialThis technical blog post from Hugging Face provides a detailed walkthrough of how to use the `transformers` library to fine-tune Meta's open-source W2V2-BERT…
IBM 輕量級時間序列模型 PatchTSMixer 正式整合至 Hugging Face★ 75
Hugging Face Blog882 days agoReleaseTime series forecasting is critically important in fields such as finance, meteorology, energy, and the Internet of Things. In recent years, while the…
使用直接偏好最佳化 (DPO) 方法對 LLM 進行偏好微調 (Preference Tuning)★ 80
Hugging Face Blog883 days agoTutorialThis technical blog post from Hugging Face takes an in-depth look at the latest techniques in "preference tuning," with a particular focus on **Direct…
使用 ONNX Runtime 與 Olive 加速 SD Turbo 和 SDXL Turbo 推論★ 75
Hugging Face Blog886 days agoTutorialSD Turbo and SDXL Turbo are single-step/few-step text-to-image models from Stability AI, with their core innovation being Adversarial Diffusion Distillation…
如何建立自己的 Hugging Face 排行榜：以 Vectara 幻覺排行榜為例的完整指南★ 75
Hugging Face Blog889 days agoTutorialIn the open-source AI community, the Hugging Face Open LLM Leaderboard serves as an important benchmark for evaluating model capabilities. However, many…
使用 Unsloth 與 🤗 TRL 讓 LLM 微調速度提升 2 倍★ 80
Hugging Face Blog891 days agoReleaseHugging Face's official blog announced a partnership with the Unsloth team to integrate Unsloth's efficient fine-tuning technology directly into Hugging Face's…
迎來 aMUSEd：高效的輕量級 Text-to-Image 文本生成圖像模型
Hugging Face Blog897 days agoReleaseThe Hugging Face official blog formally introduced a brand-new open-source text-to-image model called "aMUSEd." This model is based on a reproduction and…
使用投機解碼（Speculative Decoding）將 Whisper 推論速度提升 2 倍★ 75
Hugging Face Blog912 days agoTutorialThe Hugging Face official blog introduces how to use "Speculative Decoding" to more than double the inference speed of OpenAI's Whisper speech-to-text model…
2023 年：開源大語言模型（Open LLMs）爆發之年★ 75
Hugging Face Blog914 days agoCommentaryLooking back on 2023, the most notable trend in the AI landscape was the explosive growth of open-source large language models (Open LLMs). In this annual…
混合專家模型 (Mixture of Experts, MoE) 技術詳解★ 85
Hugging Face Blog921 days agoTutorialMixture of Experts (MoE) has become a core technology for improving the performance and efficiency of today's large language models (LLMs). Traditional "dense…
歡迎 Mixtral：Hugging Face 迎來頂尖的混合專家（MoE）開源模型★ 90
Hugging Face Blog921 days agoReleaseFrench AI startup Mistral AI officially released its highly anticipated open-source Mixture of Experts (MoE) model — Mixtral 8x7B. The model caused a sensation…
SetFitABSA：基於 SetFit 的少樣本屬性情感分析，僅需極少數據即可精準分類★ 75
Hugging Face Blog926 days agoRelease### Background and Challenges Sentiment analysis is one of the most classic tasks in natural language processing (NLP). However, traditional sentence-level…
Optimum-NVIDIA：只需一行程式碼，即可解鎖極速 LLM 推理★ 80
Hugging Face Blog927 days agoReleaseHugging Face announced the launch of a new open-source library called "Optimum-NVIDIA," the result of a deep collaboration with NVIDIA, aimed at seamlessly…
告別冷啟動：Hugging Face 如何將 LoRA 推論速度提升 300%★ 85
Hugging Face Blog927 days agoReleaseIn real-world generative AI applications, fine-tuning for specific tasks or clients is a common requirement. However, deploying a full base model for every…
AMD 攜手 Hugging Face：推出 optimum-amd 實現 AMD GPU 的大語言模型即開即用加速★ 75
Hugging Face Blog927 days agoReleaseHugging Face's official blog announced a deep partnership with chip giant AMD, launching `optimum-amd`, an open-source library optimized specifically for AMD…
Replicate 完成由 a16z 領投的 4,000 萬美元 B 輪融資，加速企業基於開源 AI 進行開發★ 75
Replicate Blog927 days agoBusinessAI infrastructure startup Replicate announced the successful completion of a $40 million Series B funding round. This round was led by prominent Silicon Valley…
Open LLM Leaderboard：深入解析 DROP 基準測試與模型「刷榜」現象★ 75
Hugging Face Blog931 days agoCommentaryThe Hugging Face Open LLM Leaderboard has long served as an important benchmark for the community to evaluate the capabilities of open-source models. However…
如何使用 API 運行 Yi 對話模型：以 Replicate 雲端託管為例
Replicate Blog939 days agoTutorialThe Yi model series is a bilingual (Chinese and English) large language model trained from scratch by 01.AI, the AI startup founded by Kai-Fu Lee. Upon its…
使用開源模型進行更快、更便宜的文字嵌入 (Text Embeddings)
Replicate Blog952 days agoTutorialThis technical blog post from Replicate provides a detailed introduction to using the open-source BGE (BAAI General Embedding) model for efficient, low-cost…
只要 4 步！使用 Latent Consistency LoRAs (LCM-LoRA) 加速 SDXL 圖像生成★ 85
Hugging Face Blog953 days agoReleaseThis Hugging Face blog post introduces **LCM-LoRA (Latent Consistency Models LoRAs)**, a revolutionary technique that enables Stable Diffusion XL (SDXL) to…
比較大語言模型性能：深入探討使用 LoRA 微調 RoBERTa、Llama 2 與 Mistral 進行災難推特分析★ 75
Hugging Face Blog955 days agoTutorialThis Hugging Face blog post takes an in-depth look at how to use LoRA (Low-Rank Adaptation) to fine-tune three models of different architectures and scales for…
介紹 Prodigy-HF：與 Hugging Face 的直接整合
Hugging Face Blog955 days agoNew ToolProdigy, the well-known machine learning data annotation tool from Explosion (the company behind the popular NLP library spaCy), has officially released a…
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…