使用自投機解碼（Self-Speculative Decoding）加速文本生成：Meta 推出 LayerSkip 技術★ 78
Hugging Face Blog571 days agoReleaseThe slow autoregressive generation speed of large language models (LLMs) has long been a major bottleneck in real-world deployment. While "speculative…
Universal Assisted Generation：支援任意輔助模型的通用輔助生成技術，大幅提升解碼速度★ 85
Hugging Face Blog593 days agoReleaseIn the deployment and inference of large language models (LLMs), reducing generation latency has always been a critical challenge. The traditional approach of…
深入解析 Aya Expanse：推動多語言 AI 模型的前沿進展★ 75
Hugging Face Blog598 days agoReleaseCohere For AI (C4AI) has officially launched Aya Expanse, a family of open-weight models designed specifically for multilingual tasks. The family includes two…
Google 與 Hugging Face 聯手推出 SynthID Text：開源 AI 生成文本浮水印技術★ 85
Hugging Face Blog599 days agoReleaseOn October 23, 2024, Google and Hugging Face jointly announced the open-sourcing of Google's "SynthID Text" technology and its integration into Hugging Face's…
中國 AI 全球擴張簡析：開源模型如何席捲 Hugging Face 與全球市場★ 75
Hugging Face Blog619 days agoCommentaryThis article from the Hugging Face blog takes an in-depth look at how China's artificial intelligence forces have successfully gone global in recent years…
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 Blog671 days agoReleaseThe Technology Innovation Institute (TII) of Abu Dhabi has officially released Falcon Mamba 7B, a significant milestone in the evolution of AI architectures…
Replicate Intelligence #8：Llama 3.1 頂級開源模型上線、全新安全分類器與模型搜尋 API★ 75
Replicate Blog688 days agoReleaseReplicate has published its eighth issue of technical intelligence (Replicate Intelligence #8), bringing three major updates for developers: 1. **Top…
Meta 推出 Llama 3.1：405B、70B 與 8B 旗艦開源模型，支援多語言與 128K 超長上下文★ 95
Hugging Face Blog691 days agoReleaseMeta's Llama 3.1 represents a major milestone in the open-source AI landscape. The most notable model is the 405B (405 billion parameter) version — the first…
使用 API 運行 Meta Llama 3.1 405B：Replicate 雲端部署指南★ 85
Replicate Blog691 days agoReleaseOn July 23, 2024, Meta officially released the highly anticipated Llama 3.1 405B — one of the most powerful open-source large language models in the world…
Google 推出全新開源大語言模型 Gemma 2：9B 與 27B 雙版本，效能超越同級模型★ 85
Hugging Face Blog717 days agoReleaseGoogle has officially launched the next generation of its open-source large language model, Gemma 2, with an initial release in two sizes — 9B (9 billion…
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 Blog751 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…
在 Replicate 上透過 API 輕鬆運行 Snowflake Arctic 開源大模型
Replicate Blog782 days agoNew ToolSnowflake recently launched a brand-new open-source large language model called "Snowflake Arctic" — a Mixture of Experts (MoE) model designed for…
歡迎 Llama 3：Meta 全新開源大型語言模型正式登陸 Hugging Face★ 95
Hugging Face Blog787 days agoReleaseMeta officially released Llama 3, the next generation of its open-source large language models, on April 18, 2024. The initial release includes two parameter…
Google 官方推出 CodeGemma：專為程式碼生成與補全設計的輕量級開源模型★ 80
Hugging Face Blog796 days agoReleaseGoogle and Hugging Face have jointly announced the launch of CodeGemma, a family of lightweight open-source large language models (LLMs) designed specifically…
Cosmopedia：如何為大型語言模型預訓練建立大規模合成數據★ 85
Hugging Face Blog816 days agoReleaseHugging Face has officially released Cosmopedia, currently the largest and fully open-source synthetic dataset designed for the pre-training of large language…
Hugging Face 推出 Quanto：適用於 Optimum 的全新 PyTorch 量化後端★ 75
Hugging Face Blog818 days agoReleaseHugging Face has officially introduced Quanto, a brand-new quantization library designed for PyTorch, which has been integrated as a backend into the Hugging…
在 NVIDIA DGX Cloud 上輕鬆使用 H100 GPU 訓練 Hugging Face 模型★ 75
Hugging Face Blog818 days agoReleaseHugging Face has announced a deep partnership with NVIDIA to directly integrate NVIDIA DGX Cloud services into the Hugging Face platform. This collaboration…
StarCoder2 與 The Stack v2 正式發布：新一代開源程式碼大模型與超大資料集★ 80
Hugging Face Blog837 days agoReleaseThe BigCode community, jointly led by Hugging Face and ServiceNow, together with NVIDIA, has officially announced the launch of a new generation of open-source…
AI 水印入門指南：工具與技術解析★ 75
Hugging Face Blog839 days agoTutorialThis guide from Hugging Face systematically introduces the technical principles, categories, existing tools, and real-world challenges of AI watermarking. As…
在 Hugging Face 中微調 Gemma 模型★ 80
Hugging Face Blog842 days agoTutorialAfter Google released the Gemma family of open-source models (including 2B and 7B parameter versions), Hugging Face promptly published this practical…
歡迎 Gemma：Google 全新開源大語言模型登陸 Hugging Face★ 85
Hugging Face Blog844 days agoReleaseGoogle has officially released a new family of open-source large language models called "Gemma" — a series of lightweight, state-of-the-art open-source models…
2023 年：開源大語言模型（Open LLMs）爆發之年★ 75
Hugging Face Blog909 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…
歡迎 Mixtral：Hugging Face 迎來頂尖的混合專家（MoE）開源模型★ 90
Hugging Face Blog916 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…
混合專家模型 (Mixture of Experts, MoE) 技術詳解★ 85
Hugging Face Blog916 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…
Optimum-NVIDIA：只需一行程式碼，即可解鎖極速 LLM 推理★ 80
Hugging Face Blog922 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…
讓你的 Llama 生成速度飛起來：使用 AWS Inferentia2 進行加速★ 72
Hugging Face Blog950 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 Transformers 原生支援量化方案全解析：bitsandbytes 與 GPTQ 實戰指南★ 75
Hugging Face Blog1,006 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…
展翅高飛：擁有 1800 億參數的 Falcon 180B 正式發布★ 75
Hugging Face Blog1,012 days agoReleaseThe Technology Innovation Institute (TII) in Abu Dhabi, UAE has officially released what is currently the largest openly accessible large language model on…
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 Blog1,024 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 API 輕鬆運行 Llama 2：只需一行程式碼即可在雲端部署
Replicate Blog1,053 days agoTutorialMeta's Llama 2 represents a landmark milestone in the history of open-source large language model (LLM) development. Its performance was regarded at the time…