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…
如何使用 API 運行 Mistral 7B 開源語言模型
Replicate Blog982 days agoTutorialMistral 7B is a milestone open-source large language model (LLM) released by the Mistral AI team in the autumn of 2023. Despite having only 7 billion…
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…
Replicate API 支援語言模型串流輸出，大幅提升應用程式響應速度★ 70
Replicate Blog1,035 days agoReleaseReplicate announced that its API now officially supports streaming output for language models (LLMs). This update addresses one of the most common pain points…
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…
Llama 2 發布首日 24 小時動態大盤點：開源社群與 Replicate 的狂歡★ 80
Replicate Blog1,061 days agoReleaseMeta officially launched the highly anticipated open-source large language model Llama 2 on July 18, 2023, immediately triggering a tsunami of cascading…
Llama 2 正式登場！已在 Hugging Face 開源上架並全面支援生態系★ 95
Hugging Face Blog1,062 days agoReleaseMeta and Microsoft jointly announced Llama 2, a new generation of open-source large language models. Compared to the original Llama, Llama 2 increases training…
Hugging Face 的開源文本生成與 LLM 生態系全景指南★ 85
Hugging Face Blog1,063 days agoReleaseThis official Hugging Face blog post systematically maps out the complete ecosystem it has built around open-source large language models (LLMs). As…
使用 Hugging Face Inference Endpoints 輕鬆部署大型語言模型 (LLM)★ 75
Hugging Face Blog1,076 days agoTutorialThis official Hugging Face blog post introduces how to use their hosted service "Inference Endpoints" to deploy large language models (LLMs). With the rapid…
Falcon 系列開源模型正式登陸 Hugging Face 生態系統★ 75
Hugging Face Blog1,105 days agoReleaseThe Falcon series of large language models (including Falcon-40B and Falcon-7B), developed by Abu Dhabi's Technology Innovation Institute (TII), have…
Hugging Face 整合 bitsandbytes、4-bit 量化與 QLoRA，讓大型語言模型更親民★ 90
Hugging Face Blog1,117 days agoReleaseThis official Hugging Face blog post introduces a deep integration with the `bitsandbytes` library, formally adding 4-bit quantization support to…
越小越好：Q8-Chat，在 Intel Xeon 處理器上實現高效的生成式 AI 體驗
Hugging Face Blog1,125 days agoReleaseThis article introduces the latest outcome of a collaboration between Hugging Face and Intel: "Q8-Chat," a project designed to demonstrate how to efficiently…
在單一 AMD GPU 上使用 ROCm 運行類似 ChatGPT 的聊天機器人
Hugging Face Blog1,126 days agoTutorialThis blog post from Hugging Face provides a detailed walkthrough of how to deploy and run an open-source ChatGPT-like chatbot on a single AMD GPU using AMD's…
Hugging Face 推出 Assisted Generation：邁向低延遲文本生成的新方向★ 85
Hugging Face Blog1,130 days agoReleaseLarge language models (LLMs) typically generate text using an "autoregressive" mechanism, meaning the model must generate one token at a time. Each generation…
使用 StarCoder 打造程式助手：StarChat Alpha 正式推出
Hugging Face Blog1,132 days agoReleaseHugging Face has announced the launch of StarChat Alpha, a conversational AI assistant designed specifically for programming. The model is based on StarCoder…
StarCoder：開源程式碼生成 LLM 的全新里程碑★ 85
Hugging Face Blog1,137 days agoReleaseThe BigCode community project, led jointly by Hugging Face and ServiceNow, has officially released StarCoder (along with its base version, StarCoderBase) — a…
Replicate 發布 2023 年 4 月開源語言模型彙整：Vicuna、Dolly v2 與 StableLM 齊聚
Replicate Blog1,150 days agoReleaseThe spring of 2023 was a golden era for open-source large language model (LLM) development. In April 2023, Replicate — the well-known AI model hosting platform…
Replicate 宣布正式支援大型語言模型（LLMs），提供快速啟動與串流 API
Replicate Blog1,166 days agoReleaseReplicate, the well-known AI model hosting platform, has announced official support for large language models (LLMs) on its platform. Previously, Replicate was…
在 Habana Gaudi2 加速器上實現大型語言模型快速推理：以 BLOOMZ 為例
Hugging Face Blog1,174 days agoTutorialThis article presents the results of a collaboration between Hugging Face and the Intel Habana team, focusing on how to leverage Intel's Habana Gaudi2 deep…
Hugging Face 與 AWS 達成深度合作，降低生成式 AI 部署與訓練門檻★ 75
Hugging Face Blog1,209 days agoBusinessOpen-source AI community leader Hugging Face and cloud computing giant Amazon Web Services (AWS) have announced an expanded partnership aimed at making…
Hugging Face 推出 PEFT 庫：用更低的硬體成本高效微調大型語言模型★ 85
Hugging Face Blog1,220 days agoNew ToolAs the parameter scale of large language models (LLMs) continues to grow, full fine-tuning has become prohibitively expensive and impractical. To lower the…
遊戲開發中的 AI 應用 #5：生成故事與敘事創作
Hugging Face Blog1,223 days agoTutorial### A New Dimension of Game Storytelling: AI-Powered Dynamic Story Generation In traditional game development, writing rich, branching narratives is an…
什麼讓對話代理（Dialog Agent）變得實用？Hugging Face 深度解析★ 75
Hugging Face Blog1,237 days agoOpinionAmid the generative AI wave sparked by ChatGPT, Hugging Face published this in-depth article exploring how to transform "base language models" — which can only…
Hugging Face Inference Endpoints 入門指南：輕鬆部署生產級 AI 模型★ 75
Hugging Face Blog1,339 days agoTutorialHugging Face Inference Endpoints is a fully managed service designed for developers and enterprises, built to solve the pain points of deploying machine…
超大型語言模型及其評估方法：Hugging Face 推出 Hub 上的零樣本評估★ 75
Hugging Face Blog1,350 days agoNew ToolIn late 2022, as massive language models like BLOOM and OPT emerged one after another, the AI community faced a core pain point: how to effectively and…
Hugging Face 揭秘：🤗 Accelerate 如何藉助 PyTorch 運行超大型模型★ 80
Hugging Face Blog1,356 days agoTutorialAs the parameter counts of large language models (LLMs) grow exponentially, how to load and run these models on limited hardware has become a major pain point…
使用 DeepSpeed 與 Accelerate 實現極速 BLOOM 模型推理
Hugging Face Blog1,367 days agoTutorialBLOOM is a massive open-source multilingual model with 176 billion parameters. Running BLOOM at FP16 precision requires at least 352 GB of video memory (VRAM)…
介紹全球最大的開源多語言大語言模型：BLOOM★ 75
Hugging Face Blog1,433 days agoReleaseIn July 2022, Hugging Face and the BigScience collaborative community officially released BLOOM (BigScience Large Open-science Open-access Multilingual…