Hugging Face 與 Habana Labs 合作加速 Transformer 模型訓練
Hugging Face Blog1,569 days agoReleaseHugging Face and Intel's Habana Labs have officially announced a partnership aimed at providing the community with more efficient and cost-effective solutions…
Hugging Face 的設計哲學：為什麼我們反其道而行，選擇「重複程式碼」？★ 85
Hugging Face Blog1,576 days agoOpinionThis classic blog post from Hugging Face examines the tension between software engineering principles and the demands of machine learning (ML) research…
Hugging Face 正式引入 Decision Transformers：將強化學習視為序列建模任務
Hugging Face Blog1,584 days agoReleaseHugging Face has announced official support for the Decision Transformer (DT) in its renowned `transformers` library. This represents a new paradigm that…
使用自定義資料集微調 SegFormer 語義分割模型
Hugging Face Blog1,595 days agoTutorialThis practical tutorial from Hugging Face provides a detailed guide on how to fine-tune the SegFormer model on a custom dataset for semantic segmentation…
使用 Hugging Face Transformers 與 AWS Inferentia 加速 BERT 推論
Hugging Face Blog1,596 days agoTutorialWhen deploying large language models such as BERT in production environments, inference latency and computational cost are often two major pain points for…
BERT 101：最先進的 NLP 模型完整原理解析
Hugging Face Blog1,610 days agoTutorialBERT (Bidirectional Encoder Representations from Transformers) is a landmark natural language processing (NLP) model proposed by Google in 2018. This Hugging…
在 🤗 Transformers 中使用 Wav2Vec2 處理超長音檔的自動語音辨識 (ASR)
Hugging Face Blog1,639 days agoTutorialIn the field of automatic speech recognition (ASR), Wav2Vec2 is a revolutionary model, but it faces a significant challenge when processing long audio files…
案例研究：使用 Hugging Face Infinity 與現代 CPU 實現毫秒級延遲
Hugging Face Blog1,658 days agoNew ToolThis case study focuses on the performance of "Hugging Face Infinity" — Hugging Face's high-performance inference container solution — on modern CPUs…
在 🤗 Transformers 中使用 n-gram 提升 Wav2Vec2 語音識別效能
Hugging Face Blog1,659 days agoTutorialThis technical blog post from Hugging Face introduces how combining n-gram language models (LMs) can significantly improve the performance of Wav2Vec2…
使用 AutoNLP 與 Prodigy 進行主動學習 (Active Learning)
Hugging Face Blog1,679 days agoTutorialThis blog post introduces the integration of Hugging Face's AutoNLP (now evolved into AutoTrain) with Prodigy, the popular data annotation tool developed by…
Perceiver IO：可擴展且適用於任何模態的全注意力機制模型★ 70
Hugging Face Blog1,687 days agoReleaseThis article introduces DeepMind's Perceiver IO model and its integration into the Hugging Face Transformers library. Traditional Transformer models, while…
Hugging Face 推出首個 Unity ML-Agents 強化學習環境「Snowball Fight ☃️」
Hugging Face Blog1,700 days agoReleaseHugging Face announced the launch of its first custom virtual environment built on Unity ML-Agents: "Snowball Fight." This marks Hugging Face's formal…
利用 Intel 技術加速 PyTorch 分散式微調
Hugging Face Blog1,713 days agoTutorialWhile GPUs dominate deep learning training today, a collaboration between Intel and Hugging Face demonstrates that through software and hardware optimization…
使用 🤗 Transformers 微調 XLSR-Wav2Vec2 以進行低資源語音辨識 (ASR)
Hugging Face Blog1,717 days agoTutorialAutomatic speech recognition (ASR) has achieved remarkable success for resource-rich languages such as English and standard Mandarin, but building…
在現代 CPU 上擴展 BERT 類模型的推理效能 - 第二部分
Hugging Face Blog1,728 days agoTutorialThis blog post is the second part of a technical guide co-authored by Hugging Face and Intel, designed to show developers how to push the inference performance…
機器學習即程式碼（ML as Code）的時代已經到來：Hugging Face 談開發者導向的 AI 新典範
Hugging Face Blog1,743 days agoOpinionThis classic 2021 article from Hugging Face declared the official arrival of the "Machine Learning as Code" (ML as Code) era. The central argument is that…
在 Hugging Face Spaces 上使用 Streamlit 託管您的模型與資料集★ 70
Hugging Face Blog1,758 days agoNew ToolHugging Face has announced the launch of its new "Spaces" feature, designed to provide the machine learning community with a simple, fast, and free platform…
Hugging Face 與 Graphcore 達成合作，推出針對 IPU 優化的 Transformers 模型
Hugging Face Blog1,779 days agoReleaseIn September 2021, Hugging Face, the leading open-source AI community, and British AI chip design company Graphcore announced a strategic partnership aimed at…
網際網路上的深度學習：以協作方式訓練語言模型
Hugging Face Blog1,840 days agoReleaseIn the field of artificial intelligence, training large language models (LLMs) has always been an extremely resource-intensive task. Traditionally, this…
Sentence Transformers 正式整合至 Hugging Face Hub
Hugging Face Blog1,857 days agoReleaseHugging Face officially announced a deep integration with the highly popular open-source library `sentence-transformers`. `sentence-transformers` (commonly…
深入理解 BigBird 的區塊稀疏注意力機制 (Block Sparse Attention)
Hugging Face Blog1,946 days agoTutorialTraditional Transformer models (such as BERT) are constrained by the quadratic complexity $O(N^2)$ of their self-attention mechanism, and are typically limited…
使用 🤗 Transformers 在 Hugging Face 中微調 Wav2Vec2 進行英文語音辨識 (ASR)★ 70
Hugging Face Blog1,965 days agoTutorialThis is a landmark technical tutorial published by the Hugging Face team in 2021, detailing how to fine-tune Meta AI's Wav2Vec2 model using the Hugging Face…
Hugging Face 讀書會：長文本 Transformer 模型技術解析與演進
Hugging Face Blog1,968 days agoCommentaryIn the field of natural language processing (NLP), the core of standard Transformer models (such as BERT and GPT-2) is the self-attention mechanism. However…
建構華麗神經網路的實用指南：給開發者的幾個簡單建議
Hugging Face Blog1,980 days agoOpinionThis classic blog post from Hugging Face explores the common mistakes developers make when building complex (fancy) neural networks, and the simple principles…
Hugging Face Transformers 中的 TensorFlow 模型加速與 TF Serving 部署指南
Hugging Face Blog2,010 days agoTutorialWhen deploying Transformer models in production environments, latency and throughput are often the deciding factors for a project's success. Hugging Face…
利用預訓練語言模型權重「熱啟動」Encoder-Decoder 模型
Hugging Face Blog2,088 days agoTutorialIn the field of natural language processing (NLP), sequence-to-sequence (Seq2Seq) models — such as those used for translation or summarization — typically…
將 Fairseq WMT19 翻譯系統移植至 Hugging Face Transformers
Hugging Face Blog2,094 days agoReleaseIn the field of natural language processing (NLP), machine translation has always been a core challenge. Facebook AI Research (FAIR) achieved outstanding…
使用 Transformers 與 Ray Tune 進行超參數搜尋
Hugging Face Blog2,095 days agoTutorialThis classic article from the official Hugging Face blog provides a detailed guide on how to integrate Hugging Face's `Transformers` library with the powerful…
Transformer 架構下的編碼器-解碼器（Encoder-Decoder）模型深度解析★ 70
Hugging Face Blog2,118 days agoTutorialThis classic blog post written by Hugging Face researcher Patrick von Platen takes a deep dive into the Transformer-based Encoder-Decoder model architecture…
使用區塊稀疏矩陣（Block Sparse Matrices）打造更小、更快的語言模型
Hugging Face Blog2,148 days agoTutorialIn the field of natural language processing (NLP), the Transformer architecture has become the dominant paradigm, but its core self-attention mechanism…