TruthfulQA: Measuring how models mimic human falsehoods
AI 速览 TruthfulQA基准用于衡量语言模型模仿人类虚假陈述的倾向。
按时间倒序汇集的来源索引。展示关键元数据并引导直达原始报道。
AI 速览 TruthfulQA基准用于衡量语言模型模仿人类虚假陈述的倾向。
We’ve created an improved version of OpenAI Codex, our AI system that translates natural language to code, and we are releasing it through our API in private beta starting today.
We’re releasing Triton 1.0, an open-source Python-like programming language which enables researchers with no CUDA experience to write highly efficient GPU code—most of the time on par with what an expert would be able to produce.
AI 速览 Deep Learning over the Internet提出通过互联网协作训练语言模型的方法。
AI 速览 spaCy正式入驻Hugging Face Hub。
AI 速览 Hugging Face模型现可通过Amazon SageMaker便捷部署。
AI 速览 评估基于代码训练的大型语言模型。
AI 速览 Hugging Face Hub现已集成Sentence Transformers,支持开发者直接获取和使用预训练句子嵌入模型。
Our latest research finds we can improve language model behavior with respect to specific behavioral values by fine-tuning on a small, curated dataset.
AI 速览 Hugging Face发布关于GPT-Neo与🤗加速推理API在少样本学习实践中的应用内容。
AI 速览 Hugging Face发布Gradio 2.0,支持混合使用多个Hugging Face模型。
We’re proud to announce that the 2021 class of OpenAI Scholars has completed our six-month mentorship program and have produced an open-source research project with stipends and support from OpenAI.
OpenAI is committed to developing general-purpose artificial intelligence that benefits all humanity, and we believe that achieving our goal requires expertise in public policy as well as technology. So, we’re delighted to announce that Congressman Will Hurd has joined our board of directors.
AI 速览 BERT模型在CPU上的推理扩展方法(第一部分)。
AI 速览 🤗 Accelerate正式发布。
AI 速览 Hugging Face联合Amazon SageMaker发布分布式训练教程,介绍如何用Transformers库训练BART/T5模型完成摘要任务。
AI 速览 BigBird的块稀疏注意力机制通过结合局部注意力、全局注意力和随机注意力,将复杂度从O(n²)降至O(n),以处理长序列。
Over 300 applications are delivering GPT-3–powered search, conversation, text completion, and other advanced AI features through our API.
AI 速览 亚马逊SageMaker与Hugging Face达成合作。
AI 速览 作者分享了在Google Cloud上构建无服务器Transformers流水线的实践历程。
AI 速览 使用🤗 Transformers在Hugging Face上微调Wav2Vec2模型,以实现英语自动语音识别(ASR)。
AI 速览 Hugging Face于2021年2月举办“Hugging Face Reads”活动,主题为长程Transformer(Long-range Transformers)。
We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn.
AI 速览 构建复杂神经网络时,简单原则同样适用:优先选择简洁架构、控制参数量并重视数据质量,避免不必要的复杂度。
AI 速览 Huggingface Transformers与Ray结合实现检索增强生成(RAG)。
AI 速览 Hugging Face宣布支持基于PyTorch/XLA的TPU。
AI 速览 大型语言模型的能力、局限及社会影响研究。
AI 速览 Hugging Face Transformers优化TensorFlow模型,提升推理速度。
We’ve scaled Kubernetes clusters to 7,500 nodes, producing a scalable infrastructure for large models like GPT-3, CLIP, and DALL·E, but also for rapid small-scale iterative research such as Scaling Laws for Neural Language Models.
AI 速览 微软DeepSpeed与FairScale集成ZeRO技术,可提升模型训练规模与速度。