Hugging Face 官方数据集库,汇集海量即用型 AI 数据集,并提供高效的数据加载与处理工具,省去自己找数据、写加载代码的麻烦。
在浏览器里直接跑 Hugging Face 的 Transformer 模型,不用后端服务器,前端就能做文本、视觉等机器学习推理。
用 LoRA、Adapter 等少量参数微调大模型和扩散模型,大幅降低显存与训练成本,是 Hugging Face 生态里做参数高效微调的标准库。
收录最全的 PyTorch 图像骨干网络合集,涵盖 ResNet、ViT、ConvNeXt 等主流模型,自带训练、评估、推理和导出脚本及预训练权重,省去自己搭网络和找权重的麻烦。
用强化学习训练 Transformer 语言模型的全流程库,覆盖 SFT、奖励建模到 PPO/DPO 等 RLHF 算法,省去自己拼训练管线。
把大语言模型和 Hugging Face 上的各类模型连起来,让 LLM 自动挑选、调用合适的模型完成多模态任务,相当于给模型加了个调度中枢。
开源金融大语言模型,提供训练好的模型和微调流程,用于金融情感分析、智能投顾等场景。
HuggingFace Transformers 库的实战教程合集,用 Jupyter Notebook 演示 BERT、GPT-2、LayoutLM、ViT 等模型的微调与推理,适合边跑边学。
开源语音识别工具包,覆盖训练、推理、流式 ASR、VAD、标点恢复和说话人分离全流程,并提供 OpenAI 兼容与 MCP 服务接口。
用 GRPO 强化学习给多步 Agent 做在线训练,让 Qwen、Llama 等模型在真实任务里边干边学,提升实际表现。
…rbor benchmarks by @lhoestq in https://github.com/huggingface/datasets/pull/8729 Vortex 🌀: High performance columnar data Add support for datasets backed by vortex file f
…in init .py by @qgallouedec in https://github.com/huggingface/datasets/pull/8244 fix conda build by @lhoestq in https://github.com/huggingface/datasets/pull/8250 Fix JSON
…easing by @IlyasMoutawwakil in https://github.com/huggingface/optimum/pull/2395 Remove deprecated INC and IPEX from documentation by @echarlaix in https://github.com/huggi
…() ( 8116) by @Brianzhengca in https://github.com/huggingface/datasets/pull/8122 Fix: decode JSON type before to list or to dict is called by @ItsTania in https://github.c
…gration by @michaelbenayoun in https://github.com/huggingface/accelerate/pull/3935 XPU Improvements We've removed IPEX dependency and improved device-agnostic code for XPU
…ort for Zamba2 by @rkazants in https://github.com/huggingface/optimum-intel/pull/1354 Add OpenVINO support for BitNet by @rkazants in https://github.com/huggingface/optimu