__init__.ja.json

{
 "<h1><a href=\"index.html\">labml.ai Annotated PyTorch Paper Implementations</a></h1>\n": "<h1><a href=\"index.html\">labml.ai \u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u4ed8\u304d PyTorch \u30da\u30fc\u30d1\u30fc\u5b9f\u88c5</a></h1>\n",
 "<h2>Highlighted Research Paper PDFs</h2>\n": "<h2>\u4e3b\u306a\u7814\u7a76\u8ad6\u6587 PDF</h2>\n",
 "<h2>Paper Implementations</h2>\n": "<h2>\u8ad6\u6587\u306b\u3088\u308b\u5b9f\u88c5</h2>\n",
 "<h2>Translations</h2>\n": "<h2>\u7ffb\u8a33</h2>\n",
 "<h3><strong><a href=\"https://nn.labml.ai\">English (original)</a></strong></h3>\n": "<h3><strong><a href=\"https://nn.labml.ai\">\u82f1\u8a9e (\u539f\u6587)</a></strong></h3>\n",
 "<h3><strong><a href=\"https://nn.labml.ai/ja/\">Japanese (translated)</a></strong></h3>\n": "</a><h3><strong><a href=\"https://nn.labml.ai/ja/\">\u65e5\u672c\u8a9e (\u7ffb\u8a33\u6e08\u307f)</strong></h3>\n",
 "<h3><strong><a href=\"https://nn.labml.ai/zh/\">Chinese (translated)</a></strong></h3>\n": "</a><h3><strong><a href=\"https://nn.labml.ai/zh/\">\u4e2d\u56fd\u8a9e (\u7ffb\u8a33\u6e08\u307f)</strong></h3>\n",
 "<h3>Citing LabML</h3>\n": "<h3>LabML \u306e\u5f15\u7528</h3>\n",
 "<h3>Installation</h3>\n": "<h3>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb</h3>\n",
 "<h4>\u2728 <a href=\"activations/index.html\">Activations</a></h4>\n": "<h4>\u2728 <a href=\"activations/index.html\">\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</a></h4>\n",
 "<h4>\u2728 <a href=\"adaptive_computation/index.html\">Adaptive Computation</a></h4>\n": "<h4>\u2728 <a href=\"adaptive_computation/index.html\">\u30a2\u30c0\u30d7\u30c6\u30a3\u30d6\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0</a></h4>\n",
 "<h4>\u2728 <a href=\"capsule_networks/index.html\">Capsule Networks</a></h4>\n": "<h4>\u2728 <a href=\"capsule_networks/index.html\">\u30ab\u30d7\u30bb\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af</a></h4>\n",
 "<h4>\u2728 <a href=\"cfr/index.html\">Counterfactual Regret Minimization (CFR)</a></h4>\n": "<h4>\u2728 <a href=\"cfr/index.html\">\u53cd\u4e8b\u5b9f\u306b\u57fa\u3065\u304f\u5f8c\u6094\u6700\u5c0f\u5316 (CFR)</a></h4>\n",
 "<h4>\u2728 <a href=\"conv_mixer/index.html\">ConvMixer</a></h4>\n": "<h4>\u2728 <a href=\"conv_mixer/index.html\">\u30b3\u30f3\u30d0\u30fc\u30b8\u30e7\u30f3\u30df\u30ad\u30b5\u30fc</a></h4>\n",
 "<h4>\u2728 <a href=\"diffusion/index.html\">Diffusion models</a></h4>\n": "<h4>\u2728 <a href=\"diffusion/index.html\">\u62e1\u6563\u30e2\u30c7\u30eb</a></h4>\n",
 "<h4>\u2728 <a href=\"distillation/index.html\">Distillation</a></h4>\n": "<h4>\u2728 <a href=\"distillation/index.html\">\u84b8\u7559</a></h4>\n",
 "<h4>\u2728 <a href=\"gan/index.html\">Generative Adversarial Networks</a></h4>\n": "<h4>\u2728 <a href=\"gan/index.html\">\u30b8\u30a7\u30cd\u30ec\u30fc\u30c6\u30a3\u30d6\u30fb\u30a2\u30c9\u30d0\u30fc\u30b5\u30ea\u30a2\u30eb\u30fb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af</a></h4>\n",
 "<h4>\u2728 <a href=\"hypernetworks/hyper_lstm.html\">HyperNetworks - HyperLSTM</a></h4>\n": "<h4>\u2728 <a href=\"hypernetworks/hyper_lstm.html\">\u30cf\u30a4\u30d1\u30fc\u30cd\u30c3\u30c8\u30ef\u30fc\u30af-</a> HyperLSTM</h4>\n",
 "<h4>\u2728 <a href=\"lstm/index.html\">LSTM</a></h4>\n": "<h4>\u2728 <a href=\"lstm/index.html\">LSTM</a></h4>\n",
 "<h4>\u2728 <a href=\"neox/index.html\">Eleuther GPT-NeoX</a></h4>\n": "<h4>\u2728 <a href=\"neox/index.html\">\u30a8\u30ea\u30e5\u30fc\u30b5\u30fcGPT-\u30cd\u30aa\u30c3\u30af\u30b9</a></h4>\n",
 "<h4>\u2728 <a href=\"normalization/index.html\">Normalization Layers</a></h4>\n": "<h4>\u2728 <a href=\"normalization/index.html\">\u6b63\u898f\u5316\u30ec\u30a4\u30e4\u30fc</a></h4>\n",
 "<h4>\u2728 <a href=\"optimizers/index.html\">Optimizers</a></h4>\n": "<h4>\u2728 <a href=\"optimizers/index.html\">\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</a></h4>\n",
 "<h4>\u2728 <a href=\"recurrent_highway_networks/index.html\">Recurrent Highway Networks</a></h4>\n": "<h4>\u2728 <a href=\"recurrent_highway_networks/index.html\">\u30ea\u30ab\u30ec\u30f3\u30c8\u30cf\u30a4\u30a6\u30a7\u30a4\u30cd\u30c3\u30c8\u30ef\u30fc\u30af</a></h4>\n",
 "<h4>\u2728 <a href=\"resnet/index.html\">ResNet</a></h4>\n": "<h4>\u2728 <a href=\"resnet/index.html\">\u30ea\u30ba\u30cd\u30c3\u30c8</a></h4>\n",
 "<h4>\u2728 <a href=\"rl/index.html\">Reinforcement Learning</a></h4>\n": "<h4>\u2728 <a href=\"rl/index.html\">\u5f37\u5316\u5b66\u7fd2</a></h4>\n",
 "<h4>\u2728 <a href=\"sampling/index.html\">Language Model Sampling Techniques</a></h4>\n": "<h4>\u2728 <a href=\"sampling/index.html\">\u8a00\u8a9e\u30e2\u30c7\u30eb\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u624b\u6cd5</a></h4>\n",
 "<h4>\u2728 <a href=\"scaling/index.html\">Scalable Training/Inference</a></h4>\n": "<h4>\u2728 <a href=\"scaling/index.html\">\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb\u306a\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0/\u63a8\u8ad6</a></h4>\n",
 "<h4>\u2728 <a href=\"sketch_rnn/index.html\">Sketch RNN</a></h4>\n": "<h4>\u2728 <a href=\"sketch_rnn/index.html\">\u30b9\u30b1\u30c3\u30c1 RNN</a></h4>\n",
 "<h4>\u2728 <a href=\"transformers/index.html\">Transformers</a></h4>\n": "<h4>\u2728 <a href=\"transformers/index.html\">\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc</a></h4>\n",
 "<h4>\u2728 <a href=\"uncertainty/index.html\">Uncertainty</a></h4>\n": "<h4>\u2728 <a href=\"uncertainty/index.html\">\u4e0d\u78ba\u5b9f\u6027</a></h4>\n",
 "<h4>\u2728 <a href=\"unet/index.html\">U-Net</a></h4>\n": "<h4>\u2728 <a href=\"unet/index.html\">\u30e6\u30fc\u30cd\u30c3\u30c8</a></h4>\n",
 "<h4>\u2728 Graph Neural Networks</h4>\n": "<h4>\u2728 \u30b0\u30e9\u30d5\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af</h4>\n",
 "<p><span translate=no>_^_0_^_</span></p>\n": "<p><span translate=no>_^_0_^_</span></p>\n",
 "<p>If you use this for academic research, please cite it using the following BibTeX entry.</p>\n": "<p>\u5b66\u8853\u7814\u7a76\u306b\u4f7f\u7528\u3059\u308b\u5834\u5408\u306f\u3001\u4ee5\u4e0b\u306eBibTeX\u30a8\u30f3\u30c8\u30ea\u3092\u4f7f\u7528\u3057\u3066\u5f15\u7528\u3057\u3066\u304f\u3060\u3055\u3044\u3002</p>\n",
 "<p>Solving games with incomplete information such as poker with CFR.</p>\n": "<p>CFR\u3067\u30dd\u30fc\u30ab\u30fc\u306a\u3069\u306e\u60c5\u5831\u304c\u4e0d\u5b8c\u5168\u306a\u30b2\u30fc\u30e0\u3092\u89e3\u6c7a\u3057\u307e\u3059\u3002</p>\n",
 "<p>This is a collection of simple PyTorch implementations of neural networks and related algorithms. <a href=\"https://github.com/labmlai/annotated_deep_learning_paper_implementations\">These implementations</a> are documented with explanations, and the <a href=\"index.html\">website</a> renders these as side-by-side formatted notes. We believe these would help you understand these algorithms better.</p>\n": "<p>\u3053\u308c\u306f\u3001\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3068\u95a2\u9023\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u5358\u7d14\u306a PyTorch \u5b9f\u88c5\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u3067\u3059\u3002<a href=\"https://github.com/labmlai/annotated_deep_learning_paper_implementations\">\u3053\u308c\u3089\u306e\u5b9f\u88c5\u306f\u8aac\u660e\u4ed8\u304d\u3067\u6587\u66f8\u5316\u3055\u308c\u3066\u304a\u308a</a>\u3001<a href=\"index.html\">\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8\u3067\u306f\u3053\u308c\u3089\u3092\u4e26\u3079\u3066\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3055\u308c\u305f\u30e1\u30e2\u3068\u3057\u3066\u8868\u793a\u3057\u3066\u3044\u307e\u3059</a>\u3002\u3053\u308c\u3089\u306f\u3001\u3053\u308c\u3089\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u3088\u308a\u3088\u304f\u7406\u89e3\u3059\u308b\u306e\u306b\u5f79\u7acb\u3064\u3068\u4fe1\u3058\u3066\u3044\u307e\u3059\u3002</p>\n",
 "<p>We are actively maintaining this repo and adding new implementations. <a href=\"https://twitter.com/labmlai\"><span translate=no>_^_0_^_</span></a> for updates.</p>\n": "<p>\u3053\u306e\u30ea\u30dd\u30b8\u30c8\u30ea\u3092\u7a4d\u6975\u7684\u306b\u7ba1\u7406\u3057\u3001\u65b0\u3057\u3044\u5b9f\u88c5\u3092\u8ffd\u52a0\u3057\u3066\u3044\u307e\u3059\u3002<a href=\"https://twitter.com/labmlai\"><span translate=no>_^_0_^_</span></a>\u66f4\u65b0\u7528\u3002</p>\n",
 "<span translate=no>_^_0_^_</span>": "<span translate=no>_^_0_^_</span>",
 "<ul><li><a href=\"activations/fta/index.html\">Fuzzy Tiling Activations</a></li></ul>\n": "<ul><li><a href=\"activations/fta/index.html\">\u30d5\u30a1\u30b8\u30fc\u30bf\u30a4\u30ea\u30f3\u30b0\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</a></li></ul>\n",
 "<ul><li><a href=\"adaptive_computation/ponder_net/index.html\">PonderNet</a></li></ul>\n": "<ul><li><a href=\"adaptive_computation/ponder_net/index.html\">\u30dd\u30f3\u30c0\u30fc\u30cd\u30c3\u30c8</a></li></ul>\n",
 "<ul><li><a href=\"cfr/kuhn/index.html\">Kuhn Poker</a></li></ul>\n": "<ul><li><a href=\"cfr/kuhn/index.html\">\u30af\u30fc\u30f3\u30dd\u30fc\u30ab\u30fc</a></li></ul>\n",
 "<ul><li><a href=\"diffusion/ddpm/index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> </li>\n<li><a href=\"diffusion/stable_diffusion/sampler/ddim.html\">Denoising Diffusion Implicit Models (DDIM)</a> </li>\n<li><a href=\"diffusion/stable_diffusion/latent_diffusion.html\">Latent Diffusion Models</a> </li>\n<li><a href=\"diffusion/stable_diffusion/index.html\">Stable Diffusion</a></li></ul>\n": "<ul><li><a href=\"diffusion/ddpm/index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM)</a></li>\n<li><a href=\"diffusion/stable_diffusion/sampler/ddim.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u6697\u9ed9\u30e2\u30c7\u30eb (DDIM)</a></li>\n<li><a href=\"diffusion/stable_diffusion/latent_diffusion.html\">\u6f5c\u5728\u62e1\u6563\u30e2\u30c7\u30eb</a></li>\n<li><a href=\"diffusion/stable_diffusion/index.html\">\u5b89\u5b9a\u62e1\u6563</a></li></ul>\n",
 "<ul><li><a href=\"gan/original/index.html\">Original GAN</a> </li>\n<li><a href=\"gan/dcgan/index.html\">GAN with deep convolutional network</a> </li>\n<li><a href=\"gan/cycle_gan/index.html\">Cycle GAN</a> </li>\n<li><a href=\"gan/wasserstein/index.html\">Wasserstein GAN</a> </li>\n<li><a href=\"gan/wasserstein/gradient_penalty/index.html\">Wasserstein GAN with Gradient Penalty</a> </li>\n<li><a href=\"gan/stylegan/index.html\">StyleGAN 2</a></li></ul>\n": "<ul><li><a href=\"gan/original/index.html\">\u30aa\u30ea\u30b8\u30ca\u30ebGAN</a></li>\n<li><a href=\"gan/dcgan/index.html\">\u6df1\u3044\u7573\u307f\u8fbc\u307f\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u5099\u3048\u305fGAN</a></li>\n<li><a href=\"gan/cycle_gan/index.html\">\u30b5\u30a4\u30af\u30eb GAN</a></li>\n<li><a href=\"gan/wasserstein/index.html\">\u30ef\u30c3\u30b5\u30fc\u30b9\u30bf\u30a4\u30f3 GAN</a></li>\n<li><a href=\"gan/wasserstein/gradient_penalty/index.html\">\u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u30da\u30ca\u30eb\u30c6\u30a3\u4ed8\u304d\u30ef\u30c3\u30b5\u30fc\u30b9\u30bf\u30a4\u30f3 GAN</a></li>\n<li><a href=\"gan/stylegan/index.html\">\u30b9\u30bf\u30a4\u30eb\u30ac\u30f3 2</a></li></ul>\n",
 "<ul><li><a href=\"graphs/gat/index.html\">Graph Attention Networks (GAT)</a> </li>\n<li><a href=\"graphs/gatv2/index.html\">Graph Attention Networks v2 (GATv2)</a></li></ul>\n": "<ul><li><a href=\"graphs/gat/index.html\">\u30b0\u30e9\u30d5\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30fb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af (GAT)</a></li>\n</ul><li><a href=\"graphs/gatv2/index.html\">\u30b0\u30e9\u30d5\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30fb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u30b9 v2 (GATv2)</a></li>\n",
 "<ul><li><a href=\"neox/samples/generate.html\">Generate on a 48GB GPU</a> </li>\n<li><a href=\"neox/samples/finetune.html\">Finetune on two 48GB GPUs</a> </li>\n<li><a href=\"neox/utils/llm_int8.html\">LLM.int8()</a></li></ul>\n": "<ul><li><a href=\"neox/samples/generate.html\">48 GB \u306e GPU \u3067\u751f\u6210</a></li>\n<li><a href=\"neox/samples/finetune.html\">2 \u3064\u306e 48 GB GPU \u3067\u5fae\u8abf\u6574\u53ef\u80fd</a></li>\n<li><a href=\"neox/utils/llm_int8.html\">llm.int8</a></li></ul>\n",
 "<ul><li><a href=\"normalization/batch_norm/index.html\">Batch Normalization</a> </li>\n<li><a href=\"normalization/layer_norm/index.html\">Layer Normalization</a> </li>\n<li><a href=\"normalization/instance_norm/index.html\">Instance Normalization</a> </li>\n<li><a href=\"normalization/group_norm/index.html\">Group Normalization</a> </li>\n<li><a href=\"normalization/weight_standardization/index.html\">Weight Standardization</a> </li>\n<li><a href=\"normalization/batch_channel_norm/index.html\">Batch-Channel Normalization</a> </li>\n<li><a href=\"normalization/deep_norm/index.html\">DeepNorm</a></li></ul>\n": "<ul><li><a href=\"normalization/batch_norm/index.html\">\u30d0\u30c3\u30c1\u6b63\u898f\u5316</a></li>\n<li><a href=\"normalization/layer_norm/index.html\">\u30ec\u30a4\u30e4\u30fc\u6b63\u898f\u5316</a></li>\n<li><a href=\"normalization/instance_norm/index.html\">\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u6b63\u898f\u5316</a></li>\n<li><a href=\"normalization/group_norm/index.html\">\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316</a></li>\n<li><a href=\"normalization/weight_standardization/index.html\">\u91cd\u91cf\u6a19\u6e96\u5316</a></li>\n<li><a href=\"normalization/batch_channel_norm/index.html\">\u30d0\u30c3\u30c1\u30c1\u30e3\u30cd\u30eb\u6b63\u898f\u5316</a></li>\n</ul><li><a href=\"normalization/deep_norm/index.html\">\u30c7\u30a3\u30fc\u30d7\u30fb\u30ce\u30fc\u30e0</a></li>\n",
 "<ul><li><a href=\"optimizers/adam.html\">Adam</a> </li>\n<li><a href=\"optimizers/amsgrad.html\">AMSGrad</a> </li>\n<li><a href=\"optimizers/adam_warmup.html\">Adam Optimizer with warmup</a> </li>\n<li><a href=\"optimizers/noam.html\">Noam Optimizer</a> </li>\n<li><a href=\"optimizers/radam.html\">Rectified Adam Optimizer</a> </li>\n<li><a href=\"optimizers/ada_belief.html\">AdaBelief Optimizer</a></li></ul>\n": "<ul><li><a href=\"optimizers/adam.html\">\u30a2\u30c0\u30e0</a></li>\n<li><a href=\"optimizers/amsgrad.html\">\u30de\u30b9\u30b0\u30e9\u30fc\u30c9</a></li>\n<li><a href=\"optimizers/adam_warmup.html\">\u30a6\u30a9\u30fc\u30e0\u30a2\u30c3\u30d7\u6a5f\u80fd\u4ed8\u304d Adam \u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</a></li>\n<li><a href=\"optimizers/noam.html\">\u30ce\u30fc\u30e0\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</a></li>\n<li><a href=\"optimizers/radam.html\">\u30ec\u30af\u30c6\u30a3\u30d5\u30a1\u30a4\u30c9\u30fb\u30a2\u30c0\u30e0\u30fb\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</a></li>\n<li><a href=\"optimizers/ada_belief.html\">\u30a2\u30c0\u30d6\u30ea\u30ea\u30fc\u30d5\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</a></li></ul>\n",
 "<ul><li><a href=\"rl/ppo/index.html\">Proximal Policy Optimization</a> with  <a href=\"rl/ppo/gae.html\">Generalized Advantage Estimation</a> </li>\n<li><a href=\"rl/dqn/index.html\">Deep Q Networks</a> with  with <a href=\"rl/dqn/model.html\">Dueling Network</a>,  <a href=\"rl/dqn/replay_buffer.html\">Prioritized Replay</a>  and Double Q Network.</li></ul>\n": "<ul><li><a href=\"rl/ppo/index.html\"><a href=\"rl/ppo/gae.html\">\u4e00\u822c\u5316\u30a2\u30c9\u30d0\u30f3\u30c6\u30fc\u30b8\u63a8\u5b9a\u306b\u3088\u308b\u8fd1\u4f4d\u653f\u7b56\u6700\u9069\u5316</a></a></li>\n</ul><li><a href=\"rl/dqn/index.html\"><a href=\"rl/dqn/model.html\">\u30c7\u30e5\u30a8\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3001<a href=\"rl/dqn/replay_buffer.html\">\u512a\u5148\u30ea\u30d7\u30ec\u30a4</a>\u3001\u30c0\u30d6\u30ebQ\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u5099\u3048\u305f\u30c7\u30a3\u30fc\u30d7Q\u30cd\u30c3\u30c8\u30ef\u30fc\u30af</a></a>\u3002</li>\n",
 "<ul><li><a href=\"sampling/greedy.html\">Greedy Sampling</a> </li>\n<li><a href=\"sampling/temperature.html\">Temperature Sampling</a> </li>\n<li><a href=\"sampling/top_k.html\">Top-k Sampling</a> </li>\n<li><a href=\"sampling/nucleus.html\">Nucleus Sampling</a></li></ul>\n": "<ul><li><a href=\"sampling/greedy.html\">\u6b32\u5f35\u308a\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</a></li>\n<li><a href=\"sampling/temperature.html\">\u6e29\u5ea6\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</a></li>\n<li><a href=\"sampling/top_k.html\">\u30c8\u30c3\u30d7k\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</a></li>\n<li><a href=\"sampling/nucleus.html\">\u6838\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</a></li></ul>\n",
 "<ul><li><a href=\"scaling/zero3/index.html\">Zero3 memory optimizations</a></li></ul>\n": "<ul><li><a href=\"scaling/zero3/index.html\">Zero3 \u30e1\u30e2\u30ea\u6700\u9069\u5316</a></li></ul>\n",
 "<ul><li><a href=\"transformers/mha.html\">Multi-headed attention</a> </li>\n<li><a href=\"transformers/models.html\">Transformer building blocks</a> </li>\n<li><a href=\"transformers/xl/index.html\">Transformer XL</a>  </li>\n<li><a href=\"transformers/xl/relative_mha.html\">Relative multi-headed attention</a> </li>\n<li><a href=\"transformers/rope/index.html\">Rotary Positional Embeddings (RoPE)</a> </li>\n<li><a href=\"transformers/alibi/index.html\">Attention with Linear Biases (ALiBi)</a> </li>\n<li><a href=\"transformers/retro/index.html\">RETRO</a> </li>\n<li><a href=\"transformers/compressive/index.html\">Compressive Transformer</a> </li>\n<li><a href=\"transformers/gpt/index.html\">GPT Architecture</a> </li>\n<li><a href=\"transformers/glu_variants/simple.html\">GLU Variants</a> </li>\n<li><a href=\"transformers/knn/index.html\">kNN-LM: Generalization through Memorization</a> </li>\n<li><a href=\"transformers/feedback/index.html\">Feedback Transformer</a> </li>\n<li><a href=\"transformers/switch/index.html\">Switch Transformer</a> </li>\n<li><a href=\"transformers/fast_weights/index.html\">Fast Weights Transformer</a> </li>\n<li><a href=\"transformers/fnet/index.html\">FNet</a> </li>\n<li><a href=\"transformers/aft/index.html\">Attention Free Transformer</a> </li>\n<li><a href=\"transformers/mlm/index.html\">Masked Language Model</a> </li>\n<li><a href=\"transformers/mlp_mixer/index.html\">MLP-Mixer: An all-MLP Architecture for Vision</a> </li>\n<li><a href=\"transformers/gmlp/index.html\">Pay Attention to MLPs (gMLP)</a> </li>\n<li><a href=\"transformers/vit/index.html\">Vision Transformer (ViT)</a> </li>\n<li><a href=\"transformers/primer_ez/index.html\">Primer EZ</a> </li>\n<li><a href=\"transformers/hour_glass/index.html\">Hourglass</a></li></ul>\n": "<ul><li><a href=\"transformers/mha.html\">\u591a\u9762\u7684\u306a\u6ce8\u610f</a></li>\n<li><a href=\"transformers/models.html\">\u5909\u5727\u5668\u30d3\u30eb\u30c7\u30a3\u30f3\u30b0\u30d6\u30ed\u30c3\u30af</a></li>\n<li><a href=\"transformers/xl/index.html\">\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc XL</a></li>\n<li><a href=\"transformers/xl/relative_mha.html\">\u6bd4\u8f03\u7684\u591a\u9762\u7684\u306a\u6ce8\u610f</a></li>\n<li><a href=\"transformers/rope/index.html\">\u30ed\u30fc\u30bf\u30ea\u30fc\u30fb\u30dd\u30b8\u30b7\u30e7\u30ca\u30eb\u30fb\u30a8\u30f3\u30d9\u30c7\u30a3\u30f3\u30b0 (RoPe)</a></li>\n<li><a href=\"transformers/alibi/index.html\">\u7dda\u5f62\u30d0\u30a4\u30a2\u30b9\u306b\u3088\u308b\u6ce8\u610f (AliBi)</a></li>\n<li><a href=\"transformers/retro/index.html\">\u30ec\u30c8\u30ed</a></li>\n<li><a href=\"transformers/compressive/index.html\">\u5727\u7e2e\u5909\u5727\u5668</a></li>\n<li><a href=\"transformers/gpt/index.html\">GPT \u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3</a></li>\n<li><a href=\"transformers/glu_variants/simple.html\">GLU \u30d0\u30ea\u30a2\u30f3\u30c8</a></li>\n<li><a href=\"transformers/knn/index.html\">Knn-LM: \u6697\u8a18\u306b\u3088\u308b\u4e00\u822c\u5316</a></li>\n<li><a href=\"transformers/feedback/index.html\">\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u5909\u5727\u5668</a></li>\n<li><a href=\"transformers/switch/index.html\">\u30b9\u30a4\u30c3\u30c1\u30c8\u30e9\u30f3\u30b9</a></li>\n<li><a href=\"transformers/fast_weights/index.html\">\u9ad8\u901f\u30a6\u30a7\u30a4\u30c8\u30c8\u30e9\u30f3\u30b9</a></li>\n<li><a href=\"transformers/fnet/index.html\">FNet</a></li>\n<li><a href=\"transformers/aft/index.html\">\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30d5\u30ea\u30fc\u5909\u5727\u5668</a></li>\n<li><a href=\"transformers/mlm/index.html\">\u30de\u30b9\u30af\u8a00\u8a9e\u30e2\u30c7\u30eb</a></li>\n<li><a href=\"transformers/mlp_mixer/index.html\">MLP\u30df\u30ad\u30b5\u30fc:\u30d3\u30b8\u30e7\u30f3\u7528\u306e\u30aa\u30fc\u30ebMLP\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3</a></li>\n<li><a href=\"transformers/gmlp/index.html\">MLP (GMLP) \u306b\u3054\u6ce8\u610f\u304f\u3060\u3055\u3044</a></li>\n<li><a href=\"transformers/vit/index.html\">\u30d3\u30b8\u30e7\u30f3\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc (ViT)</a></li>\n<li><a href=\"transformers/primer_ez/index.html\">\u30d7\u30e9\u30a4\u30de\u30fc EZ</a></li>\n<li><a href=\"transformers/hour_glass/index.html\">\u7802\u6642\u8a08</a></li></ul>\n",
 "<ul><li><a href=\"uncertainty/evidence/index.html\">Evidential Deep Learning to Quantify Classification Uncertainty</a></li></ul>\n": "<ul><li><a href=\"uncertainty/evidence/index.html\">\u5206\u985e\u306e\u4e0d\u78ba\u5b9f\u6027\u3092\u5b9a\u91cf\u5316\u3059\u308b\u30a8\u30d3\u30c7\u30f3\u30b7\u30e3\u30eb\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0</a></li></ul>\n",
 "labml.ai Annotated PyTorch Paper Implementations": "labml.ai \u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u4ed8\u304d PyTorch \u30da\u30fc\u30d1\u30fc\u5b9f\u88c5"
}