From d858f2eec021cd02453cbf80f694801e271917a4 Mon Sep 17 00:00:00 2001 From: Varuna Jayasiri Date: Fri, 21 Jun 2024 19:35:22 +0530 Subject: [PATCH] remove tranding papers link --- docs/RWKV/configs.html | 1 - docs/RWKV/experiment.html | 1 - docs/RWKV/index.html | 1 - docs/activations/fta/experiment.html | 1 - docs/activations/fta/index.html | 1 - docs/activations/index.html | 1 - docs/activations/swish.html | 1 - docs/adaptive_computation/index.html | 1 - docs/adaptive_computation/parity.html | 1 - docs/adaptive_computation/ponder_net/experiment.html | 1 - docs/adaptive_computation/ponder_net/index.html | 1 - docs/adaptive_computation/ponder_net/readme.html | 1 - docs/adaptive_computation/readme.html | 1 - docs/capsule_networks/index.html | 1 - docs/capsule_networks/mnist.html | 1 - docs/capsule_networks/readme.html | 1 - docs/cfr/analytics.html | 1 - docs/cfr/index.html | 1 - docs/cfr/infoset_saver.html | 1 - docs/cfr/kuhn/index.html | 1 - docs/conv_mixer/experiment.html | 1 - docs/conv_mixer/index.html | 1 - docs/conv_mixer/readme.html | 1 - docs/diffusion/ddpm/evaluate.html | 1 - docs/diffusion/ddpm/experiment.html | 1 - docs/diffusion/ddpm/index.html | 1 - docs/diffusion/ddpm/readme.html | 1 - docs/diffusion/ddpm/unet.html | 1 - docs/diffusion/ddpm/utils.html | 1 - docs/diffusion/index.html | 1 - docs/diffusion/stable_diffusion/index.html | 1 - docs/diffusion/stable_diffusion/latent_diffusion.html | 1 - docs/diffusion/stable_diffusion/model/autoencoder.html | 1 - docs/diffusion/stable_diffusion/model/clip_embedder.html | 1 - docs/diffusion/stable_diffusion/model/index.html | 1 - docs/diffusion/stable_diffusion/model/unet.html | 1 - docs/diffusion/stable_diffusion/model/unet_attention.html | 1 - docs/diffusion/stable_diffusion/sampler/ddim.html | 1 - docs/diffusion/stable_diffusion/sampler/ddpm.html | 1 - docs/diffusion/stable_diffusion/sampler/index.html | 1 - docs/diffusion/stable_diffusion/scripts/image_to_image.html | 1 - docs/diffusion/stable_diffusion/scripts/in_paint.html | 1 - docs/diffusion/stable_diffusion/scripts/index.html | 1 - docs/diffusion/stable_diffusion/scripts/text_to_image.html | 1 - docs/diffusion/stable_diffusion/util.html | 1 - docs/distillation/index.html | 1 - docs/distillation/large.html | 1 - docs/distillation/readme.html | 1 - docs/distillation/small.html | 1 - docs/experiments/arithmetic_dataset.html | 1 - docs/experiments/cifar10.html | 1 - docs/experiments/index.html | 1 - docs/experiments/mnist.html | 1 - docs/experiments/nlp_autoregression.html | 1 - docs/experiments/nlp_classification.html | 1 - docs/gan/cycle_gan/index.html | 1 - docs/gan/cycle_gan/readme.html | 1 - docs/gan/dcgan/index.html | 1 - docs/gan/dcgan/readme.html | 1 - docs/gan/index.html | 1 - docs/gan/original/experiment.html | 1 - docs/gan/original/index.html | 1 - docs/gan/original/readme.html | 1 - docs/gan/stylegan/experiment.html | 1 - docs/gan/stylegan/index.html | 1 - docs/gan/stylegan/readme.html | 1 - docs/gan/wasserstein/experiment.html | 1 - docs/gan/wasserstein/gradient_penalty/experiment.html | 1 - docs/gan/wasserstein/gradient_penalty/index.html | 1 - docs/gan/wasserstein/gradient_penalty/readme.html | 1 - docs/gan/wasserstein/index.html | 1 - docs/gan/wasserstein/readme.html | 1 - docs/graphs/gat/experiment.html | 1 - docs/graphs/gat/index.html | 1 - docs/graphs/gat/readme.html | 1 - docs/graphs/gatv2/experiment.html | 1 - docs/graphs/gatv2/index.html | 1 - docs/graphs/gatv2/readme.html | 1 - docs/graphs/index.html | 1 - docs/hypernetworks/experiment.html | 1 - docs/hypernetworks/hyper_lstm.html | 1 - docs/hypernetworks/index.html | 1 - docs/index.html | 1 - docs/lstm/index.html | 1 - docs/neox/checkpoint.html | 1 - docs/neox/evaluation/half_precision.html | 1 - docs/neox/evaluation/index.html | 1 - docs/neox/evaluation/llm_int8.html | 1 - docs/neox/index.html | 1 - docs/neox/model.html | 1 - docs/neox/readme.html | 1 - docs/neox/samples/finetune.html | 1 - docs/neox/samples/generate.html | 1 - docs/neox/samples/index.html | 1 - docs/neox/samples/llm_int8.html | 1 - docs/neox/tokenizer.html | 1 - docs/neox/utils/cache.html | 1 - docs/neox/utils/finetune.html | 1 - docs/neox/utils/index.html | 1 - docs/neox/utils/llm_int8.html | 1 - docs/neox/utils/text_dataset.html | 1 - docs/neox/utils/trainer.html | 1 - docs/normalization/batch_channel_norm/index.html | 1 - docs/normalization/batch_norm/cifar10.html | 1 - docs/normalization/batch_norm/index.html | 1 - docs/normalization/batch_norm/mnist.html | 1 - docs/normalization/batch_norm/readme.html | 1 - docs/normalization/deep_norm/experiment.html | 1 - docs/normalization/deep_norm/index.html | 1 - docs/normalization/group_norm/experiment.html | 1 - docs/normalization/group_norm/index.html | 1 - docs/normalization/group_norm/readme.html | 1 - docs/normalization/index.html | 1 - docs/normalization/instance_norm/experiment.html | 1 - docs/normalization/instance_norm/index.html | 1 - docs/normalization/instance_norm/readme.html | 1 - docs/normalization/layer_norm/index.html | 1 - docs/normalization/layer_norm/readme.html | 1 - docs/normalization/weight_standardization/conv2d.html | 1 - docs/normalization/weight_standardization/experiment.html | 1 - docs/normalization/weight_standardization/index.html | 1 - docs/normalization/weight_standardization/readme.html | 1 - docs/optimizers/ada_belief.html | 1 - docs/optimizers/adam.html | 1 - docs/optimizers/adam_fp16.html | 1 - docs/optimizers/adam_warmup.html | 1 - docs/optimizers/adam_warmup_cosine_decay.html | 1 - docs/optimizers/amsgrad.html | 1 - docs/optimizers/configs.html | 1 - docs/optimizers/index.html | 1 - docs/optimizers/mnist_experiment.html | 1 - docs/optimizers/noam.html | 1 - docs/optimizers/performance_test.html | 1 - docs/optimizers/radam.html | 1 - docs/optimizers/readme.html | 1 - docs/optimizers/sophia.html | 1 - docs/recurrent_highway_networks/index.html | 1 - docs/resnet/experiment.html | 1 - docs/resnet/index.html | 1 - docs/resnet/readme.html | 1 - docs/rl/dqn/experiment.html | 1 - docs/rl/dqn/index.html | 1 - docs/rl/dqn/model.html | 1 - docs/rl/dqn/readme.html | 1 - docs/rl/dqn/replay_buffer.html | 1 - docs/rl/game.html | 1 - docs/rl/index.html | 1 - docs/rl/ppo/experiment.html | 1 - docs/rl/ppo/gae.html | 1 - docs/rl/ppo/index.html | 1 - docs/rl/ppo/readme.html | 1 - docs/sampling/experiment.html | 1 - docs/sampling/experiment_tiny.html | 1 - docs/sampling/greedy.html | 1 - docs/sampling/index.html | 1 - docs/sampling/nucleus.html | 1 - docs/sampling/temperature.html | 1 - docs/sampling/top_k.html | 1 - docs/scaling/index.html | 1 - docs/scaling/zero3/finetune_neox.html | 1 - docs/scaling/zero3/index.html | 1 - docs/sitemap.xml | 4 ++-- docs/sketch_rnn/index.html | 1 - docs/transformers/aft/experiment.html | 1 - docs/transformers/aft/index.html | 1 - docs/transformers/aft/readme.html | 1 - docs/transformers/alibi/experiment.html | 1 - docs/transformers/alibi/index.html | 1 - docs/transformers/basic/autoregressive_experiment.html | 1 - docs/transformers/basic/index.html | 1 - docs/transformers/basic/with_sophia.html | 1 - docs/transformers/compressive/experiment.html | 1 - docs/transformers/compressive/index.html | 1 - docs/transformers/compressive/readme.html | 1 - docs/transformers/configs.html | 1 - docs/transformers/fast_weights/experiment.html | 1 - docs/transformers/fast_weights/index.html | 1 - docs/transformers/fast_weights/readme.html | 1 - docs/transformers/fast_weights/token_wise.html | 1 - docs/transformers/feed_forward.html | 1 - docs/transformers/feedback/experiment.html | 1 - docs/transformers/feedback/index.html | 1 - docs/transformers/feedback/readme.html | 1 - docs/transformers/fnet/experiment.html | 1 - docs/transformers/fnet/index.html | 1 - docs/transformers/fnet/readme.html | 1 - docs/transformers/glu_variants/experiment.html | 1 - docs/transformers/glu_variants/index.html | 1 - docs/transformers/glu_variants/simple.html | 1 - docs/transformers/gmlp/experiment.html | 1 - docs/transformers/gmlp/index.html | 1 - docs/transformers/gmlp/readme.html | 1 - docs/transformers/gpt/index.html | 1 - docs/transformers/hour_glass/experiment.html | 1 - docs/transformers/hour_glass/index.html | 1 - docs/transformers/index.html | 1 - docs/transformers/knn/build_index.html | 1 - docs/transformers/knn/eval_knn.html | 1 - docs/transformers/knn/index.html | 1 - docs/transformers/knn/train_model.html | 1 - docs/transformers/label_smoothing_loss.html | 1 - docs/transformers/mha.html | 1 - docs/transformers/mlm/experiment.html | 1 - docs/transformers/mlm/index.html | 1 - docs/transformers/mlm/readme.html | 1 - docs/transformers/mlp_mixer/experiment.html | 1 - docs/transformers/mlp_mixer/index.html | 1 - docs/transformers/mlp_mixer/readme.html | 1 - docs/transformers/models.html | 1 - docs/transformers/positional_encoding.html | 1 - docs/transformers/primer_ez/efficient.html | 1 - docs/transformers/primer_ez/experiment.html | 1 - docs/transformers/primer_ez/index.html | 1 - docs/transformers/primer_ez/readme.html | 1 - docs/transformers/primer_ez/variations.html | 1 - docs/transformers/relative_mha.html | 1 - docs/transformers/retro/bert_embeddings.html | 1 - docs/transformers/retro/database.html | 1 - docs/transformers/retro/dataset.html | 1 - docs/transformers/retro/index.html | 1 - docs/transformers/retro/model.html | 1 - docs/transformers/retro/train.html | 1 - docs/transformers/rope/experiment.html | 1 - docs/transformers/rope/index.html | 1 - docs/transformers/rope/value_pe/arithmetic_experiment.html | 1 - docs/transformers/rope/value_pe/experiment.html | 1 - docs/transformers/rope/value_pe/index.html | 1 - docs/transformers/switch/experiment.html | 1 - docs/transformers/switch/index.html | 1 - docs/transformers/switch/readme.html | 1 - docs/transformers/utils.html | 1 - docs/transformers/vit/experiment.html | 1 - docs/transformers/vit/index.html | 1 - docs/transformers/vit/readme.html | 1 - docs/transformers/xl/experiment.html | 1 - docs/transformers/xl/index.html | 1 - docs/transformers/xl/readme.html | 1 - docs/transformers/xl/relative_mha.html | 1 - docs/uncertainty/evidence/experiment.html | 1 - docs/uncertainty/evidence/index.html | 1 - docs/uncertainty/evidence/readme.html | 1 - docs/uncertainty/index.html | 1 - docs/uncertainty/readme.html | 1 - docs/unet/carvana.html | 1 - docs/unet/experiment.html | 1 - docs/unet/index.html | 1 - docs/utils/index.html | 1 - docs/utils/tokenizer.html | 1 - docs/zh/RWKV/configs.html | 1 - docs/zh/RWKV/experiment.html | 1 - docs/zh/RWKV/index.html | 1 - docs/zh/activations/fta/experiment.html | 1 - docs/zh/activations/fta/index.html | 1 - docs/zh/activations/index.html | 1 - docs/zh/activations/swish.html | 1 - docs/zh/adaptive_computation/index.html | 1 - docs/zh/adaptive_computation/parity.html | 1 - docs/zh/adaptive_computation/ponder_net/experiment.html | 1 - docs/zh/adaptive_computation/ponder_net/index.html | 1 - docs/zh/adaptive_computation/ponder_net/readme.html | 1 - docs/zh/adaptive_computation/readme.html | 1 - docs/zh/capsule_networks/index.html | 1 - docs/zh/capsule_networks/mnist.html | 1 - docs/zh/capsule_networks/readme.html | 1 - docs/zh/cfr/analytics.html | 1 - docs/zh/cfr/index.html | 1 - docs/zh/cfr/infoset_saver.html | 1 - docs/zh/cfr/kuhn/index.html | 1 - docs/zh/conv_mixer/experiment.html | 1 - docs/zh/conv_mixer/index.html | 1 - docs/zh/conv_mixer/readme.html | 1 - docs/zh/diffusion/ddpm/evaluate.html | 1 - docs/zh/diffusion/ddpm/experiment.html | 1 - docs/zh/diffusion/ddpm/index.html | 1 - docs/zh/diffusion/ddpm/readme.html | 1 - docs/zh/diffusion/ddpm/unet.html | 1 - docs/zh/diffusion/ddpm/utils.html | 1 - docs/zh/diffusion/index.html | 1 - docs/zh/diffusion/stable_diffusion/index.html | 1 - docs/zh/diffusion/stable_diffusion/latent_diffusion.html | 1 - docs/zh/diffusion/stable_diffusion/model/autoencoder.html | 1 - docs/zh/diffusion/stable_diffusion/model/clip_embedder.html | 1 - docs/zh/diffusion/stable_diffusion/model/index.html | 1 - docs/zh/diffusion/stable_diffusion/model/unet.html | 1 - docs/zh/diffusion/stable_diffusion/model/unet_attention.html | 1 - docs/zh/diffusion/stable_diffusion/sampler/ddim.html | 1 - docs/zh/diffusion/stable_diffusion/sampler/ddpm.html | 1 - docs/zh/diffusion/stable_diffusion/sampler/index.html | 1 - .../zh/diffusion/stable_diffusion/scripts/image_to_image.html | 1 - docs/zh/diffusion/stable_diffusion/scripts/in_paint.html | 1 - docs/zh/diffusion/stable_diffusion/scripts/index.html | 1 - docs/zh/diffusion/stable_diffusion/scripts/text_to_image.html | 1 - docs/zh/diffusion/stable_diffusion/util.html | 1 - docs/zh/distillation/index.html | 1 - docs/zh/distillation/large.html | 1 - docs/zh/distillation/readme.html | 1 - docs/zh/distillation/small.html | 1 - docs/zh/experiments/arithmetic_dataset.html | 1 - docs/zh/experiments/cifar10.html | 1 - docs/zh/experiments/index.html | 1 - docs/zh/experiments/mnist.html | 1 - docs/zh/experiments/nlp_autoregression.html | 1 - docs/zh/experiments/nlp_classification.html | 1 - docs/zh/gan/cycle_gan/index.html | 1 - docs/zh/gan/cycle_gan/readme.html | 1 - docs/zh/gan/dcgan/index.html | 1 - docs/zh/gan/dcgan/readme.html | 1 - docs/zh/gan/index.html | 1 - docs/zh/gan/original/experiment.html | 1 - docs/zh/gan/original/index.html | 1 - docs/zh/gan/original/readme.html | 1 - docs/zh/gan/stylegan/experiment.html | 1 - docs/zh/gan/stylegan/index.html | 1 - docs/zh/gan/stylegan/readme.html | 1 - docs/zh/gan/wasserstein/experiment.html | 1 - docs/zh/gan/wasserstein/gradient_penalty/experiment.html | 1 - docs/zh/gan/wasserstein/gradient_penalty/index.html | 1 - docs/zh/gan/wasserstein/gradient_penalty/readme.html | 1 - docs/zh/gan/wasserstein/index.html | 1 - docs/zh/gan/wasserstein/readme.html | 1 - docs/zh/graphs/gat/experiment.html | 1 - docs/zh/graphs/gat/index.html | 1 - docs/zh/graphs/gat/readme.html | 1 - docs/zh/graphs/gatv2/experiment.html | 1 - docs/zh/graphs/gatv2/index.html | 1 - docs/zh/graphs/gatv2/readme.html | 1 - docs/zh/graphs/index.html | 1 - docs/zh/hypernetworks/experiment.html | 1 - docs/zh/hypernetworks/hyper_lstm.html | 1 - docs/zh/hypernetworks/index.html | 1 - docs/zh/index.html | 1 - docs/zh/lstm/index.html | 1 - docs/zh/neox/checkpoint.html | 1 - docs/zh/neox/evaluation/half_precision.html | 1 - docs/zh/neox/evaluation/index.html | 1 - docs/zh/neox/evaluation/llm_int8.html | 1 - docs/zh/neox/index.html | 1 - docs/zh/neox/model.html | 1 - docs/zh/neox/readme.html | 1 - docs/zh/neox/samples/finetune.html | 1 - docs/zh/neox/samples/generate.html | 1 - docs/zh/neox/samples/index.html | 1 - docs/zh/neox/samples/llm_int8.html | 1 - docs/zh/neox/tokenizer.html | 1 - docs/zh/neox/utils/cache.html | 1 - docs/zh/neox/utils/finetune.html | 1 - docs/zh/neox/utils/index.html | 1 - docs/zh/neox/utils/llm_int8.html | 1 - docs/zh/neox/utils/text_dataset.html | 1 - docs/zh/neox/utils/trainer.html | 1 - docs/zh/normalization/batch_channel_norm/index.html | 1 - docs/zh/normalization/batch_norm/cifar10.html | 1 - docs/zh/normalization/batch_norm/index.html | 1 - docs/zh/normalization/batch_norm/mnist.html | 1 - docs/zh/normalization/batch_norm/readme.html | 1 - docs/zh/normalization/deep_norm/experiment.html | 1 - docs/zh/normalization/deep_norm/index.html | 1 - docs/zh/normalization/group_norm/experiment.html | 1 - docs/zh/normalization/group_norm/index.html | 1 - docs/zh/normalization/group_norm/readme.html | 1 - docs/zh/normalization/index.html | 1 - docs/zh/normalization/instance_norm/experiment.html | 1 - docs/zh/normalization/instance_norm/index.html | 1 - docs/zh/normalization/instance_norm/readme.html | 1 - docs/zh/normalization/layer_norm/index.html | 1 - docs/zh/normalization/layer_norm/readme.html | 1 - docs/zh/normalization/weight_standardization/conv2d.html | 1 - docs/zh/normalization/weight_standardization/experiment.html | 1 - docs/zh/normalization/weight_standardization/index.html | 1 - docs/zh/normalization/weight_standardization/readme.html | 1 - docs/zh/optimizers/ada_belief.html | 1 - docs/zh/optimizers/adam.html | 1 - docs/zh/optimizers/adam_fp16.html | 1 - docs/zh/optimizers/adam_warmup.html | 1 - docs/zh/optimizers/adam_warmup_cosine_decay.html | 1 - docs/zh/optimizers/amsgrad.html | 1 - docs/zh/optimizers/configs.html | 1 - docs/zh/optimizers/index.html | 1 - docs/zh/optimizers/mnist_experiment.html | 1 - docs/zh/optimizers/noam.html | 1 - docs/zh/optimizers/performance_test.html | 1 - docs/zh/optimizers/radam.html | 1 - docs/zh/optimizers/readme.html | 1 - docs/zh/optimizers/sophia.html | 1 - docs/zh/recurrent_highway_networks/index.html | 1 - docs/zh/resnet/experiment.html | 1 - docs/zh/resnet/index.html | 1 - docs/zh/resnet/readme.html | 1 - docs/zh/rl/dqn/experiment.html | 1 - docs/zh/rl/dqn/index.html | 1 - docs/zh/rl/dqn/model.html | 1 - docs/zh/rl/dqn/readme.html | 1 - docs/zh/rl/dqn/replay_buffer.html | 1 - docs/zh/rl/game.html | 1 - docs/zh/rl/index.html | 1 - docs/zh/rl/ppo/experiment.html | 1 - docs/zh/rl/ppo/gae.html | 1 - docs/zh/rl/ppo/index.html | 1 - docs/zh/rl/ppo/readme.html | 1 - docs/zh/sampling/experiment.html | 1 - docs/zh/sampling/experiment_tiny.html | 1 - docs/zh/sampling/greedy.html | 1 - docs/zh/sampling/index.html | 1 - docs/zh/sampling/nucleus.html | 1 - docs/zh/sampling/temperature.html | 1 - docs/zh/sampling/top_k.html | 1 - docs/zh/scaling/index.html | 1 - docs/zh/scaling/zero3/finetune_neox.html | 1 - docs/zh/scaling/zero3/index.html | 1 - docs/zh/sitemap.xml | 4 ++-- docs/zh/sketch_rnn/index.html | 1 - docs/zh/transformers/aft/experiment.html | 1 - docs/zh/transformers/aft/index.html | 1 - docs/zh/transformers/aft/readme.html | 1 - docs/zh/transformers/alibi/experiment.html | 1 - docs/zh/transformers/alibi/index.html | 1 - docs/zh/transformers/basic/autoregressive_experiment.html | 1 - docs/zh/transformers/basic/index.html | 1 - docs/zh/transformers/basic/with_sophia.html | 1 - docs/zh/transformers/compressive/experiment.html | 1 - docs/zh/transformers/compressive/index.html | 1 - docs/zh/transformers/compressive/readme.html | 1 - docs/zh/transformers/configs.html | 1 - docs/zh/transformers/fast_weights/experiment.html | 1 - docs/zh/transformers/fast_weights/index.html | 1 - docs/zh/transformers/fast_weights/readme.html | 1 - docs/zh/transformers/fast_weights/token_wise.html | 1 - docs/zh/transformers/feed_forward.html | 1 - docs/zh/transformers/feedback/experiment.html | 1 - docs/zh/transformers/feedback/index.html | 1 - docs/zh/transformers/feedback/readme.html | 1 - docs/zh/transformers/fnet/experiment.html | 1 - docs/zh/transformers/fnet/index.html | 1 - docs/zh/transformers/fnet/readme.html | 1 - docs/zh/transformers/glu_variants/experiment.html | 1 - docs/zh/transformers/glu_variants/index.html | 1 - docs/zh/transformers/glu_variants/simple.html | 1 - docs/zh/transformers/gmlp/experiment.html | 1 - docs/zh/transformers/gmlp/index.html | 1 - docs/zh/transformers/gmlp/readme.html | 1 - docs/zh/transformers/gpt/index.html | 1 - docs/zh/transformers/hour_glass/experiment.html | 1 - docs/zh/transformers/hour_glass/index.html | 1 - docs/zh/transformers/index.html | 1 - docs/zh/transformers/knn/build_index.html | 1 - docs/zh/transformers/knn/eval_knn.html | 1 - docs/zh/transformers/knn/index.html | 1 - docs/zh/transformers/knn/train_model.html | 1 - docs/zh/transformers/label_smoothing_loss.html | 1 - docs/zh/transformers/mha.html | 1 - docs/zh/transformers/mlm/experiment.html | 1 - docs/zh/transformers/mlm/index.html | 1 - docs/zh/transformers/mlm/readme.html | 1 - docs/zh/transformers/mlp_mixer/experiment.html | 1 - docs/zh/transformers/mlp_mixer/index.html | 1 - docs/zh/transformers/mlp_mixer/readme.html | 1 - docs/zh/transformers/models.html | 1 - docs/zh/transformers/positional_encoding.html | 1 - docs/zh/transformers/primer_ez/efficient.html | 1 - docs/zh/transformers/primer_ez/experiment.html | 1 - docs/zh/transformers/primer_ez/index.html | 1 - docs/zh/transformers/primer_ez/readme.html | 1 - docs/zh/transformers/primer_ez/variations.html | 1 - docs/zh/transformers/relative_mha.html | 1 - docs/zh/transformers/retro/bert_embeddings.html | 1 - docs/zh/transformers/retro/database.html | 1 - docs/zh/transformers/retro/dataset.html | 1 - docs/zh/transformers/retro/index.html | 1 - docs/zh/transformers/retro/model.html | 1 - docs/zh/transformers/retro/train.html | 1 - docs/zh/transformers/rope/experiment.html | 1 - docs/zh/transformers/rope/index.html | 1 - docs/zh/transformers/rope/value_pe/arithmetic_experiment.html | 1 - docs/zh/transformers/rope/value_pe/experiment.html | 1 - docs/zh/transformers/rope/value_pe/index.html | 1 - docs/zh/transformers/switch/experiment.html | 1 - docs/zh/transformers/switch/index.html | 1 - docs/zh/transformers/switch/readme.html | 1 - docs/zh/transformers/utils.html | 1 - docs/zh/transformers/vit/experiment.html | 1 - docs/zh/transformers/vit/index.html | 1 - docs/zh/transformers/vit/readme.html | 1 - docs/zh/transformers/xl/experiment.html | 1 - docs/zh/transformers/xl/index.html | 1 - docs/zh/transformers/xl/readme.html | 1 - docs/zh/transformers/xl/relative_mha.html | 1 - docs/zh/uncertainty/evidence/experiment.html | 1 - docs/zh/uncertainty/evidence/index.html | 1 - docs/zh/uncertainty/evidence/readme.html | 1 - docs/zh/uncertainty/index.html | 1 - docs/zh/uncertainty/readme.html | 1 - docs/zh/unet/carvana.html | 1 - docs/zh/unet/experiment.html | 1 - docs/zh/unet/index.html | 1 - docs/zh/utils/index.html | 1 - docs/zh/utils/tokenizer.html | 1 - 496 files changed, 4 insertions(+), 498 deletions(-) diff --git a/docs/RWKV/configs.html b/docs/RWKV/configs.html index 909ebb18..3780bb86 100644 --- a/docs/RWKV/configs.html +++ b/docs/RWKV/configs.html @@ -162,7 +162,6 @@ diff --git a/docs/RWKV/experiment.html b/docs/RWKV/experiment.html index b431f2ff..71698823 100644 --- a/docs/RWKV/experiment.html +++ b/docs/RWKV/experiment.html @@ -576,7 +576,6 @@ diff --git a/docs/RWKV/index.html b/docs/RWKV/index.html index bf808f4f..cb73300b 100644 --- a/docs/RWKV/index.html +++ b/docs/RWKV/index.html @@ -788,7 +788,6 @@ diff --git a/docs/activations/fta/experiment.html b/docs/activations/fta/experiment.html index 9a9ea9ba..6cdeb76d 100644 --- a/docs/activations/fta/experiment.html +++ b/docs/activations/fta/experiment.html @@ -792,7 +792,6 @@ diff --git a/docs/activations/fta/index.html b/docs/activations/fta/index.html index a7da4712..c2a8811f 100644 --- a/docs/activations/fta/index.html +++ b/docs/activations/fta/index.html @@ -360,7 +360,6 @@ diff --git a/docs/activations/index.html b/docs/activations/index.html index 58ab3c8a..012359bb 100644 --- a/docs/activations/index.html +++ b/docs/activations/index.html @@ -80,7 +80,6 @@ diff --git a/docs/activations/swish.html b/docs/activations/swish.html index 77cea45f..90182e04 100644 --- a/docs/activations/swish.html +++ b/docs/activations/swish.html @@ -116,7 +116,6 @@ diff --git a/docs/adaptive_computation/index.html b/docs/adaptive_computation/index.html index 3af34ab1..151c1170 100644 --- a/docs/adaptive_computation/index.html +++ b/docs/adaptive_computation/index.html @@ -81,7 +81,6 @@ diff --git a/docs/adaptive_computation/parity.html b/docs/adaptive_computation/parity.html index 4d05a580..1619f029 100644 --- a/docs/adaptive_computation/parity.html +++ b/docs/adaptive_computation/parity.html @@ -229,7 +229,6 @@ diff --git a/docs/adaptive_computation/ponder_net/experiment.html b/docs/adaptive_computation/ponder_net/experiment.html index d694e724..17573c42 100644 --- a/docs/adaptive_computation/ponder_net/experiment.html +++ b/docs/adaptive_computation/ponder_net/experiment.html @@ -592,7 +592,6 @@ diff --git a/docs/adaptive_computation/ponder_net/index.html b/docs/adaptive_computation/ponder_net/index.html index b7113137..403c2f9d 100644 --- a/docs/adaptive_computation/ponder_net/index.html +++ b/docs/adaptive_computation/ponder_net/index.html @@ -757,7 +757,6 @@ s is odd and false otherwise.

diff --git a/docs/adaptive_computation/ponder_net/readme.html b/docs/adaptive_computation/ponder_net/readme.html index cdab71bc..6301f826 100644 --- a/docs/adaptive_computation/ponder_net/readme.html +++ b/docs/adaptive_computation/ponder_net/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/adaptive_computation/readme.html b/docs/adaptive_computation/readme.html index f3d45034..a9ea6579 100644 --- a/docs/adaptive_computation/readme.html +++ b/docs/adaptive_computation/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/capsule_networks/index.html b/docs/capsule_networks/index.html index 4a9e1a6e..3b69b85c 100644 --- a/docs/capsule_networks/index.html +++ b/docs/capsule_networks/index.html @@ -442,7 +442,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/capsule_networks/mnist.html b/docs/capsule_networks/mnist.html index dfe15fe3..69db16af 100644 --- a/docs/capsule_networks/mnist.html +++ b/docs/capsule_networks/mnist.html @@ -552,7 +552,6 @@ diff --git a/docs/capsule_networks/readme.html b/docs/capsule_networks/readme.html index 6ef199cf..42db2cc9 100644 --- a/docs/capsule_networks/readme.html +++ b/docs/capsule_networks/readme.html @@ -85,7 +85,6 @@ diff --git a/docs/cfr/analytics.html b/docs/cfr/analytics.html index 6eb04c27..03be2b75 100644 --- a/docs/cfr/analytics.html +++ b/docs/cfr/analytics.html @@ -158,7 +158,6 @@ diff --git a/docs/cfr/index.html b/docs/cfr/index.html index 4934a695..94326a5a 100644 --- a/docs/cfr/index.html +++ b/docs/cfr/index.html @@ -1365,7 +1365,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/cfr/infoset_saver.html b/docs/cfr/infoset_saver.html index 89875b29..0c459a05 100644 --- a/docs/cfr/infoset_saver.html +++ b/docs/cfr/infoset_saver.html @@ -139,7 +139,6 @@ diff --git a/docs/cfr/kuhn/index.html b/docs/cfr/kuhn/index.html index a3d6f350..e92d199f 100644 --- a/docs/cfr/kuhn/index.html +++ b/docs/cfr/kuhn/index.html @@ -827,7 +827,6 @@ diff --git a/docs/conv_mixer/experiment.html b/docs/conv_mixer/experiment.html index 5b5f243e..a44b392e 100644 --- a/docs/conv_mixer/experiment.html +++ b/docs/conv_mixer/experiment.html @@ -330,7 +330,6 @@ diff --git a/docs/conv_mixer/index.html b/docs/conv_mixer/index.html index 0585aef8..648fa5c4 100644 --- a/docs/conv_mixer/index.html +++ b/docs/conv_mixer/index.html @@ -678,7 +678,6 @@ diff --git a/docs/conv_mixer/readme.html b/docs/conv_mixer/readme.html index 1a59a128..ef9708e3 100644 --- a/docs/conv_mixer/readme.html +++ b/docs/conv_mixer/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/diffusion/ddpm/evaluate.html b/docs/diffusion/ddpm/evaluate.html index 70cdfd6d..1f221499 100644 --- a/docs/diffusion/ddpm/evaluate.html +++ b/docs/diffusion/ddpm/evaluate.html @@ -1347,7 +1347,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/ddpm/experiment.html b/docs/diffusion/ddpm/experiment.html index bc99adcb..f0f21fb0 100644 --- a/docs/diffusion/ddpm/experiment.html +++ b/docs/diffusion/ddpm/experiment.html @@ -943,7 +943,6 @@ diff --git a/docs/diffusion/ddpm/index.html b/docs/diffusion/ddpm/index.html index 636db783..f9957496 100644 --- a/docs/diffusion/ddpm/index.html +++ b/docs/diffusion/ddpm/index.html @@ -838,7 +838,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/ddpm/readme.html b/docs/diffusion/ddpm/readme.html index 5a9c1a02..221968ea 100644 --- a/docs/diffusion/ddpm/readme.html +++ b/docs/diffusion/ddpm/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/diffusion/ddpm/unet.html b/docs/diffusion/ddpm/unet.html index bd925fd1..a2a27290 100644 --- a/docs/diffusion/ddpm/unet.html +++ b/docs/diffusion/ddpm/unet.html @@ -1406,7 +1406,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/ddpm/utils.html b/docs/diffusion/ddpm/utils.html index be148a15..b53f60dc 100644 --- a/docs/diffusion/ddpm/utils.html +++ b/docs/diffusion/ddpm/utils.html @@ -103,7 +103,6 @@ diff --git a/docs/diffusion/index.html b/docs/diffusion/index.html index ccd0995b..cd46de02 100644 --- a/docs/diffusion/index.html +++ b/docs/diffusion/index.html @@ -82,7 +82,6 @@ diff --git a/docs/diffusion/stable_diffusion/index.html b/docs/diffusion/stable_diffusion/index.html index 26294f56..d7d44a9a 100644 --- a/docs/diffusion/stable_diffusion/index.html +++ b/docs/diffusion/stable_diffusion/index.html @@ -101,7 +101,6 @@ diff --git a/docs/diffusion/stable_diffusion/latent_diffusion.html b/docs/diffusion/stable_diffusion/latent_diffusion.html index ddc69cc8..c58a4c37 100644 --- a/docs/diffusion/stable_diffusion/latent_diffusion.html +++ b/docs/diffusion/stable_diffusion/latent_diffusion.html @@ -406,7 +406,6 @@ diff --git a/docs/diffusion/stable_diffusion/model/autoencoder.html b/docs/diffusion/stable_diffusion/model/autoencoder.html index a35c80d7..a4522152 100644 --- a/docs/diffusion/stable_diffusion/model/autoencoder.html +++ b/docs/diffusion/stable_diffusion/model/autoencoder.html @@ -1547,7 +1547,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/stable_diffusion/model/clip_embedder.html b/docs/diffusion/stable_diffusion/model/clip_embedder.html index 14fb4720..8d9744b1 100644 --- a/docs/diffusion/stable_diffusion/model/clip_embedder.html +++ b/docs/diffusion/stable_diffusion/model/clip_embedder.html @@ -201,7 +201,6 @@ diff --git a/docs/diffusion/stable_diffusion/model/index.html b/docs/diffusion/stable_diffusion/model/index.html index ee087f71..520e87a0 100644 --- a/docs/diffusion/stable_diffusion/model/index.html +++ b/docs/diffusion/stable_diffusion/model/index.html @@ -83,7 +83,6 @@ diff --git a/docs/diffusion/stable_diffusion/model/unet.html b/docs/diffusion/stable_diffusion/model/unet.html index ef446630..38a44695 100644 --- a/docs/diffusion/stable_diffusion/model/unet.html +++ b/docs/diffusion/stable_diffusion/model/unet.html @@ -1080,7 +1080,6 @@ diff --git a/docs/diffusion/stable_diffusion/model/unet_attention.html b/docs/diffusion/stable_diffusion/model/unet_attention.html index 75bfb746..ae27a51e 100644 --- a/docs/diffusion/stable_diffusion/model/unet_attention.html +++ b/docs/diffusion/stable_diffusion/model/unet_attention.html @@ -1101,7 +1101,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/stable_diffusion/sampler/ddim.html b/docs/diffusion/stable_diffusion/sampler/ddim.html index 5854479c..91cf2921 100644 --- a/docs/diffusion/stable_diffusion/sampler/ddim.html +++ b/docs/diffusion/stable_diffusion/sampler/ddim.html @@ -1030,7 +1030,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/stable_diffusion/sampler/ddpm.html b/docs/diffusion/stable_diffusion/sampler/ddpm.html index 3ffeb419..90e785ad 100644 --- a/docs/diffusion/stable_diffusion/sampler/ddpm.html +++ b/docs/diffusion/stable_diffusion/sampler/ddpm.html @@ -894,7 +894,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/diffusion/stable_diffusion/sampler/index.html b/docs/diffusion/stable_diffusion/sampler/index.html index 161cb511..0861124b 100644 --- a/docs/diffusion/stable_diffusion/sampler/index.html +++ b/docs/diffusion/stable_diffusion/sampler/index.html @@ -380,7 +380,6 @@ diff --git a/docs/diffusion/stable_diffusion/scripts/image_to_image.html b/docs/diffusion/stable_diffusion/scripts/image_to_image.html index 5eb66bf8..014a3b33 100644 --- a/docs/diffusion/stable_diffusion/scripts/image_to_image.html +++ b/docs/diffusion/stable_diffusion/scripts/image_to_image.html @@ -426,7 +426,6 @@ diff --git a/docs/diffusion/stable_diffusion/scripts/in_paint.html b/docs/diffusion/stable_diffusion/scripts/in_paint.html index 3e0538b6..02fff25d 100644 --- a/docs/diffusion/stable_diffusion/scripts/in_paint.html +++ b/docs/diffusion/stable_diffusion/scripts/in_paint.html @@ -473,7 +473,6 @@ diff --git a/docs/diffusion/stable_diffusion/scripts/index.html b/docs/diffusion/stable_diffusion/scripts/index.html index bcdc4877..11ed8ee6 100644 --- a/docs/diffusion/stable_diffusion/scripts/index.html +++ b/docs/diffusion/stable_diffusion/scripts/index.html @@ -83,7 +83,6 @@ diff --git a/docs/diffusion/stable_diffusion/scripts/text_to_image.html b/docs/diffusion/stable_diffusion/scripts/text_to_image.html index 96c74b10..c6717fc5 100644 --- a/docs/diffusion/stable_diffusion/scripts/text_to_image.html +++ b/docs/diffusion/stable_diffusion/scripts/text_to_image.html @@ -435,7 +435,6 @@ diff --git a/docs/diffusion/stable_diffusion/util.html b/docs/diffusion/stable_diffusion/util.html index 5750be5f..6555e9a6 100644 --- a/docs/diffusion/stable_diffusion/util.html +++ b/docs/diffusion/stable_diffusion/util.html @@ -431,7 +431,6 @@ diff --git a/docs/distillation/index.html b/docs/distillation/index.html index 1b3ad087..e0548b09 100644 --- a/docs/distillation/index.html +++ b/docs/distillation/index.html @@ -732,7 +732,6 @@ diff --git a/docs/distillation/large.html b/docs/distillation/large.html index f7eaa994..67aee5c1 100644 --- a/docs/distillation/large.html +++ b/docs/distillation/large.html @@ -343,7 +343,6 @@ diff --git a/docs/distillation/readme.html b/docs/distillation/readme.html index 69562e09..25ac67c7 100644 --- a/docs/distillation/readme.html +++ b/docs/distillation/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/distillation/small.html b/docs/distillation/small.html index 1c09d03a..afcfb22a 100644 --- a/docs/distillation/small.html +++ b/docs/distillation/small.html @@ -329,7 +329,6 @@ diff --git a/docs/experiments/arithmetic_dataset.html b/docs/experiments/arithmetic_dataset.html index 93b2904c..fba0b4d5 100644 --- a/docs/experiments/arithmetic_dataset.html +++ b/docs/experiments/arithmetic_dataset.html @@ -855,7 +855,6 @@ diff --git a/docs/experiments/cifar10.html b/docs/experiments/cifar10.html index 77a6734f..ba327664 100644 --- a/docs/experiments/cifar10.html +++ b/docs/experiments/cifar10.html @@ -396,7 +396,6 @@ diff --git a/docs/experiments/index.html b/docs/experiments/index.html index 1b8214cc..72d344c3 100644 --- a/docs/experiments/index.html +++ b/docs/experiments/index.html @@ -66,7 +66,6 @@ diff --git a/docs/experiments/mnist.html b/docs/experiments/mnist.html index f7f96e60..7e865bff 100644 --- a/docs/experiments/mnist.html +++ b/docs/experiments/mnist.html @@ -433,7 +433,6 @@ diff --git a/docs/experiments/nlp_autoregression.html b/docs/experiments/nlp_autoregression.html index 4156f305..ad88ea9d 100644 --- a/docs/experiments/nlp_autoregression.html +++ b/docs/experiments/nlp_autoregression.html @@ -1080,7 +1080,6 @@ diff --git a/docs/experiments/nlp_classification.html b/docs/experiments/nlp_classification.html index c75db977..4c20f3b5 100644 --- a/docs/experiments/nlp_classification.html +++ b/docs/experiments/nlp_classification.html @@ -1010,7 +1010,6 @@ diff --git a/docs/gan/cycle_gan/index.html b/docs/gan/cycle_gan/index.html index e974cb8b..7c7d9e05 100644 --- a/docs/gan/cycle_gan/index.html +++ b/docs/gan/cycle_gan/index.html @@ -1934,7 +1934,6 @@ diff --git a/docs/gan/cycle_gan/readme.html b/docs/gan/cycle_gan/readme.html index d8422ec4..708f0f8b 100644 --- a/docs/gan/cycle_gan/readme.html +++ b/docs/gan/cycle_gan/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/gan/dcgan/index.html b/docs/gan/dcgan/index.html index 7f3da403..66289400 100644 --- a/docs/gan/dcgan/index.html +++ b/docs/gan/dcgan/index.html @@ -366,7 +366,6 @@ diff --git a/docs/gan/dcgan/readme.html b/docs/gan/dcgan/readme.html index 3258197f..cfbed9b4 100644 --- a/docs/gan/dcgan/readme.html +++ b/docs/gan/dcgan/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/gan/index.html b/docs/gan/index.html index 2df2efc3..f7ed2f57 100644 --- a/docs/gan/index.html +++ b/docs/gan/index.html @@ -84,7 +84,6 @@ diff --git a/docs/gan/original/experiment.html b/docs/gan/original/experiment.html index ff212bd0..460f73c8 100644 --- a/docs/gan/original/experiment.html +++ b/docs/gan/original/experiment.html @@ -599,7 +599,6 @@ diff --git a/docs/gan/original/index.html b/docs/gan/original/index.html index ff0bcee1..25a0347e 100644 --- a/docs/gan/original/index.html +++ b/docs/gan/original/index.html @@ -270,7 +270,6 @@ diff --git a/docs/gan/original/readme.html b/docs/gan/original/readme.html index 86c8efb9..cc823689 100644 --- a/docs/gan/original/readme.html +++ b/docs/gan/original/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/gan/stylegan/experiment.html b/docs/gan/stylegan/experiment.html index 6977d5e9..61a00023 100644 --- a/docs/gan/stylegan/experiment.html +++ b/docs/gan/stylegan/experiment.html @@ -1716,7 +1716,6 @@ diff --git a/docs/gan/stylegan/index.html b/docs/gan/stylegan/index.html index 2cbc8de7..bbaeca0a 100644 --- a/docs/gan/stylegan/index.html +++ b/docs/gan/stylegan/index.html @@ -2746,7 +2746,6 @@ s76,-153,76,-153s77,-151,77,-151c0.7,0.7,35.7,202,105,604c67.3,400.7,102,602.7,1 diff --git a/docs/gan/stylegan/readme.html b/docs/gan/stylegan/readme.html index a6850277..ea5ca4a2 100644 --- a/docs/gan/stylegan/readme.html +++ b/docs/gan/stylegan/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/gan/wasserstein/experiment.html b/docs/gan/wasserstein/experiment.html index 96b5ad02..a2017d96 100644 --- a/docs/gan/wasserstein/experiment.html +++ b/docs/gan/wasserstein/experiment.html @@ -189,7 +189,6 @@ diff --git a/docs/gan/wasserstein/gradient_penalty/experiment.html b/docs/gan/wasserstein/gradient_penalty/experiment.html index 200c9aa4..24d8b019 100644 --- a/docs/gan/wasserstein/gradient_penalty/experiment.html +++ b/docs/gan/wasserstein/gradient_penalty/experiment.html @@ -331,7 +331,6 @@ diff --git a/docs/gan/wasserstein/gradient_penalty/index.html b/docs/gan/wasserstein/gradient_penalty/index.html index 86609f74..9dcf225c 100644 --- a/docs/gan/wasserstein/gradient_penalty/index.html +++ b/docs/gan/wasserstein/gradient_penalty/index.html @@ -187,7 +187,6 @@ diff --git a/docs/gan/wasserstein/gradient_penalty/readme.html b/docs/gan/wasserstein/gradient_penalty/readme.html index 558cb43d..7e82d768 100644 --- a/docs/gan/wasserstein/gradient_penalty/readme.html +++ b/docs/gan/wasserstein/gradient_penalty/readme.html @@ -84,7 +84,6 @@ diff --git a/docs/gan/wasserstein/index.html b/docs/gan/wasserstein/index.html index c6e4e4ee..72bb41c4 100644 --- a/docs/gan/wasserstein/index.html +++ b/docs/gan/wasserstein/index.html @@ -179,7 +179,6 @@ diff --git a/docs/gan/wasserstein/readme.html b/docs/gan/wasserstein/readme.html index 25f8e8d1..dff6bf0d 100644 --- a/docs/gan/wasserstein/readme.html +++ b/docs/gan/wasserstein/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/graphs/gat/experiment.html b/docs/graphs/gat/experiment.html index b4904815..d85373e6 100644 --- a/docs/graphs/gat/experiment.html +++ b/docs/graphs/gat/experiment.html @@ -1218,7 +1218,6 @@ diff --git a/docs/graphs/gat/index.html b/docs/graphs/gat/index.html index 127d5d58..3c59059b 100644 --- a/docs/graphs/gat/index.html +++ b/docs/graphs/gat/index.html @@ -828,7 +828,6 @@ diff --git a/docs/graphs/gat/readme.html b/docs/graphs/gat/readme.html index 4fd9d1db..ac548796 100644 --- a/docs/graphs/gat/readme.html +++ b/docs/graphs/gat/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/graphs/gatv2/experiment.html b/docs/graphs/gatv2/experiment.html index 3f8bbf43..1ac01900 100644 --- a/docs/graphs/gatv2/experiment.html +++ b/docs/graphs/gatv2/experiment.html @@ -424,7 +424,6 @@ diff --git a/docs/graphs/gatv2/index.html b/docs/graphs/gatv2/index.html index 44903004..27463cda 100644 --- a/docs/graphs/gatv2/index.html +++ b/docs/graphs/gatv2/index.html @@ -923,7 +923,6 @@ diff --git a/docs/graphs/gatv2/readme.html b/docs/graphs/gatv2/readme.html index ccbe7ed6..11bfc144 100644 --- a/docs/graphs/gatv2/readme.html +++ b/docs/graphs/gatv2/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/graphs/index.html b/docs/graphs/index.html index 27d558b0..598119b7 100644 --- a/docs/graphs/index.html +++ b/docs/graphs/index.html @@ -80,7 +80,6 @@ diff --git a/docs/hypernetworks/experiment.html b/docs/hypernetworks/experiment.html index f2450264..25740207 100644 --- a/docs/hypernetworks/experiment.html +++ b/docs/hypernetworks/experiment.html @@ -340,7 +340,6 @@ diff --git a/docs/hypernetworks/hyper_lstm.html b/docs/hypernetworks/hyper_lstm.html index 654f2ace..ffcf227b 100644 --- a/docs/hypernetworks/hyper_lstm.html +++ b/docs/hypernetworks/hyper_lstm.html @@ -669,7 +669,6 @@ diff --git a/docs/hypernetworks/index.html b/docs/hypernetworks/index.html index 543084ac..9511cb0a 100644 --- a/docs/hypernetworks/index.html +++ b/docs/hypernetworks/index.html @@ -78,7 +78,6 @@ diff --git a/docs/index.html b/docs/index.html index 7923129a..ec24f58a 100644 --- a/docs/index.html +++ b/docs/index.html @@ -173,7 +173,6 @@ diff --git a/docs/lstm/index.html b/docs/lstm/index.html index ef5060c4..042b66af 100644 --- a/docs/lstm/index.html +++ b/docs/lstm/index.html @@ -453,7 +453,6 @@ diff --git a/docs/neox/checkpoint.html b/docs/neox/checkpoint.html index eacc25a7..4bf7c62b 100644 --- a/docs/neox/checkpoint.html +++ b/docs/neox/checkpoint.html @@ -466,7 +466,6 @@ diff --git a/docs/neox/evaluation/half_precision.html b/docs/neox/evaluation/half_precision.html index d8799140..3e4b0d45 100644 --- a/docs/neox/evaluation/half_precision.html +++ b/docs/neox/evaluation/half_precision.html @@ -180,7 +180,6 @@ diff --git a/docs/neox/evaluation/index.html b/docs/neox/evaluation/index.html index d8f3c9ce..496054d2 100644 --- a/docs/neox/evaluation/index.html +++ b/docs/neox/evaluation/index.html @@ -902,7 +902,6 @@ diff --git a/docs/neox/evaluation/llm_int8.html b/docs/neox/evaluation/llm_int8.html index 27629d4d..70b2f105 100644 --- a/docs/neox/evaluation/llm_int8.html +++ b/docs/neox/evaluation/llm_int8.html @@ -191,7 +191,6 @@ diff --git a/docs/neox/index.html b/docs/neox/index.html index 2290da46..918b582e 100644 --- a/docs/neox/index.html +++ b/docs/neox/index.html @@ -92,7 +92,6 @@ diff --git a/docs/neox/model.html b/docs/neox/model.html index 89a4dc2f..b1efd3be 100644 --- a/docs/neox/model.html +++ b/docs/neox/model.html @@ -2110,7 +2110,6 @@ diff --git a/docs/neox/readme.html b/docs/neox/readme.html index c02791d2..8b7a8769 100644 --- a/docs/neox/readme.html +++ b/docs/neox/readme.html @@ -77,7 +77,6 @@ diff --git a/docs/neox/samples/finetune.html b/docs/neox/samples/finetune.html index 3f543bde..b3c84121 100644 --- a/docs/neox/samples/finetune.html +++ b/docs/neox/samples/finetune.html @@ -396,7 +396,6 @@ diff --git a/docs/neox/samples/generate.html b/docs/neox/samples/generate.html index 76ccbb58..5ac68ff8 100644 --- a/docs/neox/samples/generate.html +++ b/docs/neox/samples/generate.html @@ -358,7 +358,6 @@ diff --git a/docs/neox/samples/index.html b/docs/neox/samples/index.html index 6f0448fe..f59f3bda 100644 --- a/docs/neox/samples/index.html +++ b/docs/neox/samples/index.html @@ -81,7 +81,6 @@ diff --git a/docs/neox/samples/llm_int8.html b/docs/neox/samples/llm_int8.html index 5091bc26..1557169f 100644 --- a/docs/neox/samples/llm_int8.html +++ b/docs/neox/samples/llm_int8.html @@ -300,7 +300,6 @@ diff --git a/docs/neox/tokenizer.html b/docs/neox/tokenizer.html index 2211eed1..9fc1e374 100644 --- a/docs/neox/tokenizer.html +++ b/docs/neox/tokenizer.html @@ -109,7 +109,6 @@ diff --git a/docs/neox/utils/cache.html b/docs/neox/utils/cache.html index 3f267be6..6987e518 100644 --- a/docs/neox/utils/cache.html +++ b/docs/neox/utils/cache.html @@ -348,7 +348,6 @@ diff --git a/docs/neox/utils/finetune.html b/docs/neox/utils/finetune.html index 3d7a54fe..55498717 100644 --- a/docs/neox/utils/finetune.html +++ b/docs/neox/utils/finetune.html @@ -245,7 +245,6 @@ diff --git a/docs/neox/utils/index.html b/docs/neox/utils/index.html index 65e1949c..82d191e7 100644 --- a/docs/neox/utils/index.html +++ b/docs/neox/utils/index.html @@ -339,7 +339,6 @@ diff --git a/docs/neox/utils/llm_int8.html b/docs/neox/utils/llm_int8.html index b4779d2e..86ff77b4 100644 --- a/docs/neox/utils/llm_int8.html +++ b/docs/neox/utils/llm_int8.html @@ -195,7 +195,6 @@ diff --git a/docs/neox/utils/text_dataset.html b/docs/neox/utils/text_dataset.html index c0866957..89ed3856 100644 --- a/docs/neox/utils/text_dataset.html +++ b/docs/neox/utils/text_dataset.html @@ -395,7 +395,6 @@ diff --git a/docs/neox/utils/trainer.html b/docs/neox/utils/trainer.html index b0461d9f..d12b14f7 100644 --- a/docs/neox/utils/trainer.html +++ b/docs/neox/utils/trainer.html @@ -489,7 +489,6 @@ diff --git a/docs/normalization/batch_channel_norm/index.html b/docs/normalization/batch_channel_norm/index.html index f63b85db..ad09b3c6 100644 --- a/docs/normalization/batch_channel_norm/index.html +++ b/docs/normalization/batch_channel_norm/index.html @@ -671,7 +671,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/batch_norm/cifar10.html b/docs/normalization/batch_norm/cifar10.html index cd247659..ab499f61 100644 --- a/docs/normalization/batch_norm/cifar10.html +++ b/docs/normalization/batch_norm/cifar10.html @@ -226,7 +226,6 @@ diff --git a/docs/normalization/batch_norm/index.html b/docs/normalization/batch_norm/index.html index 02982955..15a20aa3 100644 --- a/docs/normalization/batch_norm/index.html +++ b/docs/normalization/batch_norm/index.html @@ -469,7 +469,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/batch_norm/mnist.html b/docs/normalization/batch_norm/mnist.html index 0eca28ae..1064931a 100644 --- a/docs/normalization/batch_norm/mnist.html +++ b/docs/normalization/batch_norm/mnist.html @@ -318,7 +318,6 @@ diff --git a/docs/normalization/batch_norm/readme.html b/docs/normalization/batch_norm/readme.html index a83557b2..1f838e75 100644 --- a/docs/normalization/batch_norm/readme.html +++ b/docs/normalization/batch_norm/readme.html @@ -110,7 +110,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/deep_norm/experiment.html b/docs/normalization/deep_norm/experiment.html index c5c58680..d3263c13 100644 --- a/docs/normalization/deep_norm/experiment.html +++ b/docs/normalization/deep_norm/experiment.html @@ -623,7 +623,6 @@ diff --git a/docs/normalization/deep_norm/index.html b/docs/normalization/deep_norm/index.html index 85680d6f..dbb2b9d1 100644 --- a/docs/normalization/deep_norm/index.html +++ b/docs/normalization/deep_norm/index.html @@ -391,7 +391,6 @@ diff --git a/docs/normalization/group_norm/experiment.html b/docs/normalization/group_norm/experiment.html index 7bb3018f..d4b7a025 100644 --- a/docs/normalization/group_norm/experiment.html +++ b/docs/normalization/group_norm/experiment.html @@ -250,7 +250,6 @@ diff --git a/docs/normalization/group_norm/index.html b/docs/normalization/group_norm/index.html index 0b08b7d1..a382ba0f 100644 --- a/docs/normalization/group_norm/index.html +++ b/docs/normalization/group_norm/index.html @@ -379,7 +379,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/group_norm/readme.html b/docs/normalization/group_norm/readme.html index e27f4239..434c35d4 100644 --- a/docs/normalization/group_norm/readme.html +++ b/docs/normalization/group_norm/readme.html @@ -84,7 +84,6 @@ diff --git a/docs/normalization/index.html b/docs/normalization/index.html index 980f4a8a..f013cb67 100644 --- a/docs/normalization/index.html +++ b/docs/normalization/index.html @@ -85,7 +85,6 @@ diff --git a/docs/normalization/instance_norm/experiment.html b/docs/normalization/instance_norm/experiment.html index 2595c990..619075bb 100644 --- a/docs/normalization/instance_norm/experiment.html +++ b/docs/normalization/instance_norm/experiment.html @@ -226,7 +226,6 @@ diff --git a/docs/normalization/instance_norm/index.html b/docs/normalization/instance_norm/index.html index 4ca500dc..df0872fc 100644 --- a/docs/normalization/instance_norm/index.html +++ b/docs/normalization/instance_norm/index.html @@ -362,7 +362,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/instance_norm/readme.html b/docs/normalization/instance_norm/readme.html index 4a31f34b..aefe6f8c 100644 --- a/docs/normalization/instance_norm/readme.html +++ b/docs/normalization/instance_norm/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/normalization/layer_norm/index.html b/docs/normalization/layer_norm/index.html index 320ffdc4..40f700f0 100644 --- a/docs/normalization/layer_norm/index.html +++ b/docs/normalization/layer_norm/index.html @@ -392,7 +392,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/normalization/layer_norm/readme.html b/docs/normalization/layer_norm/readme.html index b0df4d39..279b261f 100644 --- a/docs/normalization/layer_norm/readme.html +++ b/docs/normalization/layer_norm/readme.html @@ -89,7 +89,6 @@ diff --git a/docs/normalization/weight_standardization/conv2d.html b/docs/normalization/weight_standardization/conv2d.html index e6aab6e3..4e4f70ab 100644 --- a/docs/normalization/weight_standardization/conv2d.html +++ b/docs/normalization/weight_standardization/conv2d.html @@ -167,7 +167,6 @@ diff --git a/docs/normalization/weight_standardization/experiment.html b/docs/normalization/weight_standardization/experiment.html index bb36381f..9629ef83 100644 --- a/docs/normalization/weight_standardization/experiment.html +++ b/docs/normalization/weight_standardization/experiment.html @@ -227,7 +227,6 @@ diff --git a/docs/normalization/weight_standardization/index.html b/docs/normalization/weight_standardization/index.html index 51ba96d7..17eeb2ff 100644 --- a/docs/normalization/weight_standardization/index.html +++ b/docs/normalization/weight_standardization/index.html @@ -168,7 +168,6 @@ c-4-3.333-8.333-7.667-13 -13l-13-13l77-155 77-156c66 199.333 139 419.667 diff --git a/docs/normalization/weight_standardization/readme.html b/docs/normalization/weight_standardization/readme.html index caa7513f..52ec5b48 100644 --- a/docs/normalization/weight_standardization/readme.html +++ b/docs/normalization/weight_standardization/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/optimizers/ada_belief.html b/docs/optimizers/ada_belief.html index 50b53954..584214a7 100644 --- a/docs/optimizers/ada_belief.html +++ b/docs/optimizers/ada_belief.html @@ -459,7 +459,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/optimizers/adam.html b/docs/optimizers/adam.html index b335debb..c96503b2 100644 --- a/docs/optimizers/adam.html +++ b/docs/optimizers/adam.html @@ -699,7 +699,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/optimizers/adam_fp16.html b/docs/optimizers/adam_fp16.html index 3f6be6a0..96871c9b 100644 --- a/docs/optimizers/adam_fp16.html +++ b/docs/optimizers/adam_fp16.html @@ -454,7 +454,6 @@ diff --git a/docs/optimizers/adam_warmup.html b/docs/optimizers/adam_warmup.html index 89843647..592b777a 100644 --- a/docs/optimizers/adam_warmup.html +++ b/docs/optimizers/adam_warmup.html @@ -195,7 +195,6 @@ diff --git a/docs/optimizers/adam_warmup_cosine_decay.html b/docs/optimizers/adam_warmup_cosine_decay.html index f0ff8a1c..82439dc5 100644 --- a/docs/optimizers/adam_warmup_cosine_decay.html +++ b/docs/optimizers/adam_warmup_cosine_decay.html @@ -246,7 +246,6 @@ diff --git a/docs/optimizers/amsgrad.html b/docs/optimizers/amsgrad.html index 17ede6e3..d9e57bda 100644 --- a/docs/optimizers/amsgrad.html +++ b/docs/optimizers/amsgrad.html @@ -515,7 +515,6 @@ diff --git a/docs/optimizers/configs.html b/docs/optimizers/configs.html index 2c30059c..9cbb46b0 100644 --- a/docs/optimizers/configs.html +++ b/docs/optimizers/configs.html @@ -405,7 +405,6 @@ diff --git a/docs/optimizers/index.html b/docs/optimizers/index.html index 48a9fe83..574f92f6 100644 --- a/docs/optimizers/index.html +++ b/docs/optimizers/index.html @@ -536,7 +536,6 @@ diff --git a/docs/optimizers/mnist_experiment.html b/docs/optimizers/mnist_experiment.html index d7bb8de4..403bc1e9 100644 --- a/docs/optimizers/mnist_experiment.html +++ b/docs/optimizers/mnist_experiment.html @@ -412,7 +412,6 @@ diff --git a/docs/optimizers/noam.html b/docs/optimizers/noam.html index 8c08ae88..3002bb95 100644 --- a/docs/optimizers/noam.html +++ b/docs/optimizers/noam.html @@ -280,7 +280,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/optimizers/performance_test.html b/docs/optimizers/performance_test.html index d3ef94bc..5884e109 100644 --- a/docs/optimizers/performance_test.html +++ b/docs/optimizers/performance_test.html @@ -127,7 +127,6 @@ MyAdam...[DONE] 1,192.89ms diff --git a/docs/optimizers/radam.html b/docs/optimizers/radam.html index e6bece4d..6fb7158f 100644 --- a/docs/optimizers/radam.html +++ b/docs/optimizers/radam.html @@ -734,7 +734,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/optimizers/readme.html b/docs/optimizers/readme.html index 71428f23..0e5d7fb9 100644 --- a/docs/optimizers/readme.html +++ b/docs/optimizers/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/optimizers/sophia.html b/docs/optimizers/sophia.html index 181120ac..2e37d8b6 100644 --- a/docs/optimizers/sophia.html +++ b/docs/optimizers/sophia.html @@ -453,7 +453,6 @@ diff --git a/docs/recurrent_highway_networks/index.html b/docs/recurrent_highway_networks/index.html index 5b26a512..f252f9b3 100644 --- a/docs/recurrent_highway_networks/index.html +++ b/docs/recurrent_highway_networks/index.html @@ -449,7 +449,6 @@ diff --git a/docs/resnet/experiment.html b/docs/resnet/experiment.html index 29a2e21a..a3843e16 100644 --- a/docs/resnet/experiment.html +++ b/docs/resnet/experiment.html @@ -305,7 +305,6 @@ diff --git a/docs/resnet/index.html b/docs/resnet/index.html index d3fca20d..bb40d3c1 100644 --- a/docs/resnet/index.html +++ b/docs/resnet/index.html @@ -999,7 +999,6 @@ diff --git a/docs/resnet/readme.html b/docs/resnet/readme.html index 1553499d..6b3c2ce9 100644 --- a/docs/resnet/readme.html +++ b/docs/resnet/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/rl/dqn/experiment.html b/docs/rl/dqn/experiment.html index d6ba5c0e..20b91df1 100644 --- a/docs/rl/dqn/experiment.html +++ b/docs/rl/dqn/experiment.html @@ -1128,7 +1128,6 @@ diff --git a/docs/rl/dqn/index.html b/docs/rl/dqn/index.html index ca8ea82b..f2b69060 100644 --- a/docs/rl/dqn/index.html +++ b/docs/rl/dqn/index.html @@ -253,7 +253,6 @@ diff --git a/docs/rl/dqn/model.html b/docs/rl/dqn/model.html index 9e959f41..4adf68ea 100644 --- a/docs/rl/dqn/model.html +++ b/docs/rl/dqn/model.html @@ -292,7 +292,6 @@ diff --git a/docs/rl/dqn/readme.html b/docs/rl/dqn/readme.html index b85c501b..a82c8333 100644 --- a/docs/rl/dqn/readme.html +++ b/docs/rl/dqn/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/rl/dqn/replay_buffer.html b/docs/rl/dqn/replay_buffer.html index 777ba2ea..31c7130e 100644 --- a/docs/rl/dqn/replay_buffer.html +++ b/docs/rl/dqn/replay_buffer.html @@ -761,7 +761,6 @@ diff --git a/docs/rl/game.html b/docs/rl/game.html index a76c3b84..3db8932d 100644 --- a/docs/rl/game.html +++ b/docs/rl/game.html @@ -461,7 +461,6 @@ diff --git a/docs/rl/index.html b/docs/rl/index.html index 497ed6c4..71e09538 100644 --- a/docs/rl/index.html +++ b/docs/rl/index.html @@ -87,7 +87,6 @@ diff --git a/docs/rl/ppo/experiment.html b/docs/rl/ppo/experiment.html index b968e9a3..96711b84 100644 --- a/docs/rl/ppo/experiment.html +++ b/docs/rl/ppo/experiment.html @@ -1318,7 +1318,6 @@ diff --git a/docs/rl/ppo/gae.html b/docs/rl/ppo/gae.html index 7c134c47..a4d78c18 100644 --- a/docs/rl/ppo/gae.html +++ b/docs/rl/ppo/gae.html @@ -202,7 +202,6 @@ diff --git a/docs/rl/ppo/index.html b/docs/rl/ppo/index.html index 043ea04c..e4a06901 100644 --- a/docs/rl/ppo/index.html +++ b/docs/rl/ppo/index.html @@ -190,7 +190,6 @@ diff --git a/docs/rl/ppo/readme.html b/docs/rl/ppo/readme.html index 4f1d84d4..a6f2aea4 100644 --- a/docs/rl/ppo/readme.html +++ b/docs/rl/ppo/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/sampling/experiment.html b/docs/sampling/experiment.html index 82e6cda8..92ab5682 100644 --- a/docs/sampling/experiment.html +++ b/docs/sampling/experiment.html @@ -371,7 +371,6 @@ diff --git a/docs/sampling/experiment_tiny.html b/docs/sampling/experiment_tiny.html index 790c3fd2..4bdb024b 100644 --- a/docs/sampling/experiment_tiny.html +++ b/docs/sampling/experiment_tiny.html @@ -250,7 +250,6 @@ diff --git a/docs/sampling/greedy.html b/docs/sampling/greedy.html index 51ced920..04cd86c1 100644 --- a/docs/sampling/greedy.html +++ b/docs/sampling/greedy.html @@ -116,7 +116,6 @@ diff --git a/docs/sampling/index.html b/docs/sampling/index.html index 27cd4534..f1496829 100644 --- a/docs/sampling/index.html +++ b/docs/sampling/index.html @@ -121,7 +121,6 @@ diff --git a/docs/sampling/nucleus.html b/docs/sampling/nucleus.html index 6abb8658..d5388b9b 100644 --- a/docs/sampling/nucleus.html +++ b/docs/sampling/nucleus.html @@ -260,7 +260,6 @@ diff --git a/docs/sampling/temperature.html b/docs/sampling/temperature.html index 2bb4d748..ae7dc602 100644 --- a/docs/sampling/temperature.html +++ b/docs/sampling/temperature.html @@ -157,7 +157,6 @@ diff --git a/docs/sampling/top_k.html b/docs/sampling/top_k.html index 4c095caa..68dbc675 100644 --- a/docs/sampling/top_k.html +++ b/docs/sampling/top_k.html @@ -183,7 +183,6 @@ diff --git a/docs/scaling/index.html b/docs/scaling/index.html index 5241e957..0e355463 100644 --- a/docs/scaling/index.html +++ b/docs/scaling/index.html @@ -79,7 +79,6 @@ diff --git a/docs/scaling/zero3/finetune_neox.html b/docs/scaling/zero3/finetune_neox.html index a6b54545..53dea98d 100644 --- a/docs/scaling/zero3/finetune_neox.html +++ b/docs/scaling/zero3/finetune_neox.html @@ -378,7 +378,6 @@ diff --git a/docs/scaling/zero3/index.html b/docs/scaling/zero3/index.html index 1745e6e3..f288a2fd 100644 --- a/docs/scaling/zero3/index.html +++ b/docs/scaling/zero3/index.html @@ -1803,7 +1803,6 @@ diff --git a/docs/sitemap.xml b/docs/sitemap.xml index dd5beb16..e1d8e169 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -960,7 +960,7 @@ https://nn.labml.ai/transformers/rope/index.html - 2023-12-08T16:30:00+00:00 + 2024-06-20T16:30:00+00:00 1.00 @@ -974,7 +974,7 @@ https://nn.labml.ai/transformers/rope/value_pe/index.html - 2023-10-24T16:30:00+00:00 + 2024-06-20T16:30:00+00:00 1.00 diff --git a/docs/sketch_rnn/index.html b/docs/sketch_rnn/index.html index 42969939..b6576bf6 100644 --- a/docs/sketch_rnn/index.html +++ b/docs/sketch_rnn/index.html @@ -2187,7 +2187,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/aft/experiment.html b/docs/transformers/aft/experiment.html index 1e58c5b2..a8f746a3 100644 --- a/docs/transformers/aft/experiment.html +++ b/docs/transformers/aft/experiment.html @@ -600,7 +600,6 @@ diff --git a/docs/transformers/aft/index.html b/docs/transformers/aft/index.html index da4c882b..70a1bcb4 100644 --- a/docs/transformers/aft/index.html +++ b/docs/transformers/aft/index.html @@ -508,7 +508,6 @@ diff --git a/docs/transformers/aft/readme.html b/docs/transformers/aft/readme.html index 4420dfc9..785932e0 100644 --- a/docs/transformers/aft/readme.html +++ b/docs/transformers/aft/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/transformers/alibi/experiment.html b/docs/transformers/alibi/experiment.html index fb6ed20b..d9feebb2 100644 --- a/docs/transformers/alibi/experiment.html +++ b/docs/transformers/alibi/experiment.html @@ -577,7 +577,6 @@ diff --git a/docs/transformers/alibi/index.html b/docs/transformers/alibi/index.html index 526a750e..e0001ef0 100644 --- a/docs/transformers/alibi/index.html +++ b/docs/transformers/alibi/index.html @@ -593,7 +593,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/basic/autoregressive_experiment.html b/docs/transformers/basic/autoregressive_experiment.html index 0097bdb0..fa96c73a 100644 --- a/docs/transformers/basic/autoregressive_experiment.html +++ b/docs/transformers/basic/autoregressive_experiment.html @@ -574,7 +574,6 @@ diff --git a/docs/transformers/basic/index.html b/docs/transformers/basic/index.html index e181ef19..ea811b71 100644 --- a/docs/transformers/basic/index.html +++ b/docs/transformers/basic/index.html @@ -67,7 +67,6 @@ diff --git a/docs/transformers/basic/with_sophia.html b/docs/transformers/basic/with_sophia.html index c322d527..3d0e6fc2 100644 --- a/docs/transformers/basic/with_sophia.html +++ b/docs/transformers/basic/with_sophia.html @@ -642,7 +642,6 @@ diff --git a/docs/transformers/compressive/experiment.html b/docs/transformers/compressive/experiment.html index f2a5d224..e9e557a5 100644 --- a/docs/transformers/compressive/experiment.html +++ b/docs/transformers/compressive/experiment.html @@ -1389,7 +1389,6 @@ diff --git a/docs/transformers/compressive/index.html b/docs/transformers/compressive/index.html index 7ed4b8c1..9a650bbf 100644 --- a/docs/transformers/compressive/index.html +++ b/docs/transformers/compressive/index.html @@ -988,7 +988,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/compressive/readme.html b/docs/transformers/compressive/readme.html index e1245fd0..d53bae56 100644 --- a/docs/transformers/compressive/readme.html +++ b/docs/transformers/compressive/readme.html @@ -88,7 +88,6 @@ diff --git a/docs/transformers/configs.html b/docs/transformers/configs.html index b291dad6..ae6cea61 100644 --- a/docs/transformers/configs.html +++ b/docs/transformers/configs.html @@ -965,7 +965,6 @@ diff --git a/docs/transformers/fast_weights/experiment.html b/docs/transformers/fast_weights/experiment.html index 3a3113d7..2e37f431 100644 --- a/docs/transformers/fast_weights/experiment.html +++ b/docs/transformers/fast_weights/experiment.html @@ -352,7 +352,6 @@ diff --git a/docs/transformers/fast_weights/index.html b/docs/transformers/fast_weights/index.html index 5296e830..df2f0811 100644 --- a/docs/transformers/fast_weights/index.html +++ b/docs/transformers/fast_weights/index.html @@ -813,7 +813,6 @@ diff --git a/docs/transformers/fast_weights/readme.html b/docs/transformers/fast_weights/readme.html index dc85a195..e324066b 100644 --- a/docs/transformers/fast_weights/readme.html +++ b/docs/transformers/fast_weights/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/transformers/fast_weights/token_wise.html b/docs/transformers/fast_weights/token_wise.html index 442240c2..6816270b 100644 --- a/docs/transformers/fast_weights/token_wise.html +++ b/docs/transformers/fast_weights/token_wise.html @@ -524,7 +524,6 @@ diff --git a/docs/transformers/feed_forward.html b/docs/transformers/feed_forward.html index 0e2f480b..564254a3 100644 --- a/docs/transformers/feed_forward.html +++ b/docs/transformers/feed_forward.html @@ -291,7 +291,6 @@ diff --git a/docs/transformers/feedback/experiment.html b/docs/transformers/feedback/experiment.html index 07faccea..f744d4b5 100644 --- a/docs/transformers/feedback/experiment.html +++ b/docs/transformers/feedback/experiment.html @@ -401,7 +401,6 @@ diff --git a/docs/transformers/feedback/index.html b/docs/transformers/feedback/index.html index b85185ee..6bc6e3f4 100644 --- a/docs/transformers/feedback/index.html +++ b/docs/transformers/feedback/index.html @@ -1802,7 +1802,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/feedback/readme.html b/docs/transformers/feedback/readme.html index d078d9cc..7b68f454 100644 --- a/docs/transformers/feedback/readme.html +++ b/docs/transformers/feedback/readme.html @@ -87,7 +87,6 @@ diff --git a/docs/transformers/fnet/experiment.html b/docs/transformers/fnet/experiment.html index a20ea6a9..681b64f3 100644 --- a/docs/transformers/fnet/experiment.html +++ b/docs/transformers/fnet/experiment.html @@ -511,7 +511,6 @@ diff --git a/docs/transformers/fnet/index.html b/docs/transformers/fnet/index.html index 4f686684..c0427dfc 100644 --- a/docs/transformers/fnet/index.html +++ b/docs/transformers/fnet/index.html @@ -196,7 +196,6 @@ diff --git a/docs/transformers/fnet/readme.html b/docs/transformers/fnet/readme.html index abf3b38b..1447f778 100644 --- a/docs/transformers/fnet/readme.html +++ b/docs/transformers/fnet/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/transformers/glu_variants/experiment.html b/docs/transformers/glu_variants/experiment.html index 8a565919..ab38b4c8 100644 --- a/docs/transformers/glu_variants/experiment.html +++ b/docs/transformers/glu_variants/experiment.html @@ -440,7 +440,6 @@ diff --git a/docs/transformers/glu_variants/index.html b/docs/transformers/glu_variants/index.html index 087a3190..1ad9f8af 100644 --- a/docs/transformers/glu_variants/index.html +++ b/docs/transformers/glu_variants/index.html @@ -82,7 +82,6 @@ diff --git a/docs/transformers/glu_variants/simple.html b/docs/transformers/glu_variants/simple.html index 3f8fcaf3..d98a9d08 100644 --- a/docs/transformers/glu_variants/simple.html +++ b/docs/transformers/glu_variants/simple.html @@ -1153,7 +1153,6 @@ diff --git a/docs/transformers/gmlp/experiment.html b/docs/transformers/gmlp/experiment.html index d0368a5b..ac636933 100644 --- a/docs/transformers/gmlp/experiment.html +++ b/docs/transformers/gmlp/experiment.html @@ -442,7 +442,6 @@ diff --git a/docs/transformers/gmlp/index.html b/docs/transformers/gmlp/index.html index a5c4672f..c67afc75 100644 --- a/docs/transformers/gmlp/index.html +++ b/docs/transformers/gmlp/index.html @@ -523,7 +523,6 @@ diff --git a/docs/transformers/gmlp/readme.html b/docs/transformers/gmlp/readme.html index 16d0ca6d..2f02caef 100644 --- a/docs/transformers/gmlp/readme.html +++ b/docs/transformers/gmlp/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/transformers/gpt/index.html b/docs/transformers/gpt/index.html index 766ec5cc..32b2b300 100644 --- a/docs/transformers/gpt/index.html +++ b/docs/transformers/gpt/index.html @@ -861,7 +861,6 @@ diff --git a/docs/transformers/hour_glass/experiment.html b/docs/transformers/hour_glass/experiment.html index 4834a730..722a608f 100644 --- a/docs/transformers/hour_glass/experiment.html +++ b/docs/transformers/hour_glass/experiment.html @@ -633,7 +633,6 @@ diff --git a/docs/transformers/hour_glass/index.html b/docs/transformers/hour_glass/index.html index 21089ff9..dcadfaad 100644 --- a/docs/transformers/hour_glass/index.html +++ b/docs/transformers/hour_glass/index.html @@ -885,7 +885,6 @@ diff --git a/docs/transformers/index.html b/docs/transformers/index.html index 02580f08..96f70d86 100644 --- a/docs/transformers/index.html +++ b/docs/transformers/index.html @@ -124,7 +124,6 @@ diff --git a/docs/transformers/knn/build_index.html b/docs/transformers/knn/build_index.html index 9aabd934..e9bd4b2e 100644 --- a/docs/transformers/knn/build_index.html +++ b/docs/transformers/knn/build_index.html @@ -607,7 +607,6 @@ diff --git a/docs/transformers/knn/eval_knn.html b/docs/transformers/knn/eval_knn.html index 96e9ffe2..52436d8f 100644 --- a/docs/transformers/knn/eval_knn.html +++ b/docs/transformers/knn/eval_knn.html @@ -575,7 +575,6 @@ diff --git a/docs/transformers/knn/index.html b/docs/transformers/knn/index.html index 141b29ff..68921ef9 100644 --- a/docs/transformers/knn/index.html +++ b/docs/transformers/knn/index.html @@ -90,7 +90,6 @@ diff --git a/docs/transformers/knn/train_model.html b/docs/transformers/knn/train_model.html index a1091b9d..99524753 100644 --- a/docs/transformers/knn/train_model.html +++ b/docs/transformers/knn/train_model.html @@ -491,7 +491,6 @@ diff --git a/docs/transformers/label_smoothing_loss.html b/docs/transformers/label_smoothing_loss.html index 2f335ed8..05ef9b3d 100644 --- a/docs/transformers/label_smoothing_loss.html +++ b/docs/transformers/label_smoothing_loss.html @@ -199,7 +199,6 @@ diff --git a/docs/transformers/mha.html b/docs/transformers/mha.html index 13eb4161..a8aac8cc 100644 --- a/docs/transformers/mha.html +++ b/docs/transformers/mha.html @@ -683,7 +683,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/mlm/experiment.html b/docs/transformers/mlm/experiment.html index ba4387bc..e398bdfc 100644 --- a/docs/transformers/mlm/experiment.html +++ b/docs/transformers/mlm/experiment.html @@ -1160,7 +1160,6 @@ diff --git a/docs/transformers/mlm/index.html b/docs/transformers/mlm/index.html index 63639e11..fcd6c7aa 100644 --- a/docs/transformers/mlm/index.html +++ b/docs/transformers/mlm/index.html @@ -335,7 +335,6 @@ diff --git a/docs/transformers/mlm/readme.html b/docs/transformers/mlm/readme.html index 41d7371d..ad88bfde 100644 --- a/docs/transformers/mlm/readme.html +++ b/docs/transformers/mlm/readme.html @@ -106,7 +106,6 @@ diff --git a/docs/transformers/mlp_mixer/experiment.html b/docs/transformers/mlp_mixer/experiment.html index 7068a0b3..15b8864f 100644 --- a/docs/transformers/mlp_mixer/experiment.html +++ b/docs/transformers/mlp_mixer/experiment.html @@ -431,7 +431,6 @@ diff --git a/docs/transformers/mlp_mixer/index.html b/docs/transformers/mlp_mixer/index.html index 0002c214..2fc5a569 100644 --- a/docs/transformers/mlp_mixer/index.html +++ b/docs/transformers/mlp_mixer/index.html @@ -228,7 +228,6 @@ diff --git a/docs/transformers/mlp_mixer/readme.html b/docs/transformers/mlp_mixer/readme.html index e3b19093..eea0190a 100644 --- a/docs/transformers/mlp_mixer/readme.html +++ b/docs/transformers/mlp_mixer/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/transformers/models.html b/docs/transformers/models.html index 9a73a3ff..f4c7670a 100644 --- a/docs/transformers/models.html +++ b/docs/transformers/models.html @@ -704,7 +704,6 @@ diff --git a/docs/transformers/positional_encoding.html b/docs/transformers/positional_encoding.html index 47db8418..dc507d52 100644 --- a/docs/transformers/positional_encoding.html +++ b/docs/transformers/positional_encoding.html @@ -246,7 +246,6 @@ diff --git a/docs/transformers/primer_ez/efficient.html b/docs/transformers/primer_ez/efficient.html index f2aec2d3..10b84ab4 100644 --- a/docs/transformers/primer_ez/efficient.html +++ b/docs/transformers/primer_ez/efficient.html @@ -213,7 +213,6 @@ diff --git a/docs/transformers/primer_ez/experiment.html b/docs/transformers/primer_ez/experiment.html index d286e12e..50ca0b29 100644 --- a/docs/transformers/primer_ez/experiment.html +++ b/docs/transformers/primer_ez/experiment.html @@ -434,7 +434,6 @@ diff --git a/docs/transformers/primer_ez/index.html b/docs/transformers/primer_ez/index.html index a862d574..0233b4e6 100644 --- a/docs/transformers/primer_ez/index.html +++ b/docs/transformers/primer_ez/index.html @@ -368,7 +368,6 @@ diff --git a/docs/transformers/primer_ez/readme.html b/docs/transformers/primer_ez/readme.html index e7e70a99..46a96318 100644 --- a/docs/transformers/primer_ez/readme.html +++ b/docs/transformers/primer_ez/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/transformers/primer_ez/variations.html b/docs/transformers/primer_ez/variations.html index 5f848e68..555c593e 100644 --- a/docs/transformers/primer_ez/variations.html +++ b/docs/transformers/primer_ez/variations.html @@ -502,7 +502,6 @@ diff --git a/docs/transformers/relative_mha.html b/docs/transformers/relative_mha.html index 8c780de0..6e263450 100644 --- a/docs/transformers/relative_mha.html +++ b/docs/transformers/relative_mha.html @@ -67,7 +67,6 @@ diff --git a/docs/transformers/retro/bert_embeddings.html b/docs/transformers/retro/bert_embeddings.html index 1aa71037..9983941f 100644 --- a/docs/transformers/retro/bert_embeddings.html +++ b/docs/transformers/retro/bert_embeddings.html @@ -474,7 +474,6 @@ diff --git a/docs/transformers/retro/database.html b/docs/transformers/retro/database.html index eccb2653..b4706a73 100644 --- a/docs/transformers/retro/database.html +++ b/docs/transformers/retro/database.html @@ -488,7 +488,6 @@ diff --git a/docs/transformers/retro/dataset.html b/docs/transformers/retro/dataset.html index ec66b809..9aeb5f0f 100644 --- a/docs/transformers/retro/dataset.html +++ b/docs/transformers/retro/dataset.html @@ -483,7 +483,6 @@ diff --git a/docs/transformers/retro/index.html b/docs/transformers/retro/index.html index 4f1ae477..320860b0 100644 --- a/docs/transformers/retro/index.html +++ b/docs/transformers/retro/index.html @@ -89,7 +89,6 @@ diff --git a/docs/transformers/retro/model.html b/docs/transformers/retro/model.html index 3064e08e..ba9957ef 100644 --- a/docs/transformers/retro/model.html +++ b/docs/transformers/retro/model.html @@ -2008,7 +2008,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/retro/train.html b/docs/transformers/retro/train.html index 4a89f749..ba946b9e 100644 --- a/docs/transformers/retro/train.html +++ b/docs/transformers/retro/train.html @@ -808,7 +808,6 @@ diff --git a/docs/transformers/rope/experiment.html b/docs/transformers/rope/experiment.html index c78424fd..1253f142 100644 --- a/docs/transformers/rope/experiment.html +++ b/docs/transformers/rope/experiment.html @@ -399,7 +399,6 @@ diff --git a/docs/transformers/rope/index.html b/docs/transformers/rope/index.html index 446b5637..6b178da5 100644 --- a/docs/transformers/rope/index.html +++ b/docs/transformers/rope/index.html @@ -445,7 +445,6 @@ diff --git a/docs/transformers/rope/value_pe/arithmetic_experiment.html b/docs/transformers/rope/value_pe/arithmetic_experiment.html index 45c262ee..8b2c868d 100644 --- a/docs/transformers/rope/value_pe/arithmetic_experiment.html +++ b/docs/transformers/rope/value_pe/arithmetic_experiment.html @@ -357,7 +357,6 @@ diff --git a/docs/transformers/rope/value_pe/experiment.html b/docs/transformers/rope/value_pe/experiment.html index 2a1ebc77..c94a7979 100644 --- a/docs/transformers/rope/value_pe/experiment.html +++ b/docs/transformers/rope/value_pe/experiment.html @@ -407,7 +407,6 @@ diff --git a/docs/transformers/rope/value_pe/index.html b/docs/transformers/rope/value_pe/index.html index 9b35ca38..be2b750c 100644 --- a/docs/transformers/rope/value_pe/index.html +++ b/docs/transformers/rope/value_pe/index.html @@ -464,7 +464,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/transformers/switch/experiment.html b/docs/transformers/switch/experiment.html index bd3d5644..64cdda31 100644 --- a/docs/transformers/switch/experiment.html +++ b/docs/transformers/switch/experiment.html @@ -837,7 +837,6 @@ diff --git a/docs/transformers/switch/index.html b/docs/transformers/switch/index.html index ffad4320..1204fde2 100644 --- a/docs/transformers/switch/index.html +++ b/docs/transformers/switch/index.html @@ -713,7 +713,6 @@ diff --git a/docs/transformers/switch/readme.html b/docs/transformers/switch/readme.html index 0d678bac..7867af71 100644 --- a/docs/transformers/switch/readme.html +++ b/docs/transformers/switch/readme.html @@ -84,7 +84,6 @@ diff --git a/docs/transformers/utils.html b/docs/transformers/utils.html index 7eba77a9..4799bd8e 100644 --- a/docs/transformers/utils.html +++ b/docs/transformers/utils.html @@ -119,7 +119,6 @@ diff --git a/docs/transformers/vit/experiment.html b/docs/transformers/vit/experiment.html index 3773271a..959a3ac5 100644 --- a/docs/transformers/vit/experiment.html +++ b/docs/transformers/vit/experiment.html @@ -368,7 +368,6 @@ diff --git a/docs/transformers/vit/index.html b/docs/transformers/vit/index.html index 4e7c07e0..8299e802 100644 --- a/docs/transformers/vit/index.html +++ b/docs/transformers/vit/index.html @@ -654,7 +654,6 @@ diff --git a/docs/transformers/vit/readme.html b/docs/transformers/vit/readme.html index 727a50f2..07985a55 100644 --- a/docs/transformers/vit/readme.html +++ b/docs/transformers/vit/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/transformers/xl/experiment.html b/docs/transformers/xl/experiment.html index 4a846b64..cbd563bc 100644 --- a/docs/transformers/xl/experiment.html +++ b/docs/transformers/xl/experiment.html @@ -1043,7 +1043,6 @@ diff --git a/docs/transformers/xl/index.html b/docs/transformers/xl/index.html index 0bb1268f..b3986b42 100644 --- a/docs/transformers/xl/index.html +++ b/docs/transformers/xl/index.html @@ -447,7 +447,6 @@ diff --git a/docs/transformers/xl/readme.html b/docs/transformers/xl/readme.html index 55c18b0a..108aaced 100644 --- a/docs/transformers/xl/readme.html +++ b/docs/transformers/xl/readme.html @@ -85,7 +85,6 @@ diff --git a/docs/transformers/xl/relative_mha.html b/docs/transformers/xl/relative_mha.html index 6fa00804..21ace713 100644 --- a/docs/transformers/xl/relative_mha.html +++ b/docs/transformers/xl/relative_mha.html @@ -373,7 +373,6 @@ diff --git a/docs/uncertainty/evidence/experiment.html b/docs/uncertainty/evidence/experiment.html index bcc98f3f..518356d9 100644 --- a/docs/uncertainty/evidence/experiment.html +++ b/docs/uncertainty/evidence/experiment.html @@ -863,7 +863,6 @@ diff --git a/docs/uncertainty/evidence/index.html b/docs/uncertainty/evidence/index.html index 071c968a..5d5eb6ae 100644 --- a/docs/uncertainty/evidence/index.html +++ b/docs/uncertainty/evidence/index.html @@ -679,7 +679,6 @@ diff --git a/docs/uncertainty/evidence/readme.html b/docs/uncertainty/evidence/readme.html index da87536f..9f35901c 100644 --- a/docs/uncertainty/evidence/readme.html +++ b/docs/uncertainty/evidence/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/uncertainty/index.html b/docs/uncertainty/index.html index 22ed3120..58b110f2 100644 --- a/docs/uncertainty/index.html +++ b/docs/uncertainty/index.html @@ -80,7 +80,6 @@ diff --git a/docs/uncertainty/readme.html b/docs/uncertainty/readme.html index 2e6fa754..4929b8dd 100644 --- a/docs/uncertainty/readme.html +++ b/docs/uncertainty/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/unet/carvana.html b/docs/unet/carvana.html index 98260be8..e4369239 100644 --- a/docs/unet/carvana.html +++ b/docs/unet/carvana.html @@ -301,7 +301,6 @@ diff --git a/docs/unet/experiment.html b/docs/unet/experiment.html index 5cc3a30b..0d411e4b 100644 --- a/docs/unet/experiment.html +++ b/docs/unet/experiment.html @@ -685,7 +685,6 @@ diff --git a/docs/unet/index.html b/docs/unet/index.html index f3b80dbb..73b3ae38 100644 --- a/docs/unet/index.html +++ b/docs/unet/index.html @@ -621,7 +621,6 @@ diff --git a/docs/utils/index.html b/docs/utils/index.html index c4b7a3aa..3528b308 100644 --- a/docs/utils/index.html +++ b/docs/utils/index.html @@ -242,7 +242,6 @@ diff --git a/docs/utils/tokenizer.html b/docs/utils/tokenizer.html index ce2a98f2..2049e971 100644 --- a/docs/utils/tokenizer.html +++ b/docs/utils/tokenizer.html @@ -190,7 +190,6 @@ diff --git a/docs/zh/RWKV/configs.html b/docs/zh/RWKV/configs.html index df1ecfc7..04044322 100644 --- a/docs/zh/RWKV/configs.html +++ b/docs/zh/RWKV/configs.html @@ -162,7 +162,6 @@ diff --git a/docs/zh/RWKV/experiment.html b/docs/zh/RWKV/experiment.html index f02f4f9c..000a0f6a 100644 --- a/docs/zh/RWKV/experiment.html +++ b/docs/zh/RWKV/experiment.html @@ -576,7 +576,6 @@ diff --git a/docs/zh/RWKV/index.html b/docs/zh/RWKV/index.html index 69857ee8..7ad11230 100644 --- a/docs/zh/RWKV/index.html +++ b/docs/zh/RWKV/index.html @@ -788,7 +788,6 @@ diff --git a/docs/zh/activations/fta/experiment.html b/docs/zh/activations/fta/experiment.html index 0d8ab014..2ceb568f 100644 --- a/docs/zh/activations/fta/experiment.html +++ b/docs/zh/activations/fta/experiment.html @@ -792,7 +792,6 @@ diff --git a/docs/zh/activations/fta/index.html b/docs/zh/activations/fta/index.html index 542c1c40..d170b58b 100644 --- a/docs/zh/activations/fta/index.html +++ b/docs/zh/activations/fta/index.html @@ -360,7 +360,6 @@ diff --git a/docs/zh/activations/index.html b/docs/zh/activations/index.html index ef42de53..3223467d 100644 --- a/docs/zh/activations/index.html +++ b/docs/zh/activations/index.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/activations/swish.html b/docs/zh/activations/swish.html index 4a1b5491..5e8c21cf 100644 --- a/docs/zh/activations/swish.html +++ b/docs/zh/activations/swish.html @@ -116,7 +116,6 @@ diff --git a/docs/zh/adaptive_computation/index.html b/docs/zh/adaptive_computation/index.html index e6110c82..d6027540 100644 --- a/docs/zh/adaptive_computation/index.html +++ b/docs/zh/adaptive_computation/index.html @@ -81,7 +81,6 @@ diff --git a/docs/zh/adaptive_computation/parity.html b/docs/zh/adaptive_computation/parity.html index 4e359cd9..a586f8fa 100644 --- a/docs/zh/adaptive_computation/parity.html +++ b/docs/zh/adaptive_computation/parity.html @@ -229,7 +229,6 @@ diff --git a/docs/zh/adaptive_computation/ponder_net/experiment.html b/docs/zh/adaptive_computation/ponder_net/experiment.html index 74a2da79..25af16be 100644 --- a/docs/zh/adaptive_computation/ponder_net/experiment.html +++ b/docs/zh/adaptive_computation/ponder_net/experiment.html @@ -592,7 +592,6 @@ diff --git a/docs/zh/adaptive_computation/ponder_net/index.html b/docs/zh/adaptive_computation/ponder_net/index.html index 1eb19035..198e87ac 100644 --- a/docs/zh/adaptive_computation/ponder_net/index.html +++ b/docs/zh/adaptive_computation/ponder_net/index.html @@ -757,7 +757,6 @@ isTrending Research Papers labml.ai diff --git a/docs/zh/capsule_networks/mnist.html b/docs/zh/capsule_networks/mnist.html index e27cd49f..411db7da 100644 --- a/docs/zh/capsule_networks/mnist.html +++ b/docs/zh/capsule_networks/mnist.html @@ -552,7 +552,6 @@ diff --git a/docs/zh/capsule_networks/readme.html b/docs/zh/capsule_networks/readme.html index f25045ca..a8dd250c 100644 --- a/docs/zh/capsule_networks/readme.html +++ b/docs/zh/capsule_networks/readme.html @@ -85,7 +85,6 @@ diff --git a/docs/zh/cfr/analytics.html b/docs/zh/cfr/analytics.html index 6248637a..11e33377 100644 --- a/docs/zh/cfr/analytics.html +++ b/docs/zh/cfr/analytics.html @@ -158,7 +158,6 @@ diff --git a/docs/zh/cfr/index.html b/docs/zh/cfr/index.html index 4eef7655..0a2aea19 100644 --- a/docs/zh/cfr/index.html +++ b/docs/zh/cfr/index.html @@ -1365,7 +1365,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/cfr/infoset_saver.html b/docs/zh/cfr/infoset_saver.html index 0e3346ea..2237e3c0 100644 --- a/docs/zh/cfr/infoset_saver.html +++ b/docs/zh/cfr/infoset_saver.html @@ -139,7 +139,6 @@ diff --git a/docs/zh/cfr/kuhn/index.html b/docs/zh/cfr/kuhn/index.html index c87c1ace..ff975064 100644 --- a/docs/zh/cfr/kuhn/index.html +++ b/docs/zh/cfr/kuhn/index.html @@ -827,7 +827,6 @@ diff --git a/docs/zh/conv_mixer/experiment.html b/docs/zh/conv_mixer/experiment.html index db53bcd2..36360d51 100644 --- a/docs/zh/conv_mixer/experiment.html +++ b/docs/zh/conv_mixer/experiment.html @@ -330,7 +330,6 @@ diff --git a/docs/zh/conv_mixer/index.html b/docs/zh/conv_mixer/index.html index 11e66550..03dde419 100644 --- a/docs/zh/conv_mixer/index.html +++ b/docs/zh/conv_mixer/index.html @@ -678,7 +678,6 @@ diff --git a/docs/zh/conv_mixer/readme.html b/docs/zh/conv_mixer/readme.html index 91b04fb8..5c28be14 100644 --- a/docs/zh/conv_mixer/readme.html +++ b/docs/zh/conv_mixer/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/diffusion/ddpm/evaluate.html b/docs/zh/diffusion/ddpm/evaluate.html index c9758107..942d0c0e 100644 --- a/docs/zh/diffusion/ddpm/evaluate.html +++ b/docs/zh/diffusion/ddpm/evaluate.html @@ -1347,7 +1347,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/ddpm/experiment.html b/docs/zh/diffusion/ddpm/experiment.html index 837d662f..6ecb21d4 100644 --- a/docs/zh/diffusion/ddpm/experiment.html +++ b/docs/zh/diffusion/ddpm/experiment.html @@ -943,7 +943,6 @@ diff --git a/docs/zh/diffusion/ddpm/index.html b/docs/zh/diffusion/ddpm/index.html index 145449a1..78d56dbc 100644 --- a/docs/zh/diffusion/ddpm/index.html +++ b/docs/zh/diffusion/ddpm/index.html @@ -838,7 +838,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/ddpm/readme.html b/docs/zh/diffusion/ddpm/readme.html index 898e247f..c9ea2ada 100644 --- a/docs/zh/diffusion/ddpm/readme.html +++ b/docs/zh/diffusion/ddpm/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/diffusion/ddpm/unet.html b/docs/zh/diffusion/ddpm/unet.html index d0e6408d..3d957119 100644 --- a/docs/zh/diffusion/ddpm/unet.html +++ b/docs/zh/diffusion/ddpm/unet.html @@ -1406,7 +1406,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/ddpm/utils.html b/docs/zh/diffusion/ddpm/utils.html index ee9d724b..daf1d8f2 100644 --- a/docs/zh/diffusion/ddpm/utils.html +++ b/docs/zh/diffusion/ddpm/utils.html @@ -103,7 +103,6 @@ diff --git a/docs/zh/diffusion/index.html b/docs/zh/diffusion/index.html index 1854ae2f..2f36e84a 100644 --- a/docs/zh/diffusion/index.html +++ b/docs/zh/diffusion/index.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/index.html b/docs/zh/diffusion/stable_diffusion/index.html index 47e6e885..bcac8820 100644 --- a/docs/zh/diffusion/stable_diffusion/index.html +++ b/docs/zh/diffusion/stable_diffusion/index.html @@ -101,7 +101,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/latent_diffusion.html b/docs/zh/diffusion/stable_diffusion/latent_diffusion.html index 55922073..af69c383 100644 --- a/docs/zh/diffusion/stable_diffusion/latent_diffusion.html +++ b/docs/zh/diffusion/stable_diffusion/latent_diffusion.html @@ -406,7 +406,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/model/autoencoder.html b/docs/zh/diffusion/stable_diffusion/model/autoencoder.html index c6a289f7..ede2cbdc 100644 --- a/docs/zh/diffusion/stable_diffusion/model/autoencoder.html +++ b/docs/zh/diffusion/stable_diffusion/model/autoencoder.html @@ -1547,7 +1547,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/stable_diffusion/model/clip_embedder.html b/docs/zh/diffusion/stable_diffusion/model/clip_embedder.html index 7265f93d..eb6e67f8 100644 --- a/docs/zh/diffusion/stable_diffusion/model/clip_embedder.html +++ b/docs/zh/diffusion/stable_diffusion/model/clip_embedder.html @@ -201,7 +201,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/model/index.html b/docs/zh/diffusion/stable_diffusion/model/index.html index cdc3cfb3..60ef9ae5 100644 --- a/docs/zh/diffusion/stable_diffusion/model/index.html +++ b/docs/zh/diffusion/stable_diffusion/model/index.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/model/unet.html b/docs/zh/diffusion/stable_diffusion/model/unet.html index c2cdcd50..05371c14 100644 --- a/docs/zh/diffusion/stable_diffusion/model/unet.html +++ b/docs/zh/diffusion/stable_diffusion/model/unet.html @@ -1080,7 +1080,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/model/unet_attention.html b/docs/zh/diffusion/stable_diffusion/model/unet_attention.html index 49c66428..125ff1a6 100644 --- a/docs/zh/diffusion/stable_diffusion/model/unet_attention.html +++ b/docs/zh/diffusion/stable_diffusion/model/unet_attention.html @@ -1101,7 +1101,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/stable_diffusion/sampler/ddim.html b/docs/zh/diffusion/stable_diffusion/sampler/ddim.html index 61b29e6c..d7bfc055 100644 --- a/docs/zh/diffusion/stable_diffusion/sampler/ddim.html +++ b/docs/zh/diffusion/stable_diffusion/sampler/ddim.html @@ -1030,7 +1030,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/stable_diffusion/sampler/ddpm.html b/docs/zh/diffusion/stable_diffusion/sampler/ddpm.html index d10c5397..01f0bb87 100644 --- a/docs/zh/diffusion/stable_diffusion/sampler/ddpm.html +++ b/docs/zh/diffusion/stable_diffusion/sampler/ddpm.html @@ -894,7 +894,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/diffusion/stable_diffusion/sampler/index.html b/docs/zh/diffusion/stable_diffusion/sampler/index.html index b1c6aa06..e73be35e 100644 --- a/docs/zh/diffusion/stable_diffusion/sampler/index.html +++ b/docs/zh/diffusion/stable_diffusion/sampler/index.html @@ -380,7 +380,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/scripts/image_to_image.html b/docs/zh/diffusion/stable_diffusion/scripts/image_to_image.html index 6fad0ecb..1c64c590 100644 --- a/docs/zh/diffusion/stable_diffusion/scripts/image_to_image.html +++ b/docs/zh/diffusion/stable_diffusion/scripts/image_to_image.html @@ -426,7 +426,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/scripts/in_paint.html b/docs/zh/diffusion/stable_diffusion/scripts/in_paint.html index cd32130d..0c3bcc50 100644 --- a/docs/zh/diffusion/stable_diffusion/scripts/in_paint.html +++ b/docs/zh/diffusion/stable_diffusion/scripts/in_paint.html @@ -473,7 +473,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/scripts/index.html b/docs/zh/diffusion/stable_diffusion/scripts/index.html index 9529ca8f..4ffd41ee 100644 --- a/docs/zh/diffusion/stable_diffusion/scripts/index.html +++ b/docs/zh/diffusion/stable_diffusion/scripts/index.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/scripts/text_to_image.html b/docs/zh/diffusion/stable_diffusion/scripts/text_to_image.html index 32ad29b3..94d4b550 100644 --- a/docs/zh/diffusion/stable_diffusion/scripts/text_to_image.html +++ b/docs/zh/diffusion/stable_diffusion/scripts/text_to_image.html @@ -435,7 +435,6 @@ diff --git a/docs/zh/diffusion/stable_diffusion/util.html b/docs/zh/diffusion/stable_diffusion/util.html index b31bcfc9..f2bf71b5 100644 --- a/docs/zh/diffusion/stable_diffusion/util.html +++ b/docs/zh/diffusion/stable_diffusion/util.html @@ -431,7 +431,6 @@ diff --git a/docs/zh/distillation/index.html b/docs/zh/distillation/index.html index 09343b51..e0260f09 100644 --- a/docs/zh/distillation/index.html +++ b/docs/zh/distillation/index.html @@ -732,7 +732,6 @@ diff --git a/docs/zh/distillation/large.html b/docs/zh/distillation/large.html index 44b0ae1d..1a23f8b8 100644 --- a/docs/zh/distillation/large.html +++ b/docs/zh/distillation/large.html @@ -343,7 +343,6 @@ diff --git a/docs/zh/distillation/readme.html b/docs/zh/distillation/readme.html index 5c02bd4d..dc1c287c 100644 --- a/docs/zh/distillation/readme.html +++ b/docs/zh/distillation/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/distillation/small.html b/docs/zh/distillation/small.html index 5b4bd5f8..e716b271 100644 --- a/docs/zh/distillation/small.html +++ b/docs/zh/distillation/small.html @@ -329,7 +329,6 @@ diff --git a/docs/zh/experiments/arithmetic_dataset.html b/docs/zh/experiments/arithmetic_dataset.html index 24c892d9..05d14eff 100644 --- a/docs/zh/experiments/arithmetic_dataset.html +++ b/docs/zh/experiments/arithmetic_dataset.html @@ -855,7 +855,6 @@ diff --git a/docs/zh/experiments/cifar10.html b/docs/zh/experiments/cifar10.html index 9feecbaf..99b04950 100644 --- a/docs/zh/experiments/cifar10.html +++ b/docs/zh/experiments/cifar10.html @@ -396,7 +396,6 @@ diff --git a/docs/zh/experiments/index.html b/docs/zh/experiments/index.html index 8526c0ef..e9a9868c 100644 --- a/docs/zh/experiments/index.html +++ b/docs/zh/experiments/index.html @@ -66,7 +66,6 @@ diff --git a/docs/zh/experiments/mnist.html b/docs/zh/experiments/mnist.html index a9e03405..522510c5 100644 --- a/docs/zh/experiments/mnist.html +++ b/docs/zh/experiments/mnist.html @@ -433,7 +433,6 @@ diff --git a/docs/zh/experiments/nlp_autoregression.html b/docs/zh/experiments/nlp_autoregression.html index 0afbaa20..c944b420 100644 --- a/docs/zh/experiments/nlp_autoregression.html +++ b/docs/zh/experiments/nlp_autoregression.html @@ -1080,7 +1080,6 @@ diff --git a/docs/zh/experiments/nlp_classification.html b/docs/zh/experiments/nlp_classification.html index c2d74a7f..7648efa2 100644 --- a/docs/zh/experiments/nlp_classification.html +++ b/docs/zh/experiments/nlp_classification.html @@ -1010,7 +1010,6 @@ diff --git a/docs/zh/gan/cycle_gan/index.html b/docs/zh/gan/cycle_gan/index.html index 5fe9ff7d..62189f97 100644 --- a/docs/zh/gan/cycle_gan/index.html +++ b/docs/zh/gan/cycle_gan/index.html @@ -1934,7 +1934,6 @@ inReLU diff --git a/docs/zh/gan/cycle_gan/readme.html b/docs/zh/gan/cycle_gan/readme.html index 243bef3e..77cbb964 100644 --- a/docs/zh/gan/cycle_gan/readme.html +++ b/docs/zh/gan/cycle_gan/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/gan/dcgan/index.html b/docs/zh/gan/dcgan/index.html index 8b98dda8..d5d8880f 100644 --- a/docs/zh/gan/dcgan/index.html +++ b/docs/zh/gan/dcgan/index.html @@ -366,7 +366,6 @@ diff --git a/docs/zh/gan/dcgan/readme.html b/docs/zh/gan/dcgan/readme.html index f350cacd..cf332544 100644 --- a/docs/zh/gan/dcgan/readme.html +++ b/docs/zh/gan/dcgan/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/gan/index.html b/docs/zh/gan/index.html index 49a5a556..32bf8e71 100644 --- a/docs/zh/gan/index.html +++ b/docs/zh/gan/index.html @@ -84,7 +84,6 @@ diff --git a/docs/zh/gan/original/experiment.html b/docs/zh/gan/original/experiment.html index ed71f6c9..7a534c98 100644 --- a/docs/zh/gan/original/experiment.html +++ b/docs/zh/gan/original/experiment.html @@ -599,7 +599,6 @@ diff --git a/docs/zh/gan/original/index.html b/docs/zh/gan/original/index.html index 0f05303d..df5515f6 100644 --- a/docs/zh/gan/original/index.html +++ b/docs/zh/gan/original/index.html @@ -270,7 +270,6 @@ logits 来自Trending Research Papers labml.ai diff --git a/docs/zh/normalization/batch_norm/cifar10.html b/docs/zh/normalization/batch_norm/cifar10.html index 04b1e22b..a9ba5231 100644 --- a/docs/zh/normalization/batch_norm/cifar10.html +++ b/docs/zh/normalization/batch_norm/cifar10.html @@ -226,7 +226,6 @@ diff --git a/docs/zh/normalization/batch_norm/index.html b/docs/zh/normalization/batch_norm/index.html index a3b98e3b..25927cab 100644 --- a/docs/zh/normalization/batch_norm/index.html +++ b/docs/zh/normalization/batch_norm/index.html @@ -469,7 +469,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/normalization/batch_norm/mnist.html b/docs/zh/normalization/batch_norm/mnist.html index 8a96a1fc..b1dd0a7c 100644 --- a/docs/zh/normalization/batch_norm/mnist.html +++ b/docs/zh/normalization/batch_norm/mnist.html @@ -318,7 +318,6 @@ diff --git a/docs/zh/normalization/batch_norm/readme.html b/docs/zh/normalization/batch_norm/readme.html index 01324778..2355ee6b 100644 --- a/docs/zh/normalization/batch_norm/readme.html +++ b/docs/zh/normalization/batch_norm/readme.html @@ -110,7 +110,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/normalization/deep_norm/experiment.html b/docs/zh/normalization/deep_norm/experiment.html index 3159d3c3..1c82ab04 100644 --- a/docs/zh/normalization/deep_norm/experiment.html +++ b/docs/zh/normalization/deep_norm/experiment.html @@ -623,7 +623,6 @@ diff --git a/docs/zh/normalization/deep_norm/index.html b/docs/zh/normalization/deep_norm/index.html index 16313998..99eba969 100644 --- a/docs/zh/normalization/deep_norm/index.html +++ b/docs/zh/normalization/deep_norm/index.html @@ -391,7 +391,6 @@ diff --git a/docs/zh/normalization/group_norm/experiment.html b/docs/zh/normalization/group_norm/experiment.html index 620f68b0..834967ea 100644 --- a/docs/zh/normalization/group_norm/experiment.html +++ b/docs/zh/normalization/group_norm/experiment.html @@ -250,7 +250,6 @@ diff --git a/docs/zh/normalization/group_norm/index.html b/docs/zh/normalization/group_norm/index.html index 17817238..b2478a58 100644 --- a/docs/zh/normalization/group_norm/index.html +++ b/docs/zh/normalization/group_norm/index.html @@ -379,7 +379,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/normalization/group_norm/readme.html b/docs/zh/normalization/group_norm/readme.html index c370b54f..92e6af26 100644 --- a/docs/zh/normalization/group_norm/readme.html +++ b/docs/zh/normalization/group_norm/readme.html @@ -84,7 +84,6 @@ diff --git a/docs/zh/normalization/index.html b/docs/zh/normalization/index.html index f5be9279..05bbf87a 100644 --- a/docs/zh/normalization/index.html +++ b/docs/zh/normalization/index.html @@ -85,7 +85,6 @@ diff --git a/docs/zh/normalization/instance_norm/experiment.html b/docs/zh/normalization/instance_norm/experiment.html index 8d29a8ee..8ae722aa 100644 --- a/docs/zh/normalization/instance_norm/experiment.html +++ b/docs/zh/normalization/instance_norm/experiment.html @@ -226,7 +226,6 @@ diff --git a/docs/zh/normalization/instance_norm/index.html b/docs/zh/normalization/instance_norm/index.html index 07789cda..948b0def 100644 --- a/docs/zh/normalization/instance_norm/index.html +++ b/docs/zh/normalization/instance_norm/index.html @@ -362,7 +362,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/normalization/instance_norm/readme.html b/docs/zh/normalization/instance_norm/readme.html index 7dc0ebb1..475fa466 100644 --- a/docs/zh/normalization/instance_norm/readme.html +++ b/docs/zh/normalization/instance_norm/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/zh/normalization/layer_norm/index.html b/docs/zh/normalization/layer_norm/index.html index 527dbacc..53123587 100644 --- a/docs/zh/normalization/layer_norm/index.html +++ b/docs/zh/normalization/layer_norm/index.html @@ -392,7 +392,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/normalization/layer_norm/readme.html b/docs/zh/normalization/layer_norm/readme.html index e971082c..bcbbd254 100644 --- a/docs/zh/normalization/layer_norm/readme.html +++ b/docs/zh/normalization/layer_norm/readme.html @@ -89,7 +89,6 @@ diff --git a/docs/zh/normalization/weight_standardization/conv2d.html b/docs/zh/normalization/weight_standardization/conv2d.html index 0dc2f4c7..8939a2c8 100644 --- a/docs/zh/normalization/weight_standardization/conv2d.html +++ b/docs/zh/normalization/weight_standardization/conv2d.html @@ -167,7 +167,6 @@ diff --git a/docs/zh/normalization/weight_standardization/experiment.html b/docs/zh/normalization/weight_standardization/experiment.html index a0ed2d75..5ed45fe7 100644 --- a/docs/zh/normalization/weight_standardization/experiment.html +++ b/docs/zh/normalization/weight_standardization/experiment.html @@ -227,7 +227,6 @@ diff --git a/docs/zh/normalization/weight_standardization/index.html b/docs/zh/normalization/weight_standardization/index.html index f849dc93..c94625fe 100644 --- a/docs/zh/normalization/weight_standardization/index.html +++ b/docs/zh/normalization/weight_standardization/index.html @@ -168,7 +168,6 @@ c-4-3.333-8.333-7.667-13 -13l-13-13l77-155 77-156c66 199.333 139 419.667 diff --git a/docs/zh/normalization/weight_standardization/readme.html b/docs/zh/normalization/weight_standardization/readme.html index 6405b6fd..ba509b74 100644 --- a/docs/zh/normalization/weight_standardization/readme.html +++ b/docs/zh/normalization/weight_standardization/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/optimizers/ada_belief.html b/docs/zh/optimizers/ada_belief.html index dda59555..31e7bba1 100644 --- a/docs/zh/optimizers/ada_belief.html +++ b/docs/zh/optimizers/ada_belief.html @@ -459,7 +459,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/optimizers/adam.html b/docs/zh/optimizers/adam.html index 997792ad..ca93d816 100644 --- a/docs/zh/optimizers/adam.html +++ b/docs/zh/optimizers/adam.html @@ -699,7 +699,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/optimizers/adam_fp16.html b/docs/zh/optimizers/adam_fp16.html index d774dabb..bc497b13 100644 --- a/docs/zh/optimizers/adam_fp16.html +++ b/docs/zh/optimizers/adam_fp16.html @@ -454,7 +454,6 @@ diff --git a/docs/zh/optimizers/adam_warmup.html b/docs/zh/optimizers/adam_warmup.html index f6db82f3..86a3a4cb 100644 --- a/docs/zh/optimizers/adam_warmup.html +++ b/docs/zh/optimizers/adam_warmup.html @@ -195,7 +195,6 @@ diff --git a/docs/zh/optimizers/adam_warmup_cosine_decay.html b/docs/zh/optimizers/adam_warmup_cosine_decay.html index d8542b5a..1305cb24 100644 --- a/docs/zh/optimizers/adam_warmup_cosine_decay.html +++ b/docs/zh/optimizers/adam_warmup_cosine_decay.html @@ -246,7 +246,6 @@ diff --git a/docs/zh/optimizers/amsgrad.html b/docs/zh/optimizers/amsgrad.html index a23218dc..5f423f1b 100644 --- a/docs/zh/optimizers/amsgrad.html +++ b/docs/zh/optimizers/amsgrad.html @@ -515,7 +515,6 @@ diff --git a/docs/zh/optimizers/configs.html b/docs/zh/optimizers/configs.html index bc62690d..3a69c769 100644 --- a/docs/zh/optimizers/configs.html +++ b/docs/zh/optimizers/configs.html @@ -405,7 +405,6 @@ diff --git a/docs/zh/optimizers/index.html b/docs/zh/optimizers/index.html index 786056f6..1c483ae9 100644 --- a/docs/zh/optimizers/index.html +++ b/docs/zh/optimizers/index.html @@ -536,7 +536,6 @@ diff --git a/docs/zh/optimizers/mnist_experiment.html b/docs/zh/optimizers/mnist_experiment.html index c79dd56b..c3ba6e94 100644 --- a/docs/zh/optimizers/mnist_experiment.html +++ b/docs/zh/optimizers/mnist_experiment.html @@ -412,7 +412,6 @@ diff --git a/docs/zh/optimizers/noam.html b/docs/zh/optimizers/noam.html index 33063487..bf0888f1 100644 --- a/docs/zh/optimizers/noam.html +++ b/docs/zh/optimizers/noam.html @@ -280,7 +280,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/optimizers/performance_test.html b/docs/zh/optimizers/performance_test.html index 8363b85a..e444ea35 100644 --- a/docs/zh/optimizers/performance_test.html +++ b/docs/zh/optimizers/performance_test.html @@ -127,7 +127,6 @@ MyAdam...[DONE] 1,192.89ms diff --git a/docs/zh/optimizers/radam.html b/docs/zh/optimizers/radam.html index 19306a3f..2f0593c1 100644 --- a/docs/zh/optimizers/radam.html +++ b/docs/zh/optimizers/radam.html @@ -734,7 +734,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/optimizers/readme.html b/docs/zh/optimizers/readme.html index 1eedfce0..40dff20a 100644 --- a/docs/zh/optimizers/readme.html +++ b/docs/zh/optimizers/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/zh/optimizers/sophia.html b/docs/zh/optimizers/sophia.html index e34d1bd6..58c613d2 100644 --- a/docs/zh/optimizers/sophia.html +++ b/docs/zh/optimizers/sophia.html @@ -453,7 +453,6 @@ diff --git a/docs/zh/recurrent_highway_networks/index.html b/docs/zh/recurrent_highway_networks/index.html index de714137..9a6fcbf2 100644 --- a/docs/zh/recurrent_highway_networks/index.html +++ b/docs/zh/recurrent_highway_networks/index.html @@ -449,7 +449,6 @@ diff --git a/docs/zh/resnet/experiment.html b/docs/zh/resnet/experiment.html index a34c7577..008580fd 100644 --- a/docs/zh/resnet/experiment.html +++ b/docs/zh/resnet/experiment.html @@ -305,7 +305,6 @@ diff --git a/docs/zh/resnet/index.html b/docs/zh/resnet/index.html index e3f00cfa..046dc3b8 100644 --- a/docs/zh/resnet/index.html +++ b/docs/zh/resnet/index.html @@ -999,7 +999,6 @@ diff --git a/docs/zh/resnet/readme.html b/docs/zh/resnet/readme.html index 889b620f..94814ce3 100644 --- a/docs/zh/resnet/readme.html +++ b/docs/zh/resnet/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/rl/dqn/experiment.html b/docs/zh/rl/dqn/experiment.html index 6a2280c9..cd73e855 100644 --- a/docs/zh/rl/dqn/experiment.html +++ b/docs/zh/rl/dqn/experiment.html @@ -1128,7 +1128,6 @@ diff --git a/docs/zh/rl/dqn/index.html b/docs/zh/rl/dqn/index.html index 6f58e3cf..b5eeecc2 100644 --- a/docs/zh/rl/dqn/index.html +++ b/docs/zh/rl/dqn/index.html @@ -253,7 +253,6 @@ diff --git a/docs/zh/rl/dqn/model.html b/docs/zh/rl/dqn/model.html index 4efeeec1..abc14b58 100644 --- a/docs/zh/rl/dqn/model.html +++ b/docs/zh/rl/dqn/model.html @@ -292,7 +292,6 @@ diff --git a/docs/zh/rl/dqn/readme.html b/docs/zh/rl/dqn/readme.html index 7b674755..6f891725 100644 --- a/docs/zh/rl/dqn/readme.html +++ b/docs/zh/rl/dqn/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/rl/dqn/replay_buffer.html b/docs/zh/rl/dqn/replay_buffer.html index 839ae4d2..d8fd457e 100644 --- a/docs/zh/rl/dqn/replay_buffer.html +++ b/docs/zh/rl/dqn/replay_buffer.html @@ -761,7 +761,6 @@ diff --git a/docs/zh/rl/game.html b/docs/zh/rl/game.html index 7d7a118c..1711c7c8 100644 --- a/docs/zh/rl/game.html +++ b/docs/zh/rl/game.html @@ -461,7 +461,6 @@ diff --git a/docs/zh/rl/index.html b/docs/zh/rl/index.html index 2049e6d9..6b00f106 100644 --- a/docs/zh/rl/index.html +++ b/docs/zh/rl/index.html @@ -87,7 +87,6 @@ diff --git a/docs/zh/rl/ppo/experiment.html b/docs/zh/rl/ppo/experiment.html index a73dfff5..a9e558ff 100644 --- a/docs/zh/rl/ppo/experiment.html +++ b/docs/zh/rl/ppo/experiment.html @@ -1318,7 +1318,6 @@ diff --git a/docs/zh/rl/ppo/gae.html b/docs/zh/rl/ppo/gae.html index e012077d..4f24233b 100644 --- a/docs/zh/rl/ppo/gae.html +++ b/docs/zh/rl/ppo/gae.html @@ -202,7 +202,6 @@ diff --git a/docs/zh/rl/ppo/index.html b/docs/zh/rl/ppo/index.html index fc0eb628..f9a24ebd 100644 --- a/docs/zh/rl/ppo/index.html +++ b/docs/zh/rl/ppo/index.html @@ -190,7 +190,6 @@ diff --git a/docs/zh/rl/ppo/readme.html b/docs/zh/rl/ppo/readme.html index bed2acad..bb068b90 100644 --- a/docs/zh/rl/ppo/readme.html +++ b/docs/zh/rl/ppo/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/sampling/experiment.html b/docs/zh/sampling/experiment.html index 45d0cd00..fe97ba1b 100644 --- a/docs/zh/sampling/experiment.html +++ b/docs/zh/sampling/experiment.html @@ -371,7 +371,6 @@ diff --git a/docs/zh/sampling/experiment_tiny.html b/docs/zh/sampling/experiment_tiny.html index 865c8ba7..ff0fc11e 100644 --- a/docs/zh/sampling/experiment_tiny.html +++ b/docs/zh/sampling/experiment_tiny.html @@ -250,7 +250,6 @@ diff --git a/docs/zh/sampling/greedy.html b/docs/zh/sampling/greedy.html index a370d454..918dca8b 100644 --- a/docs/zh/sampling/greedy.html +++ b/docs/zh/sampling/greedy.html @@ -116,7 +116,6 @@ diff --git a/docs/zh/sampling/index.html b/docs/zh/sampling/index.html index 5772e6dd..074c8f18 100644 --- a/docs/zh/sampling/index.html +++ b/docs/zh/sampling/index.html @@ -121,7 +121,6 @@ diff --git a/docs/zh/sampling/nucleus.html b/docs/zh/sampling/nucleus.html index 31834b37..42af3237 100644 --- a/docs/zh/sampling/nucleus.html +++ b/docs/zh/sampling/nucleus.html @@ -260,7 +260,6 @@ diff --git a/docs/zh/sampling/temperature.html b/docs/zh/sampling/temperature.html index 1421f699..51ea1ed3 100644 --- a/docs/zh/sampling/temperature.html +++ b/docs/zh/sampling/temperature.html @@ -157,7 +157,6 @@ diff --git a/docs/zh/sampling/top_k.html b/docs/zh/sampling/top_k.html index 001369aa..7b7a8b6b 100644 --- a/docs/zh/sampling/top_k.html +++ b/docs/zh/sampling/top_k.html @@ -183,7 +183,6 @@ diff --git a/docs/zh/scaling/index.html b/docs/zh/scaling/index.html index d42f008e..063055c6 100644 --- a/docs/zh/scaling/index.html +++ b/docs/zh/scaling/index.html @@ -79,7 +79,6 @@ diff --git a/docs/zh/scaling/zero3/finetune_neox.html b/docs/zh/scaling/zero3/finetune_neox.html index 97e857e6..b3fc5ce6 100644 --- a/docs/zh/scaling/zero3/finetune_neox.html +++ b/docs/zh/scaling/zero3/finetune_neox.html @@ -378,7 +378,6 @@ diff --git a/docs/zh/scaling/zero3/index.html b/docs/zh/scaling/zero3/index.html index dc12c8da..f634cab5 100644 --- a/docs/zh/scaling/zero3/index.html +++ b/docs/zh/scaling/zero3/index.html @@ -1803,7 +1803,6 @@ diff --git a/docs/zh/sitemap.xml b/docs/zh/sitemap.xml index dd5beb16..e1d8e169 100644 --- a/docs/zh/sitemap.xml +++ b/docs/zh/sitemap.xml @@ -960,7 +960,7 @@ https://nn.labml.ai/transformers/rope/index.html - 2023-12-08T16:30:00+00:00 + 2024-06-20T16:30:00+00:00 1.00 @@ -974,7 +974,7 @@ https://nn.labml.ai/transformers/rope/value_pe/index.html - 2023-10-24T16:30:00+00:00 + 2024-06-20T16:30:00+00:00 1.00 diff --git a/docs/zh/sketch_rnn/index.html b/docs/zh/sketch_rnn/index.html index f662edcf..046f1b51 100644 --- a/docs/zh/sketch_rnn/index.html +++ b/docs/zh/sketch_rnn/index.html @@ -2187,7 +2187,6 @@ M1001 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/transformers/aft/experiment.html b/docs/zh/transformers/aft/experiment.html index 434b79cc..113e5f87 100644 --- a/docs/zh/transformers/aft/experiment.html +++ b/docs/zh/transformers/aft/experiment.html @@ -600,7 +600,6 @@ diff --git a/docs/zh/transformers/aft/index.html b/docs/zh/transformers/aft/index.html index 8ea21b13..a390d496 100644 --- a/docs/zh/transformers/aft/index.html +++ b/docs/zh/transformers/aft/index.html @@ -508,7 +508,6 @@ A@@

FT(类似于 MHA)首先将嵌

diff --git a/docs/zh/transformers/aft/readme.html b/docs/zh/transformers/aft/readme.html index 8c8606d2..c843bdd5 100644 --- a/docs/zh/transformers/aft/readme.html +++ b/docs/zh/transformers/aft/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/transformers/alibi/experiment.html b/docs/zh/transformers/alibi/experiment.html index 50a34971..e4e442ea 100644 --- a/docs/zh/transformers/alibi/experiment.html +++ b/docs/zh/transformers/alibi/experiment.html @@ -577,7 +577,6 @@ diff --git a/docs/zh/transformers/alibi/index.html b/docs/zh/transformers/alibi/index.html index 04fafaac..4b870635 100644 --- a/docs/zh/transformers/alibi/index.html +++ b/docs/zh/transformers/alibi/index.html @@ -593,7 +593,6 @@ M834 80h400000v40h-400000z">
Trending Research Papers labml.ai diff --git a/docs/zh/transformers/basic/autoregressive_experiment.html b/docs/zh/transformers/basic/autoregressive_experiment.html index 4d4587c5..f42afe73 100644 --- a/docs/zh/transformers/basic/autoregressive_experiment.html +++ b/docs/zh/transformers/basic/autoregressive_experiment.html @@ -574,7 +574,6 @@ diff --git a/docs/zh/transformers/basic/index.html b/docs/zh/transformers/basic/index.html index fa439d96..cc5fbb5a 100644 --- a/docs/zh/transformers/basic/index.html +++ b/docs/zh/transformers/basic/index.html @@ -67,7 +67,6 @@ diff --git a/docs/zh/transformers/basic/with_sophia.html b/docs/zh/transformers/basic/with_sophia.html index 91830a17..13ee658d 100644 --- a/docs/zh/transformers/basic/with_sophia.html +++ b/docs/zh/transformers/basic/with_sophia.html @@ -642,7 +642,6 @@ diff --git a/docs/zh/transformers/compressive/experiment.html b/docs/zh/transformers/compressive/experiment.html index 949be53a..d9cec70f 100644 --- a/docs/zh/transformers/compressive/experiment.html +++ b/docs/zh/transformers/compressive/experiment.html @@ -1389,7 +1389,6 @@ diff --git a/docs/zh/transformers/compressive/index.html b/docs/zh/transformers/compressive/index.html index aa8109e5..805d8167 100644 --- a/docs/zh/transformers/compressive/index.html +++ b/docs/zh/transformers/compressive/index.html @@ -988,7 +988,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/transformers/compressive/readme.html b/docs/zh/transformers/compressive/readme.html index 36e41f1f..cc97636f 100644 --- a/docs/zh/transformers/compressive/readme.html +++ b/docs/zh/transformers/compressive/readme.html @@ -88,7 +88,6 @@ diff --git a/docs/zh/transformers/configs.html b/docs/zh/transformers/configs.html index a7906b54..91013706 100644 --- a/docs/zh/transformers/configs.html +++ b/docs/zh/transformers/configs.html @@ -965,7 +965,6 @@ diff --git a/docs/zh/transformers/fast_weights/experiment.html b/docs/zh/transformers/fast_weights/experiment.html index 6926851a..88acb821 100644 --- a/docs/zh/transformers/fast_weights/experiment.html +++ b/docs/zh/transformers/fast_weights/experiment.html @@ -352,7 +352,6 @@ diff --git a/docs/zh/transformers/fast_weights/index.html b/docs/zh/transformers/fast_weights/index.html index 34d6a44f..83e912a4 100644 --- a/docs/zh/transformers/fast_weights/index.html +++ b/docs/zh/transformers/fast_weights/index.html @@ -813,7 +813,6 @@ diff --git a/docs/zh/transformers/fast_weights/readme.html b/docs/zh/transformers/fast_weights/readme.html index e6a1ef27..18a3e824 100644 --- a/docs/zh/transformers/fast_weights/readme.html +++ b/docs/zh/transformers/fast_weights/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/transformers/fast_weights/token_wise.html b/docs/zh/transformers/fast_weights/token_wise.html index 652741ec..79aeeccf 100644 --- a/docs/zh/transformers/fast_weights/token_wise.html +++ b/docs/zh/transformers/fast_weights/token_wise.html @@ -524,7 +524,6 @@ diff --git a/docs/zh/transformers/feed_forward.html b/docs/zh/transformers/feed_forward.html index c8ed8082..f663c74d 100644 --- a/docs/zh/transformers/feed_forward.html +++ b/docs/zh/transformers/feed_forward.html @@ -291,7 +291,6 @@ diff --git a/docs/zh/transformers/feedback/experiment.html b/docs/zh/transformers/feedback/experiment.html index a7113864..3229373d 100644 --- a/docs/zh/transformers/feedback/experiment.html +++ b/docs/zh/transformers/feedback/experiment.html @@ -401,7 +401,6 @@ diff --git a/docs/zh/transformers/feedback/index.html b/docs/zh/transformers/feedback/index.html index f9ebaf15..1d9103a0 100644 --- a/docs/zh/transformers/feedback/index.html +++ b/docs/zh/transformers/feedback/index.html @@ -1802,7 +1802,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/transformers/feedback/readme.html b/docs/zh/transformers/feedback/readme.html index 4325a38b..2a783772 100644 --- a/docs/zh/transformers/feedback/readme.html +++ b/docs/zh/transformers/feedback/readme.html @@ -87,7 +87,6 @@ diff --git a/docs/zh/transformers/fnet/experiment.html b/docs/zh/transformers/fnet/experiment.html index 45b9a77c..b0ec2685 100644 --- a/docs/zh/transformers/fnet/experiment.html +++ b/docs/zh/transformers/fnet/experiment.html @@ -511,7 +511,6 @@ diff --git a/docs/zh/transformers/fnet/index.html b/docs/zh/transformers/fnet/index.html index 2de09f8b..739dbb50 100644 --- a/docs/zh/transformers/fnet/index.html +++ b/docs/zh/transformers/fnet/index.html @@ -196,7 +196,6 @@ diff --git a/docs/zh/transformers/fnet/readme.html b/docs/zh/transformers/fnet/readme.html index 4a630224..89a1c213 100644 --- a/docs/zh/transformers/fnet/readme.html +++ b/docs/zh/transformers/fnet/readme.html @@ -81,7 +81,6 @@ diff --git a/docs/zh/transformers/glu_variants/experiment.html b/docs/zh/transformers/glu_variants/experiment.html index be91a292..ecf2431a 100644 --- a/docs/zh/transformers/glu_variants/experiment.html +++ b/docs/zh/transformers/glu_variants/experiment.html @@ -440,7 +440,6 @@ diff --git a/docs/zh/transformers/glu_variants/index.html b/docs/zh/transformers/glu_variants/index.html index 4bd67394..22dfd647 100644 --- a/docs/zh/transformers/glu_variants/index.html +++ b/docs/zh/transformers/glu_variants/index.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/transformers/glu_variants/simple.html b/docs/zh/transformers/glu_variants/simple.html index 7af37c9a..32339c92 100644 --- a/docs/zh/transformers/glu_variants/simple.html +++ b/docs/zh/transformers/glu_variants/simple.html @@ -1153,7 +1153,6 @@ diff --git a/docs/zh/transformers/gmlp/experiment.html b/docs/zh/transformers/gmlp/experiment.html index 179e30a7..edc18f52 100644 --- a/docs/zh/transformers/gmlp/experiment.html +++ b/docs/zh/transformers/gmlp/experiment.html @@ -442,7 +442,6 @@ diff --git a/docs/zh/transformers/gmlp/index.html b/docs/zh/transformers/gmlp/index.html index 48a28e56..77006555 100644 --- a/docs/zh/transformers/gmlp/index.html +++ b/docs/zh/transformers/gmlp/index.html @@ -523,7 +523,6 @@ is 是形状的布尔掩码 diff --git a/docs/zh/transformers/gmlp/readme.html b/docs/zh/transformers/gmlp/readme.html index 2145db62..e7b7e414 100644 --- a/docs/zh/transformers/gmlp/readme.html +++ b/docs/zh/transformers/gmlp/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/transformers/gpt/index.html b/docs/zh/transformers/gpt/index.html index 0f6b0b4e..ec65f3b9 100644 --- a/docs/zh/transformers/gpt/index.html +++ b/docs/zh/transformers/gpt/index.html @@ -861,7 +861,6 @@ diff --git a/docs/zh/transformers/hour_glass/experiment.html b/docs/zh/transformers/hour_glass/experiment.html index c6be9fb4..ed4965d0 100644 --- a/docs/zh/transformers/hour_glass/experiment.html +++ b/docs/zh/transformers/hour_glass/experiment.html @@ -633,7 +633,6 @@ diff --git a/docs/zh/transformers/hour_glass/index.html b/docs/zh/transformers/hour_glass/index.html index 90bbe32f..09e7c1a0 100644 --- a/docs/zh/transformers/hour_glass/index.html +++ b/docs/zh/transformers/hour_glass/index.html @@ -885,7 +885,6 @@ diff --git a/docs/zh/transformers/index.html b/docs/zh/transformers/index.html index 4b6b7018..43f34b9e 100644 --- a/docs/zh/transformers/index.html +++ b/docs/zh/transformers/index.html @@ -124,7 +124,6 @@ diff --git a/docs/zh/transformers/knn/build_index.html b/docs/zh/transformers/knn/build_index.html index 0af56b3f..3d023f81 100644 --- a/docs/zh/transformers/knn/build_index.html +++ b/docs/zh/transformers/knn/build_index.html @@ -607,7 +607,6 @@ diff --git a/docs/zh/transformers/knn/eval_knn.html b/docs/zh/transformers/knn/eval_knn.html index ec23bc6e..cf52f786 100644 --- a/docs/zh/transformers/knn/eval_knn.html +++ b/docs/zh/transformers/knn/eval_knn.html @@ -575,7 +575,6 @@ diff --git a/docs/zh/transformers/knn/index.html b/docs/zh/transformers/knn/index.html index d7bc013d..97800b10 100644 --- a/docs/zh/transformers/knn/index.html +++ b/docs/zh/transformers/knn/index.html @@ -90,7 +90,6 @@ diff --git a/docs/zh/transformers/knn/train_model.html b/docs/zh/transformers/knn/train_model.html index 863471bf..ce555068 100644 --- a/docs/zh/transformers/knn/train_model.html +++ b/docs/zh/transformers/knn/train_model.html @@ -491,7 +491,6 @@ diff --git a/docs/zh/transformers/label_smoothing_loss.html b/docs/zh/transformers/label_smoothing_loss.html index 5fe16997..cbafc90c 100644 --- a/docs/zh/transformers/label_smoothing_loss.html +++ b/docs/zh/transformers/label_smoothing_loss.html @@ -199,7 +199,6 @@ diff --git a/docs/zh/transformers/mha.html b/docs/zh/transformers/mha.html index b087e548..4fce0daf 100644 --- a/docs/zh/transformers/mha.html +++ b/docs/zh/transformers/mha.html @@ -683,7 +683,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/transformers/mlm/experiment.html b/docs/zh/transformers/mlm/experiment.html index 5829c96a..566c12df 100644 --- a/docs/zh/transformers/mlm/experiment.html +++ b/docs/zh/transformers/mlm/experiment.html @@ -1160,7 +1160,6 @@ diff --git a/docs/zh/transformers/mlm/index.html b/docs/zh/transformers/mlm/index.html index bb35ef29..6ed34ab4 100644 --- a/docs/zh/transformers/mlm/index.html +++ b/docs/zh/transformers/mlm/index.html @@ -335,7 +335,6 @@ diff --git a/docs/zh/transformers/mlm/readme.html b/docs/zh/transformers/mlm/readme.html index f044e15b..319cbec1 100644 --- a/docs/zh/transformers/mlm/readme.html +++ b/docs/zh/transformers/mlm/readme.html @@ -106,7 +106,6 @@ diff --git a/docs/zh/transformers/mlp_mixer/experiment.html b/docs/zh/transformers/mlp_mixer/experiment.html index 505de1b2..8b241908 100644 --- a/docs/zh/transformers/mlp_mixer/experiment.html +++ b/docs/zh/transformers/mlp_mixer/experiment.html @@ -431,7 +431,6 @@ diff --git a/docs/zh/transformers/mlp_mixer/index.html b/docs/zh/transformers/mlp_mixer/index.html index 3c359dbd..0a0b0a64 100644 --- a/docs/zh/transformers/mlp_mixer/index.html +++ b/docs/zh/transformers/mlp_mixer/index.html @@ -228,7 +228,6 @@ diff --git a/docs/zh/transformers/mlp_mixer/readme.html b/docs/zh/transformers/mlp_mixer/readme.html index 7a3911f5..48691992 100644 --- a/docs/zh/transformers/mlp_mixer/readme.html +++ b/docs/zh/transformers/mlp_mixer/readme.html @@ -83,7 +83,6 @@ diff --git a/docs/zh/transformers/models.html b/docs/zh/transformers/models.html index 60ddb541..721b93e1 100644 --- a/docs/zh/transformers/models.html +++ b/docs/zh/transformers/models.html @@ -704,7 +704,6 @@ diff --git a/docs/zh/transformers/positional_encoding.html b/docs/zh/transformers/positional_encoding.html index 0e501c97..4d14d992 100644 --- a/docs/zh/transformers/positional_encoding.html +++ b/docs/zh/transformers/positional_encoding.html @@ -246,7 +246,6 @@ diff --git a/docs/zh/transformers/primer_ez/efficient.html b/docs/zh/transformers/primer_ez/efficient.html index dd15e4c5..517fd405 100644 --- a/docs/zh/transformers/primer_ez/efficient.html +++ b/docs/zh/transformers/primer_ez/efficient.html @@ -213,7 +213,6 @@ diff --git a/docs/zh/transformers/primer_ez/experiment.html b/docs/zh/transformers/primer_ez/experiment.html index 47f2fcfe..3e8ed1a2 100644 --- a/docs/zh/transformers/primer_ez/experiment.html +++ b/docs/zh/transformers/primer_ez/experiment.html @@ -434,7 +434,6 @@ diff --git a/docs/zh/transformers/primer_ez/index.html b/docs/zh/transformers/primer_ez/index.html index eadafaa2..df022614 100644 --- a/docs/zh/transformers/primer_ez/index.html +++ b/docs/zh/transformers/primer_ez/index.html @@ -368,7 +368,6 @@ diff --git a/docs/zh/transformers/primer_ez/readme.html b/docs/zh/transformers/primer_ez/readme.html index a50f8dbe..985d5ece 100644 --- a/docs/zh/transformers/primer_ez/readme.html +++ b/docs/zh/transformers/primer_ez/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/zh/transformers/primer_ez/variations.html b/docs/zh/transformers/primer_ez/variations.html index 2adf3f15..59d90c25 100644 --- a/docs/zh/transformers/primer_ez/variations.html +++ b/docs/zh/transformers/primer_ez/variations.html @@ -502,7 +502,6 @@ diff --git a/docs/zh/transformers/relative_mha.html b/docs/zh/transformers/relative_mha.html index b2eb733e..3c08c520 100644 --- a/docs/zh/transformers/relative_mha.html +++ b/docs/zh/transformers/relative_mha.html @@ -67,7 +67,6 @@ diff --git a/docs/zh/transformers/retro/bert_embeddings.html b/docs/zh/transformers/retro/bert_embeddings.html index d3b62209..362d79e7 100644 --- a/docs/zh/transformers/retro/bert_embeddings.html +++ b/docs/zh/transformers/retro/bert_embeddings.html @@ -474,7 +474,6 @@ diff --git a/docs/zh/transformers/retro/database.html b/docs/zh/transformers/retro/database.html index 23aa8f51..0fed4784 100644 --- a/docs/zh/transformers/retro/database.html +++ b/docs/zh/transformers/retro/database.html @@ -488,7 +488,6 @@ diff --git a/docs/zh/transformers/retro/dataset.html b/docs/zh/transformers/retro/dataset.html index 5a27d0fa..44c61a49 100644 --- a/docs/zh/transformers/retro/dataset.html +++ b/docs/zh/transformers/retro/dataset.html @@ -483,7 +483,6 @@ diff --git a/docs/zh/transformers/retro/index.html b/docs/zh/transformers/retro/index.html index 68bf111c..e75ec33d 100644 --- a/docs/zh/transformers/retro/index.html +++ b/docs/zh/transformers/retro/index.html @@ -89,7 +89,6 @@ diff --git a/docs/zh/transformers/retro/model.html b/docs/zh/transformers/retro/model.html index bfee6dd3..1c229059 100644 --- a/docs/zh/transformers/retro/model.html +++ b/docs/zh/transformers/retro/model.html @@ -2008,7 +2008,6 @@ is 是形状的输入令牌嵌入Trending Research Papers labml.ai diff --git a/docs/zh/transformers/retro/train.html b/docs/zh/transformers/retro/train.html index 4da24132..bb244fe0 100644 --- a/docs/zh/transformers/retro/train.html +++ b/docs/zh/transformers/retro/train.html @@ -808,7 +808,6 @@ diff --git a/docs/zh/transformers/rope/experiment.html b/docs/zh/transformers/rope/experiment.html index 2eb3c281..79642660 100644 --- a/docs/zh/transformers/rope/experiment.html +++ b/docs/zh/transformers/rope/experiment.html @@ -399,7 +399,6 @@ diff --git a/docs/zh/transformers/rope/index.html b/docs/zh/transformers/rope/index.html index 978153c9..1e27d432 100644 --- a/docs/zh/transformers/rope/index.html +++ b/docs/zh/transformers/rope/index.html @@ -445,7 +445,6 @@ diff --git a/docs/zh/transformers/rope/value_pe/arithmetic_experiment.html b/docs/zh/transformers/rope/value_pe/arithmetic_experiment.html index 37fd35c6..308eead0 100644 --- a/docs/zh/transformers/rope/value_pe/arithmetic_experiment.html +++ b/docs/zh/transformers/rope/value_pe/arithmetic_experiment.html @@ -357,7 +357,6 @@ diff --git a/docs/zh/transformers/rope/value_pe/experiment.html b/docs/zh/transformers/rope/value_pe/experiment.html index a9dc766e..6cea9689 100644 --- a/docs/zh/transformers/rope/value_pe/experiment.html +++ b/docs/zh/transformers/rope/value_pe/experiment.html @@ -407,7 +407,6 @@ diff --git a/docs/zh/transformers/rope/value_pe/index.html b/docs/zh/transformers/rope/value_pe/index.html index b533974b..88c851a4 100644 --- a/docs/zh/transformers/rope/value_pe/index.html +++ b/docs/zh/transformers/rope/value_pe/index.html @@ -464,7 +464,6 @@ M834 80h400000v40h-400000z">Trending Research Papers labml.ai diff --git a/docs/zh/transformers/switch/experiment.html b/docs/zh/transformers/switch/experiment.html index 1c7e6f44..8580465e 100644 --- a/docs/zh/transformers/switch/experiment.html +++ b/docs/zh/transformers/switch/experiment.html @@ -837,7 +837,6 @@ diff --git a/docs/zh/transformers/switch/index.html b/docs/zh/transformers/switch/index.html index bd2ce0c1..ea74c3dc 100644 --- a/docs/zh/transformers/switch/index.html +++ b/docs/zh/transformers/switch/index.html @@ -713,7 +713,6 @@ FFN 中的辍学概率是多少 diff --git a/docs/zh/transformers/switch/readme.html b/docs/zh/transformers/switch/readme.html index 2ea3a695..fe05cc65 100644 --- a/docs/zh/transformers/switch/readme.html +++ b/docs/zh/transformers/switch/readme.html @@ -84,7 +84,6 @@ diff --git a/docs/zh/transformers/utils.html b/docs/zh/transformers/utils.html index 0d0d4e04..f4cdcbf4 100644 --- a/docs/zh/transformers/utils.html +++ b/docs/zh/transformers/utils.html @@ -119,7 +119,6 @@ diff --git a/docs/zh/transformers/vit/experiment.html b/docs/zh/transformers/vit/experiment.html index a187531f..1ae0fbf3 100644 --- a/docs/zh/transformers/vit/experiment.html +++ b/docs/zh/transformers/vit/experiment.html @@ -368,7 +368,6 @@ diff --git a/docs/zh/transformers/vit/index.html b/docs/zh/transformers/vit/index.html index 73723e70..157f096a 100644 --- a/docs/zh/transformers/vit/index.html +++ b/docs/zh/transformers/vit/index.html @@ -654,7 +654,6 @@ diff --git a/docs/zh/transformers/vit/readme.html b/docs/zh/transformers/vit/readme.html index 13fbec06..50a8e5e9 100644 --- a/docs/zh/transformers/vit/readme.html +++ b/docs/zh/transformers/vit/readme.html @@ -86,7 +86,6 @@ diff --git a/docs/zh/transformers/xl/experiment.html b/docs/zh/transformers/xl/experiment.html index c47ce55f..9be8136c 100644 --- a/docs/zh/transformers/xl/experiment.html +++ b/docs/zh/transformers/xl/experiment.html @@ -1043,7 +1043,6 @@ diff --git a/docs/zh/transformers/xl/index.html b/docs/zh/transformers/xl/index.html index 3d7e170f..692a0c29 100644 --- a/docs/zh/transformers/xl/index.html +++ b/docs/zh/transformers/xl/index.html @@ -447,7 +447,6 @@ diff --git a/docs/zh/transformers/xl/readme.html b/docs/zh/transformers/xl/readme.html index ef24d604..3c3c51e4 100644 --- a/docs/zh/transformers/xl/readme.html +++ b/docs/zh/transformers/xl/readme.html @@ -85,7 +85,6 @@ diff --git a/docs/zh/transformers/xl/relative_mha.html b/docs/zh/transformers/xl/relative_mha.html index d68687e6..80de5590 100644 --- a/docs/zh/transformers/xl/relative_mha.html +++ b/docs/zh/transformers/xl/relative_mha.html @@ -373,7 +373,6 @@ diff --git a/docs/zh/uncertainty/evidence/experiment.html b/docs/zh/uncertainty/evidence/experiment.html index 147921bf..421393ec 100644 --- a/docs/zh/uncertainty/evidence/experiment.html +++ b/docs/zh/uncertainty/evidence/experiment.html @@ -863,7 +863,6 @@ diff --git a/docs/zh/uncertainty/evidence/index.html b/docs/zh/uncertainty/evidence/index.html index f275d130..070bab43 100644 --- a/docs/zh/uncertainty/evidence/index.html +++ b/docs/zh/uncertainty/evidence/index.html @@ -679,7 +679,6 @@ diff --git a/docs/zh/uncertainty/evidence/readme.html b/docs/zh/uncertainty/evidence/readme.html index 9e3e30f7..69bdc116 100644 --- a/docs/zh/uncertainty/evidence/readme.html +++ b/docs/zh/uncertainty/evidence/readme.html @@ -82,7 +82,6 @@ diff --git a/docs/zh/uncertainty/index.html b/docs/zh/uncertainty/index.html index cd5c86c3..5799a860 100644 --- a/docs/zh/uncertainty/index.html +++ b/docs/zh/uncertainty/index.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/uncertainty/readme.html b/docs/zh/uncertainty/readme.html index 5e7b7d88..bafaf1f0 100644 --- a/docs/zh/uncertainty/readme.html +++ b/docs/zh/uncertainty/readme.html @@ -80,7 +80,6 @@ diff --git a/docs/zh/unet/carvana.html b/docs/zh/unet/carvana.html index 9e3f9b1f..4794a436 100644 --- a/docs/zh/unet/carvana.html +++ b/docs/zh/unet/carvana.html @@ -301,7 +301,6 @@ diff --git a/docs/zh/unet/experiment.html b/docs/zh/unet/experiment.html index 9448d863..88f8dce7 100644 --- a/docs/zh/unet/experiment.html +++ b/docs/zh/unet/experiment.html @@ -685,7 +685,6 @@ diff --git a/docs/zh/unet/index.html b/docs/zh/unet/index.html index 2eb6ef4f..6b0ecb92 100644 --- a/docs/zh/unet/index.html +++ b/docs/zh/unet/index.html @@ -621,7 +621,6 @@ diff --git a/docs/zh/utils/index.html b/docs/zh/utils/index.html index 6382c446..a95a4115 100644 --- a/docs/zh/utils/index.html +++ b/docs/zh/utils/index.html @@ -242,7 +242,6 @@ diff --git a/docs/zh/utils/tokenizer.html b/docs/zh/utils/tokenizer.html index d07bb64e..45188780 100644 --- a/docs/zh/utils/tokenizer.html +++ b/docs/zh/utils/tokenizer.html @@ -190,7 +190,6 @@