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">