Merge pull request #6 from THUDM/finer-attn-hooks

SwissArmyTransformer/arguments.py

SwissArmyTransformer/data_utils/configure_data.py

SwissArmyTransformer/data_utils/datasets.py

SwissArmyTransformer/generation/autoregressive_sampling.py

SwissArmyTransformer/model/__init__.py

SwissArmyTransformer/model/base_model.py

SwissArmyTransformer/model/cached_autoregressive_model.py

SwissArmyTransformer/model/common_layers.py

SwissArmyTransformer/model/cuda2d_model.py

SwissArmyTransformer/model/encoder_decoder_model.py

SwissArmyTransformer/model/finetune/__init__.py

SwissArmyTransformer/model/finetune/mlp_head.py

SwissArmyTransformer/model/finetune/prompt_tuning.py

SwissArmyTransformer/model/mixins.py

SwissArmyTransformer/model/t5_model.py

SwissArmyTransformer/mpu/layers.py

SwissArmyTransformer/mpu/transformer.py

SwissArmyTransformer/mpu/utils.py

SwissArmyTransformer/tokenization/__init__.py

SwissArmyTransformer/tokenization/cogview/sp_tokenizer.py