├── .gitignore ├── LICENSE ├── README.md ├── pretrain ├── .gitignore ├── MANIFEST.in ├── Megatron.LICENSE ├── README.md ├── examples │ ├── evaluate_zeroshot_gpt.sh │ ├── finetune_mnli_distributed.sh │ ├── finetune_race_distributed.sh │ ├── generate_text.sh │ ├── merge_mp_bert.sh │ ├── pretrain_bert.sh │ ├── pretrain_bert_distributed.sh │ ├── pretrain_bert_distributed_with_mp.sh │ ├── pretrain_gpt.sh │ ├── pretrain_gpt3_175B.sh │ ├── pretrain_gpt_distributed.sh │ ├── pretrain_gpt_distributed_with_mp.sh │ ├── pretrain_tape.sh │ └── pretrain_tape_distributed.sh ├── images │ ├── Makefile │ ├── cases_jan2021.png │ ├── scaling.png │ └── tables.tex ├── megatron │ ├── __init__.py │ ├── arguments.py │ ├── checkpointing.py │ ├── data │ │ ├── Makefile │ │ ├── __init__.py │ │ ├── bert_dataset.py │ │ ├── blendable_dataset.py │ │ ├── data_loaders.py │ │ ├── dataset_utils.py │ │ ├── gpt_dataset.py │ │ ├── helpers.cpp │ │ ├── ict_dataset.py │ │ ├── indexed_dataset.py │ │ ├── realm_dataset_utils.py │ │ ├── realm_index.py │ │ ├── tape_dataset.py │ │ └── test │ │ │ ├── test_indexed_dataset.py │ │ │ └── test_preprocess_data.sh │ ├── fp16_deprecated │ │ └── loss_scaler.py │ ├── fused_kernels │ │ ├── __init__.py │ │ ├── compat.h │ │ ├── layer_norm_cuda.cpp │ │ ├── layer_norm_cuda_kernel.cu │ │ ├── scaled_masked_softmax.cpp │ │ ├── scaled_masked_softmax.h │ │ ├── scaled_masked_softmax_cuda.cu │ │ ├── scaled_upper_triang_masked_softmax.cpp │ │ ├── scaled_upper_triang_masked_softmax.h │ │ ├── scaled_upper_triang_masked_softmax_cuda.cu │ │ └── type_shim.h │ ├── global_vars.py │ ├── indexer.py │ ├── initialize.py │ ├── learning_rates.py │ ├── memory.py │ ├── microbatches.py │ ├── model │ │ ├── __init__.py │ │ ├── bert_model.py │ │ ├── classification.py │ │ ├── distributed.py │ │ ├── fused_bias_gelu.py │ │ ├── fused_layer_norm.py │ │ ├── fused_softmax.py │ │ ├── gpt_model.py │ │ ├── language_model.py │ │ ├── module.py │ │ ├── multiple_choice.py │ │ ├── realm_model.py │ │ ├── token_classification.py │ │ ├── token_pair_classification.py │ │ ├── transformer.py │ │ └── utils.py │ ├── mpu │ │ ├── __init__.py │ │ ├── cross_entropy.py │ │ ├── data.py │ │ ├── initialize.py │ │ ├── layers.py │ │ ├── mappings.py │ │ ├── random.py │ │ ├── tests │ │ │ ├── __init__.py │ │ │ ├── commons.py │ │ │ ├── test_cross_entropy.py │ │ │ ├── test_data.py │ │ │ ├── test_initialize.py │ │ │ ├── test_layers.py │ │ │ └── test_random.py │ │ └── utils.py │ ├── optimizer │ │ ├── __init__.py │ │ ├── clip_grads.py │ │ ├── grad_scaler.py │ │ └── optimizer.py │ ├── package_info.py │ ├── text_generation_utils.py │ ├── tokenizer │ │ ├── __init__.py │ │ ├── bert_tokenization.py │ │ ├── gpt2_tokenization.py │ │ └── tokenizer.py │ ├── training.py │ └── utils.py ├── pretrain_tape.py ├── pretrain_tools │ ├── README.md │ ├── mpirun_hidden1024_layer16_head16.sh │ └── pretrain_tape_distributed_hidden1024_layer16_head16.sh ├── protein_tools │ ├── README.md │ ├── iupac_vocab.txt │ ├── lmdb2tab.py │ ├── pfam2json.sh │ └── preprocess_tape.sh ├── requirements.txt ├── setup.py ├── tasks │ ├── data_utils.py │ ├── ensemble_classifier.py │ ├── eval_utils.py │ ├── finetune_utils.py │ ├── glue │ │ ├── data.py │ │ ├── finetune.py │ │ ├── mnli.py │ │ └── qqp.py │ ├── main.py │ ├── protein │ │ ├── contact_prediction.py │ │ ├── data.py │ │ ├── eval_utils.py │ │ ├── finetune.py │ │ ├── finetune_utils.py │ │ ├── fluorescence.py │ │ ├── remote_homology.py │ │ ├── secondary_structure.py │ │ └── stability.py │ ├── race │ │ ├── data.py │ │ └── finetune.py │ └── zeroshot_gpt2 │ │ ├── datasets.py │ │ ├── detokenizer.py │ │ └── evaluate.py └── tools │ ├── create_doc_index.py │ ├── generate_samples_gpt.py │ ├── linter.py │ ├── merge_mp_partitions.py │ ├── openwebtext │ ├── README.md │ ├── blacklist_urls.py │ ├── cleanup_dataset.py │ ├── find_duplicates.py │ ├── group_duplicate_url.py │ ├── merge_jsons.py │ └── remove_group_duplicates.py │ └── preprocess_data.py └── tape ├── .gitignore ├── MANIFEST.in ├── README.md ├── TAPE.LICENSE ├── clean_checkpoints.sh ├── cleanup_results.sh ├── conda_env ├── base.yaml └── torch1.7.yaml ├── config ├── resnet_config.json ├── transformer_config.json └── transformer_tiny_config.json ├── converter ├── config.json └── megatron-converter.py ├── data_refs.bib ├── deprecated ├── converter.py └── modeling_bert.py ├── download_data.sh ├── download_data_aws.sh ├── environment.yml ├── examples ├── adding_model.py └── adding_task.py ├── gridsearch_config.json ├── mypy.ini ├── requirements.txt ├── scripts ├── fix_lmdb.py ├── generate_plots.py ├── lmdb_to_fasta.py ├── shells │ ├── activate_base.sh │ ├── activate_torch1.7.sh │ ├── megatron-tape-generator.sh │ ├── para.sh │ └── test.sh ├── tfrecord_to_json.py └── tfrecord_to_lmdb.py ├── setup.py ├── tape ├── __init__.py ├── datasets.py ├── errors.py ├── main.py ├── metrics.py ├── models │ ├── __init__.py │ ├── file_utils.py │ ├── modeling_bert.py │ ├── modeling_lstm.py │ ├── modeling_onehot.py │ ├── modeling_resnet.py │ ├── modeling_trrosetta.py │ ├── modeling_unirep.py │ └── modeling_utils.py ├── optimization.py ├── registry.py ├── tokenizers.py ├── training.py ├── utils │ ├── __init__.py │ ├── _sampler.py │ ├── distributed_utils.py │ ├── setup_utils.py │ └── utils.py └── visualization.py ├── tape_eval.py ├── tape_train.py ├── tests ├── test_basic.py └── test_forceDownload.py └── tox.ini /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/README.md -------------------------------------------------------------------------------- /pretrain/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/.gitignore -------------------------------------------------------------------------------- /pretrain/MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/MANIFEST.in -------------------------------------------------------------------------------- /pretrain/Megatron.LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/Megatron.LICENSE -------------------------------------------------------------------------------- /pretrain/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/README.md -------------------------------------------------------------------------------- /pretrain/examples/evaluate_zeroshot_gpt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/evaluate_zeroshot_gpt.sh -------------------------------------------------------------------------------- /pretrain/examples/finetune_mnli_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/finetune_mnli_distributed.sh -------------------------------------------------------------------------------- /pretrain/examples/finetune_race_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/finetune_race_distributed.sh -------------------------------------------------------------------------------- /pretrain/examples/generate_text.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/generate_text.sh -------------------------------------------------------------------------------- /pretrain/examples/merge_mp_bert.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/merge_mp_bert.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_bert.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_bert.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_bert_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_bert_distributed.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_bert_distributed_with_mp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_bert_distributed_with_mp.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_gpt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_gpt.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_gpt3_175B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_gpt3_175B.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_gpt_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_gpt_distributed.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_gpt_distributed_with_mp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_gpt_distributed_with_mp.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_tape.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_tape.sh -------------------------------------------------------------------------------- /pretrain/examples/pretrain_tape_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/examples/pretrain_tape_distributed.sh -------------------------------------------------------------------------------- /pretrain/images/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/images/Makefile -------------------------------------------------------------------------------- /pretrain/images/cases_jan2021.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/images/cases_jan2021.png -------------------------------------------------------------------------------- /pretrain/images/scaling.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/images/scaling.png -------------------------------------------------------------------------------- /pretrain/images/tables.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/images/tables.tex -------------------------------------------------------------------------------- /pretrain/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/arguments.py -------------------------------------------------------------------------------- /pretrain/megatron/checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/checkpointing.py -------------------------------------------------------------------------------- /pretrain/megatron/data/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/Makefile -------------------------------------------------------------------------------- /pretrain/megatron/data/__init__.py: -------------------------------------------------------------------------------- 1 | from . import indexed_dataset 2 | -------------------------------------------------------------------------------- /pretrain/megatron/data/bert_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/bert_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/blendable_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/blendable_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/data_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/data_loaders.py -------------------------------------------------------------------------------- /pretrain/megatron/data/dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/dataset_utils.py -------------------------------------------------------------------------------- /pretrain/megatron/data/gpt_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/gpt_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/helpers.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/helpers.cpp -------------------------------------------------------------------------------- /pretrain/megatron/data/ict_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/ict_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/indexed_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/indexed_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/realm_dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/realm_dataset_utils.py -------------------------------------------------------------------------------- /pretrain/megatron/data/realm_index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/realm_index.py -------------------------------------------------------------------------------- /pretrain/megatron/data/tape_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/tape_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/test/test_indexed_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/test/test_indexed_dataset.py -------------------------------------------------------------------------------- /pretrain/megatron/data/test/test_preprocess_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/data/test/test_preprocess_data.sh -------------------------------------------------------------------------------- /pretrain/megatron/fp16_deprecated/loss_scaler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fp16_deprecated/loss_scaler.py -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/compat.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/compat.h -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/layer_norm_cuda.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/layer_norm_cuda.cpp -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/layer_norm_cuda_kernel.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/layer_norm_cuda_kernel.cu -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_masked_softmax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_masked_softmax.cpp -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_masked_softmax.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_masked_softmax.h -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_masked_softmax_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -------------------------------------------------------------------------------- /pretrain/megatron/fused_kernels/type_shim.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/fused_kernels/type_shim.h -------------------------------------------------------------------------------- /pretrain/megatron/global_vars.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/global_vars.py -------------------------------------------------------------------------------- /pretrain/megatron/indexer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/indexer.py -------------------------------------------------------------------------------- /pretrain/megatron/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/initialize.py -------------------------------------------------------------------------------- /pretrain/megatron/learning_rates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/learning_rates.py -------------------------------------------------------------------------------- /pretrain/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/memory.py -------------------------------------------------------------------------------- /pretrain/megatron/microbatches.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/microbatches.py -------------------------------------------------------------------------------- /pretrain/megatron/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/model/bert_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/bert_model.py -------------------------------------------------------------------------------- /pretrain/megatron/model/classification.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/classification.py -------------------------------------------------------------------------------- /pretrain/megatron/model/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/distributed.py -------------------------------------------------------------------------------- /pretrain/megatron/model/fused_bias_gelu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/fused_bias_gelu.py -------------------------------------------------------------------------------- /pretrain/megatron/model/fused_layer_norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/fused_layer_norm.py -------------------------------------------------------------------------------- /pretrain/megatron/model/fused_softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/fused_softmax.py -------------------------------------------------------------------------------- /pretrain/megatron/model/gpt_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/gpt_model.py -------------------------------------------------------------------------------- /pretrain/megatron/model/language_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/language_model.py -------------------------------------------------------------------------------- /pretrain/megatron/model/module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/module.py -------------------------------------------------------------------------------- /pretrain/megatron/model/multiple_choice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/multiple_choice.py -------------------------------------------------------------------------------- /pretrain/megatron/model/realm_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/realm_model.py -------------------------------------------------------------------------------- /pretrain/megatron/model/token_classification.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/token_classification.py -------------------------------------------------------------------------------- /pretrain/megatron/model/token_pair_classification.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/token_pair_classification.py -------------------------------------------------------------------------------- /pretrain/megatron/model/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/transformer.py -------------------------------------------------------------------------------- /pretrain/megatron/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/model/utils.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/cross_entropy.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/data.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/initialize.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/layers.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/mappings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/mappings.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/random.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/commons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/commons.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/test_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/test_cross_entropy.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/test_data.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/test_initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/test_initialize.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/test_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/test_layers.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/tests/test_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/tests/test_random.py -------------------------------------------------------------------------------- /pretrain/megatron/mpu/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/mpu/utils.py -------------------------------------------------------------------------------- /pretrain/megatron/optimizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/optimizer/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/optimizer/clip_grads.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/optimizer/clip_grads.py -------------------------------------------------------------------------------- /pretrain/megatron/optimizer/grad_scaler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/optimizer/grad_scaler.py -------------------------------------------------------------------------------- /pretrain/megatron/optimizer/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/optimizer/optimizer.py -------------------------------------------------------------------------------- /pretrain/megatron/package_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/package_info.py -------------------------------------------------------------------------------- /pretrain/megatron/text_generation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/text_generation_utils.py -------------------------------------------------------------------------------- /pretrain/megatron/tokenizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/tokenizer/__init__.py -------------------------------------------------------------------------------- /pretrain/megatron/tokenizer/bert_tokenization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/tokenizer/bert_tokenization.py -------------------------------------------------------------------------------- /pretrain/megatron/tokenizer/gpt2_tokenization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/tokenizer/gpt2_tokenization.py -------------------------------------------------------------------------------- /pretrain/megatron/tokenizer/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/tokenizer/tokenizer.py -------------------------------------------------------------------------------- /pretrain/megatron/training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/training.py -------------------------------------------------------------------------------- /pretrain/megatron/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/megatron/utils.py -------------------------------------------------------------------------------- /pretrain/pretrain_tape.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/pretrain_tape.py -------------------------------------------------------------------------------- /pretrain/pretrain_tools/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/pretrain_tools/README.md -------------------------------------------------------------------------------- /pretrain/pretrain_tools/mpirun_hidden1024_layer16_head16.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/pretrain_tools/mpirun_hidden1024_layer16_head16.sh -------------------------------------------------------------------------------- /pretrain/pretrain_tools/pretrain_tape_distributed_hidden1024_layer16_head16.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/pretrain_tools/pretrain_tape_distributed_hidden1024_layer16_head16.sh -------------------------------------------------------------------------------- /pretrain/protein_tools/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/protein_tools/README.md -------------------------------------------------------------------------------- /pretrain/protein_tools/iupac_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/protein_tools/iupac_vocab.txt -------------------------------------------------------------------------------- /pretrain/protein_tools/lmdb2tab.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/protein_tools/lmdb2tab.py -------------------------------------------------------------------------------- /pretrain/protein_tools/pfam2json.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/protein_tools/pfam2json.sh -------------------------------------------------------------------------------- /pretrain/protein_tools/preprocess_tape.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/protein_tools/preprocess_tape.sh -------------------------------------------------------------------------------- /pretrain/requirements.txt: -------------------------------------------------------------------------------- 1 | pybind11 2 | torch 3 | six 4 | regex 5 | numpy 6 | -------------------------------------------------------------------------------- /pretrain/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/setup.py -------------------------------------------------------------------------------- /pretrain/tasks/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/data_utils.py -------------------------------------------------------------------------------- /pretrain/tasks/ensemble_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/ensemble_classifier.py -------------------------------------------------------------------------------- /pretrain/tasks/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/eval_utils.py -------------------------------------------------------------------------------- /pretrain/tasks/finetune_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/finetune_utils.py -------------------------------------------------------------------------------- /pretrain/tasks/glue/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/glue/data.py -------------------------------------------------------------------------------- /pretrain/tasks/glue/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/glue/finetune.py -------------------------------------------------------------------------------- /pretrain/tasks/glue/mnli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/glue/mnli.py -------------------------------------------------------------------------------- /pretrain/tasks/glue/qqp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/glue/qqp.py -------------------------------------------------------------------------------- /pretrain/tasks/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/main.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/contact_prediction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/contact_prediction.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/data.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/eval_utils.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/finetune.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/finetune_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/finetune_utils.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/fluorescence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/fluorescence.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/remote_homology.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/remote_homology.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/secondary_structure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/secondary_structure.py -------------------------------------------------------------------------------- /pretrain/tasks/protein/stability.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/protein/stability.py -------------------------------------------------------------------------------- /pretrain/tasks/race/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/race/data.py -------------------------------------------------------------------------------- /pretrain/tasks/race/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/race/finetune.py -------------------------------------------------------------------------------- /pretrain/tasks/zeroshot_gpt2/datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/zeroshot_gpt2/datasets.py -------------------------------------------------------------------------------- /pretrain/tasks/zeroshot_gpt2/detokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/zeroshot_gpt2/detokenizer.py -------------------------------------------------------------------------------- /pretrain/tasks/zeroshot_gpt2/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tasks/zeroshot_gpt2/evaluate.py -------------------------------------------------------------------------------- /pretrain/tools/create_doc_index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/create_doc_index.py -------------------------------------------------------------------------------- /pretrain/tools/generate_samples_gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/generate_samples_gpt.py -------------------------------------------------------------------------------- /pretrain/tools/linter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/linter.py -------------------------------------------------------------------------------- /pretrain/tools/merge_mp_partitions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/merge_mp_partitions.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/README.md -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/blacklist_urls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/blacklist_urls.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/cleanup_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/cleanup_dataset.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/find_duplicates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/find_duplicates.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/group_duplicate_url.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/group_duplicate_url.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/merge_jsons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/merge_jsons.py -------------------------------------------------------------------------------- /pretrain/tools/openwebtext/remove_group_duplicates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/openwebtext/remove_group_duplicates.py -------------------------------------------------------------------------------- /pretrain/tools/preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/pretrain/tools/preprocess_data.py -------------------------------------------------------------------------------- /tape/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/.gitignore -------------------------------------------------------------------------------- /tape/MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/MANIFEST.in -------------------------------------------------------------------------------- /tape/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/README.md -------------------------------------------------------------------------------- /tape/TAPE.LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/TAPE.LICENSE -------------------------------------------------------------------------------- /tape/clean_checkpoints.sh: -------------------------------------------------------------------------------- 1 | cd ./results 2 | find . -name "*.bin" | xargs rm -rf 3 | -------------------------------------------------------------------------------- /tape/cleanup_results.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/cleanup_results.sh -------------------------------------------------------------------------------- /tape/conda_env/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/conda_env/base.yaml -------------------------------------------------------------------------------- /tape/conda_env/torch1.7.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/conda_env/torch1.7.yaml -------------------------------------------------------------------------------- /tape/config/resnet_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/config/resnet_config.json -------------------------------------------------------------------------------- /tape/config/transformer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/config/transformer_config.json -------------------------------------------------------------------------------- /tape/config/transformer_tiny_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/config/transformer_tiny_config.json -------------------------------------------------------------------------------- /tape/converter/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/converter/config.json -------------------------------------------------------------------------------- /tape/converter/megatron-converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/converter/megatron-converter.py -------------------------------------------------------------------------------- /tape/data_refs.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/data_refs.bib -------------------------------------------------------------------------------- /tape/deprecated/converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/deprecated/converter.py -------------------------------------------------------------------------------- /tape/deprecated/modeling_bert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/deprecated/modeling_bert.py -------------------------------------------------------------------------------- /tape/download_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/download_data.sh -------------------------------------------------------------------------------- /tape/download_data_aws.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/download_data_aws.sh -------------------------------------------------------------------------------- /tape/environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/environment.yml -------------------------------------------------------------------------------- /tape/examples/adding_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/examples/adding_model.py -------------------------------------------------------------------------------- /tape/examples/adding_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/examples/adding_task.py -------------------------------------------------------------------------------- /tape/gridsearch_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/gridsearch_config.json -------------------------------------------------------------------------------- /tape/mypy.ini: -------------------------------------------------------------------------------- 1 | [mypy] 2 | ignore_missing_imports = True 3 | -------------------------------------------------------------------------------- /tape/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/requirements.txt -------------------------------------------------------------------------------- /tape/scripts/fix_lmdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/fix_lmdb.py -------------------------------------------------------------------------------- /tape/scripts/generate_plots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/generate_plots.py -------------------------------------------------------------------------------- /tape/scripts/lmdb_to_fasta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/lmdb_to_fasta.py -------------------------------------------------------------------------------- /tape/scripts/shells/activate_base.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/shells/activate_base.sh -------------------------------------------------------------------------------- /tape/scripts/shells/activate_torch1.7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/shells/activate_torch1.7.sh -------------------------------------------------------------------------------- /tape/scripts/shells/megatron-tape-generator.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/shells/megatron-tape-generator.sh -------------------------------------------------------------------------------- /tape/scripts/shells/para.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/shells/para.sh -------------------------------------------------------------------------------- /tape/scripts/shells/test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/shells/test.sh -------------------------------------------------------------------------------- /tape/scripts/tfrecord_to_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/tfrecord_to_json.py -------------------------------------------------------------------------------- /tape/scripts/tfrecord_to_lmdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/scripts/tfrecord_to_lmdb.py -------------------------------------------------------------------------------- /tape/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/setup.py -------------------------------------------------------------------------------- /tape/tape/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/__init__.py -------------------------------------------------------------------------------- /tape/tape/datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/datasets.py -------------------------------------------------------------------------------- /tape/tape/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/errors.py -------------------------------------------------------------------------------- /tape/tape/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/main.py -------------------------------------------------------------------------------- /tape/tape/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/metrics.py -------------------------------------------------------------------------------- /tape/tape/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/__init__.py -------------------------------------------------------------------------------- /tape/tape/models/file_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/file_utils.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_bert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_bert.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_lstm.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_onehot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_onehot.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_resnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_resnet.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_trrosetta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_trrosetta.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_unirep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_unirep.py -------------------------------------------------------------------------------- /tape/tape/models/modeling_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/models/modeling_utils.py -------------------------------------------------------------------------------- /tape/tape/optimization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/optimization.py -------------------------------------------------------------------------------- /tape/tape/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/registry.py -------------------------------------------------------------------------------- /tape/tape/tokenizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/tokenizers.py -------------------------------------------------------------------------------- /tape/tape/training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/training.py -------------------------------------------------------------------------------- /tape/tape/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/utils/__init__.py -------------------------------------------------------------------------------- /tape/tape/utils/_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/utils/_sampler.py -------------------------------------------------------------------------------- /tape/tape/utils/distributed_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/utils/distributed_utils.py -------------------------------------------------------------------------------- /tape/tape/utils/setup_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/utils/setup_utils.py -------------------------------------------------------------------------------- /tape/tape/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/utils/utils.py -------------------------------------------------------------------------------- /tape/tape/visualization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape/visualization.py -------------------------------------------------------------------------------- /tape/tape_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape_eval.py -------------------------------------------------------------------------------- /tape/tape_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tape_train.py -------------------------------------------------------------------------------- /tape/tests/test_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tests/test_basic.py -------------------------------------------------------------------------------- /tape/tests/test_forceDownload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tests/test_forceDownload.py -------------------------------------------------------------------------------- /tape/tox.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/ProteinLM/HEAD/tape/tox.ini --------------------------------------------------------------------------------