├── .gitignore ├── LICENSE ├── README.md ├── conf ├── accelerate_cpu.yaml ├── accelerate_ddp.yaml ├── accelerate_deepspeed_zero2.yaml ├── accelerate_deepspeed_zero3.yaml ├── config.yaml ├── dataset │ ├── uniref100+.yaml │ ├── uniref100.yaml │ └── uniref50.yaml ├── model │ ├── 120M.yaml │ ├── 150M.yaml │ ├── 15B.yaml │ ├── 350M.yaml │ ├── 35M.yaml │ ├── 3B.yaml │ ├── 650M.yaml │ ├── 750M.yaml │ ├── 8M.yaml │ ├── amplify.yaml │ └── esm.yaml ├── optimizer │ ├── adam.yaml │ └── adamw.yaml ├── scheduler │ ├── cosine_decay.yaml │ ├── cosine_decay_warm_restart.yaml │ ├── linear_decay.yaml │ └── linear_decay_warm_restart.yaml ├── tokenizer │ ├── amplify_tokenizer.yaml │ ├── amplify_vocab.txt │ ├── esm_tokenizer.yaml │ └── esm_vocab.txt └── trainer │ ├── base.yaml │ ├── mlm.yaml │ └── span.yaml ├── data-pipeline ├── README.md ├── bulk_download.sh └── oas_file_parser.py ├── docs ├── Makefile ├── make.bat └── source │ ├── amplify.config.rst │ ├── amplify.dataset.rst │ ├── amplify.loss.rst │ ├── amplify.metric.rst │ ├── amplify.model.rst │ ├── amplify.optimizer.rst │ ├── amplify.rst │ ├── amplify.scheduler.rst │ ├── amplify.tokenizer.rst │ ├── amplify.trainer.rst │ ├── conf.py │ ├── index.rst │ ├── installation.rst │ └── usage.rst ├── examples ├── attribution.ipynb ├── contact_prediction.ipynb ├── efficiency.ipynb ├── projection_proteins.ipynb ├── projection_residues.ipynb ├── pseudo_ppl.ipynb └── utils.py ├── framework-integrations └── sagemaker │ ├── README.md │ ├── img │ ├── Inference.png │ └── training.png │ ├── inference │ ├── code │ │ ├── hf │ │ │ ├── inference_hf.py │ │ │ └── requirements.txt │ │ └── sm-trained │ │ │ ├── conf │ │ │ ├── config.yaml │ │ │ └── tokenizer │ │ │ │ ├── amplify_tokenizer.yaml │ │ │ │ └── amplify_vocab.txt │ │ │ ├── inference_sm_trained.py │ │ │ └── requirements.txt │ ├── sagemaker_inference_hf.ipynb │ └── sagemaker_inference_sm_trained_model.ipynb │ └── training │ ├── code │ ├── conf │ │ ├── accelerate_ddp.yaml │ │ ├── accelerate_deepspeed_zero2.yaml │ │ ├── accelerate_deepspeed_zero3.yaml │ │ ├── config.yaml │ │ ├── dataset │ │ │ ├── uniref100+.yaml │ │ │ ├── uniref100.yaml │ │ │ └── uniref50.yaml │ │ ├── model │ │ │ ├── 120M.yaml │ │ │ ├── 150M.yaml │ │ │ ├── 15B.yaml │ │ │ ├── 350M.yaml │ │ │ ├── 35M.yaml │ │ │ ├── 3B.yaml │ │ │ ├── 650M.yaml │ │ │ ├── 750M.yaml │ │ │ ├── 8M.yaml │ │ │ ├── amplify.yaml │ │ │ └── esm.yaml │ │ ├── optimizer │ │ │ ├── adam.yaml │ │ │ └── adamw.yaml │ │ ├── scheduler │ │ │ ├── cosine_decay.yaml │ │ │ ├── cosine_decay_warm_restart.yaml │ │ │ ├── linear_decay.yaml │ │ │ └── linear_decay_warm_restart.yaml │ │ ├── tokenizer │ │ │ ├── amplify_tokenizer.yaml │ │ │ ├── amplify_vocab.txt │ │ │ ├── esm_tokenizer.yaml │ │ │ └── esm_vocab.txt │ │ └── trainer │ │ │ ├── base.yaml │ │ │ ├── mlm.yaml │ │ │ └── span.yaml │ ├── requirements.txt │ ├── sm_training.py │ └── train.py │ └── sagemaker_training.ipynb ├── pyproject.toml ├── scripts ├── fasta_to_csv.py ├── huggingface_esm.py ├── pretrain.py └── safetensors_to_pt.py ├── src └── amplify │ ├── __init__.py │ ├── config │ ├── __init__.py │ ├── schema.py │ └── validator.py │ ├── dataset │ ├── __init__.py │ ├── data_collator.py │ ├── dataloader.py │ └── iterable_protein_dataset.py │ ├── inference │ ├── __init__.py │ ├── embeddings.py │ ├── human_text.py │ ├── predictor.py │ └── strings.py │ ├── loss │ ├── __init__.py │ └── loss.py │ ├── metric │ ├── __init__.py │ └── metrics.py │ ├── model │ ├── __init__.py │ ├── amplify.py │ ├── rmsnorm.py │ └── rotary.py │ ├── optimizer │ ├── __init__.py │ └── optimizer.py │ ├── scheduler │ ├── __init__.py │ └── scheduler.py │ ├── tokenizer │ ├── __init__.py │ └── tokenizer.py │ └── trainer │ ├── __init__.py │ └── trainer.py └── tests ├── __init__.py ├── easy_data.py ├── example-configs └── frankenstein-config │ └── config.yaml ├── example-data ├── big-easy-holdout.csv ├── big-easy-train.csv ├── big-easy-val.csv ├── easy-out-of-sample.csv ├── easy-task-train.csv ├── easy-task-val.csv ├── easy-vocab.txt ├── frankenstein-sequences.csv ├── frankenstein.txt ├── harder-out-of-sample.csv └── reference-embeddings.json ├── fixtures.py ├── produce-reference-model.py ├── reference-model ├── config.yaml └── saved │ └── model.safetensors ├── test_api.py ├── test_config.py ├── test_embeddings.py ├── test_model.py └── test_strings.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/README.md -------------------------------------------------------------------------------- /conf/accelerate_cpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/accelerate_cpu.yaml -------------------------------------------------------------------------------- /conf/accelerate_ddp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/accelerate_ddp.yaml -------------------------------------------------------------------------------- /conf/accelerate_deepspeed_zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/accelerate_deepspeed_zero2.yaml -------------------------------------------------------------------------------- /conf/accelerate_deepspeed_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/accelerate_deepspeed_zero3.yaml -------------------------------------------------------------------------------- /conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/config.yaml -------------------------------------------------------------------------------- /conf/dataset/uniref100+.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/dataset/uniref100+.yaml -------------------------------------------------------------------------------- /conf/dataset/uniref100.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/dataset/uniref100.yaml -------------------------------------------------------------------------------- /conf/dataset/uniref50.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/dataset/uniref50.yaml -------------------------------------------------------------------------------- /conf/model/120M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/120M.yaml -------------------------------------------------------------------------------- /conf/model/150M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/150M.yaml -------------------------------------------------------------------------------- /conf/model/15B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/15B.yaml -------------------------------------------------------------------------------- /conf/model/350M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/350M.yaml -------------------------------------------------------------------------------- /conf/model/35M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/35M.yaml -------------------------------------------------------------------------------- /conf/model/3B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/3B.yaml -------------------------------------------------------------------------------- /conf/model/650M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/650M.yaml -------------------------------------------------------------------------------- /conf/model/750M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/750M.yaml -------------------------------------------------------------------------------- /conf/model/8M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/8M.yaml -------------------------------------------------------------------------------- /conf/model/amplify.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/amplify.yaml -------------------------------------------------------------------------------- /conf/model/esm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/model/esm.yaml -------------------------------------------------------------------------------- /conf/optimizer/adam.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/optimizer/adam.yaml -------------------------------------------------------------------------------- /conf/optimizer/adamw.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/optimizer/adamw.yaml -------------------------------------------------------------------------------- /conf/scheduler/cosine_decay.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/scheduler/cosine_decay.yaml -------------------------------------------------------------------------------- /conf/scheduler/cosine_decay_warm_restart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/scheduler/cosine_decay_warm_restart.yaml -------------------------------------------------------------------------------- /conf/scheduler/linear_decay.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/scheduler/linear_decay.yaml -------------------------------------------------------------------------------- /conf/scheduler/linear_decay_warm_restart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/scheduler/linear_decay_warm_restart.yaml -------------------------------------------------------------------------------- /conf/tokenizer/amplify_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/tokenizer/amplify_tokenizer.yaml -------------------------------------------------------------------------------- /conf/tokenizer/amplify_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/tokenizer/amplify_vocab.txt -------------------------------------------------------------------------------- /conf/tokenizer/esm_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/tokenizer/esm_tokenizer.yaml -------------------------------------------------------------------------------- /conf/tokenizer/esm_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/tokenizer/esm_vocab.txt -------------------------------------------------------------------------------- /conf/trainer/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/trainer/base.yaml -------------------------------------------------------------------------------- /conf/trainer/mlm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/trainer/mlm.yaml -------------------------------------------------------------------------------- /conf/trainer/span.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/conf/trainer/span.yaml -------------------------------------------------------------------------------- /data-pipeline/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/data-pipeline/README.md -------------------------------------------------------------------------------- /data-pipeline/bulk_download.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/data-pipeline/bulk_download.sh -------------------------------------------------------------------------------- /data-pipeline/oas_file_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/data-pipeline/oas_file_parser.py -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/source/amplify.config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.config.rst -------------------------------------------------------------------------------- /docs/source/amplify.dataset.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.dataset.rst -------------------------------------------------------------------------------- /docs/source/amplify.loss.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.loss.rst -------------------------------------------------------------------------------- /docs/source/amplify.metric.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.metric.rst -------------------------------------------------------------------------------- /docs/source/amplify.model.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.model.rst -------------------------------------------------------------------------------- /docs/source/amplify.optimizer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.optimizer.rst -------------------------------------------------------------------------------- /docs/source/amplify.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.rst -------------------------------------------------------------------------------- /docs/source/amplify.scheduler.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.scheduler.rst -------------------------------------------------------------------------------- /docs/source/amplify.tokenizer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.tokenizer.rst -------------------------------------------------------------------------------- /docs/source/amplify.trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/amplify.trainer.rst -------------------------------------------------------------------------------- /docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/conf.py -------------------------------------------------------------------------------- /docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/index.rst -------------------------------------------------------------------------------- /docs/source/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/installation.rst -------------------------------------------------------------------------------- /docs/source/usage.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/docs/source/usage.rst -------------------------------------------------------------------------------- /examples/attribution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/attribution.ipynb -------------------------------------------------------------------------------- /examples/contact_prediction.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/contact_prediction.ipynb -------------------------------------------------------------------------------- /examples/efficiency.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/efficiency.ipynb -------------------------------------------------------------------------------- /examples/projection_proteins.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/projection_proteins.ipynb -------------------------------------------------------------------------------- /examples/projection_residues.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/projection_residues.ipynb -------------------------------------------------------------------------------- /examples/pseudo_ppl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/pseudo_ppl.ipynb -------------------------------------------------------------------------------- /examples/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/examples/utils.py -------------------------------------------------------------------------------- /framework-integrations/sagemaker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/README.md -------------------------------------------------------------------------------- /framework-integrations/sagemaker/img/Inference.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/img/Inference.png -------------------------------------------------------------------------------- /framework-integrations/sagemaker/img/training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/img/training.png -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/hf/inference_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/hf/inference_hf.py -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/hf/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/hf/requirements.txt -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/sm-trained/conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/sm-trained/conf/config.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/sm-trained/conf/tokenizer/amplify_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/sm-trained/conf/tokenizer/amplify_tokenizer.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/sm-trained/conf/tokenizer/amplify_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/sm-trained/conf/tokenizer/amplify_vocab.txt -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/sm-trained/inference_sm_trained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/code/sm-trained/inference_sm_trained.py -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/code/sm-trained/requirements.txt: -------------------------------------------------------------------------------- 1 | git+https://github.com/chandar-lab/AMPLIFY.git -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/sagemaker_inference_hf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/sagemaker_inference_hf.ipynb -------------------------------------------------------------------------------- /framework-integrations/sagemaker/inference/sagemaker_inference_sm_trained_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/inference/sagemaker_inference_sm_trained_model.ipynb -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/accelerate_ddp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/accelerate_ddp.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/accelerate_deepspeed_zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/accelerate_deepspeed_zero2.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/accelerate_deepspeed_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/accelerate_deepspeed_zero3.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/config.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/dataset/uniref100+.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/dataset/uniref100+.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/dataset/uniref100.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/dataset/uniref100.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/dataset/uniref50.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/dataset/uniref50.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/120M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/120M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/150M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/150M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/15B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/15B.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/350M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/350M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/35M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/35M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/3B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/3B.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/650M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/650M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/750M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/750M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/8M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/8M.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/amplify.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/amplify.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/model/esm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/model/esm.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/optimizer/adam.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/optimizer/adam.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/optimizer/adamw.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/optimizer/adamw.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/scheduler/cosine_decay.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/scheduler/cosine_decay.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/scheduler/cosine_decay_warm_restart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/scheduler/cosine_decay_warm_restart.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/scheduler/linear_decay.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/scheduler/linear_decay.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/scheduler/linear_decay_warm_restart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/scheduler/linear_decay_warm_restart.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/tokenizer/amplify_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/tokenizer/amplify_tokenizer.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/tokenizer/amplify_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/tokenizer/amplify_vocab.txt -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/tokenizer/esm_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/tokenizer/esm_tokenizer.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/tokenizer/esm_vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/tokenizer/esm_vocab.txt -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/trainer/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/trainer/base.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/trainer/mlm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/trainer/mlm.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/conf/trainer/span.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/conf/trainer/span.yaml -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/requirements.txt: -------------------------------------------------------------------------------- 1 | git+https://github.com/chandar-lab/AMPLIFY.git 2 | hydra-core==1.3.2 3 | -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/sm_training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/sm_training.py -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/code/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/code/train.py -------------------------------------------------------------------------------- /framework-integrations/sagemaker/training/sagemaker_training.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/framework-integrations/sagemaker/training/sagemaker_training.ipynb -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/fasta_to_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/scripts/fasta_to_csv.py -------------------------------------------------------------------------------- /scripts/huggingface_esm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/scripts/huggingface_esm.py -------------------------------------------------------------------------------- /scripts/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/scripts/pretrain.py -------------------------------------------------------------------------------- /scripts/safetensors_to_pt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/scripts/safetensors_to_pt.py -------------------------------------------------------------------------------- /src/amplify/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/__init__.py -------------------------------------------------------------------------------- /src/amplify/config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/config/__init__.py -------------------------------------------------------------------------------- /src/amplify/config/schema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/config/schema.py -------------------------------------------------------------------------------- /src/amplify/config/validator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/config/validator.py -------------------------------------------------------------------------------- /src/amplify/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/dataset/__init__.py -------------------------------------------------------------------------------- /src/amplify/dataset/data_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/dataset/data_collator.py -------------------------------------------------------------------------------- /src/amplify/dataset/dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/dataset/dataloader.py -------------------------------------------------------------------------------- /src/amplify/dataset/iterable_protein_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/dataset/iterable_protein_dataset.py -------------------------------------------------------------------------------- /src/amplify/inference/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/inference/__init__.py -------------------------------------------------------------------------------- /src/amplify/inference/embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/inference/embeddings.py -------------------------------------------------------------------------------- /src/amplify/inference/human_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/inference/human_text.py -------------------------------------------------------------------------------- /src/amplify/inference/predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/inference/predictor.py -------------------------------------------------------------------------------- /src/amplify/inference/strings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/inference/strings.py -------------------------------------------------------------------------------- /src/amplify/loss/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/loss/__init__.py -------------------------------------------------------------------------------- /src/amplify/loss/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/loss/loss.py -------------------------------------------------------------------------------- /src/amplify/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/metric/__init__.py -------------------------------------------------------------------------------- /src/amplify/metric/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/metric/metrics.py -------------------------------------------------------------------------------- /src/amplify/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/model/__init__.py -------------------------------------------------------------------------------- /src/amplify/model/amplify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/model/amplify.py -------------------------------------------------------------------------------- /src/amplify/model/rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/model/rmsnorm.py -------------------------------------------------------------------------------- /src/amplify/model/rotary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/model/rotary.py -------------------------------------------------------------------------------- /src/amplify/optimizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/optimizer/__init__.py -------------------------------------------------------------------------------- /src/amplify/optimizer/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/optimizer/optimizer.py -------------------------------------------------------------------------------- /src/amplify/scheduler/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/scheduler/__init__.py -------------------------------------------------------------------------------- /src/amplify/scheduler/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/scheduler/scheduler.py -------------------------------------------------------------------------------- /src/amplify/tokenizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/tokenizer/__init__.py -------------------------------------------------------------------------------- /src/amplify/tokenizer/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/tokenizer/tokenizer.py -------------------------------------------------------------------------------- /src/amplify/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/trainer/__init__.py -------------------------------------------------------------------------------- /src/amplify/trainer/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/src/amplify/trainer/trainer.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/easy_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/easy_data.py -------------------------------------------------------------------------------- /tests/example-configs/frankenstein-config/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-configs/frankenstein-config/config.yaml -------------------------------------------------------------------------------- /tests/example-data/big-easy-holdout.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/big-easy-holdout.csv -------------------------------------------------------------------------------- /tests/example-data/big-easy-train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/big-easy-train.csv -------------------------------------------------------------------------------- /tests/example-data/big-easy-val.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/big-easy-val.csv -------------------------------------------------------------------------------- /tests/example-data/easy-out-of-sample.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/easy-out-of-sample.csv -------------------------------------------------------------------------------- /tests/example-data/easy-task-train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/easy-task-train.csv -------------------------------------------------------------------------------- /tests/example-data/easy-task-val.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/easy-task-val.csv -------------------------------------------------------------------------------- /tests/example-data/easy-vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/easy-vocab.txt -------------------------------------------------------------------------------- /tests/example-data/frankenstein-sequences.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/frankenstein-sequences.csv -------------------------------------------------------------------------------- /tests/example-data/frankenstein.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/frankenstein.txt -------------------------------------------------------------------------------- /tests/example-data/harder-out-of-sample.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/harder-out-of-sample.csv -------------------------------------------------------------------------------- /tests/example-data/reference-embeddings.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/example-data/reference-embeddings.json -------------------------------------------------------------------------------- /tests/fixtures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/fixtures.py -------------------------------------------------------------------------------- /tests/produce-reference-model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/produce-reference-model.py -------------------------------------------------------------------------------- /tests/reference-model/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/reference-model/config.yaml -------------------------------------------------------------------------------- /tests/reference-model/saved/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/reference-model/saved/model.safetensors -------------------------------------------------------------------------------- /tests/test_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/test_api.py -------------------------------------------------------------------------------- /tests/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/test_config.py -------------------------------------------------------------------------------- /tests/test_embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/test_embeddings.py -------------------------------------------------------------------------------- /tests/test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/test_model.py -------------------------------------------------------------------------------- /tests/test_strings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chandar-lab/AMPLIFY/HEAD/tests/test_strings.py --------------------------------------------------------------------------------