mt-dnn
Multi-Task Deep Neural Networks for Natural Language Understanding
File Explorer
Download Latest Version (.zip)- __init__.py
- log_wrapper.py
- metrics.py
- mrc_eval.py
- my_statics.py
- roberta_utils.py
- squad_eval.py
- task_def.py
- tokenizer_utils.py
- utils.py
- utils_qa.py
- vocab.py
- Dockerfile
- domain_adaptation_def.yml
- domain_prepro.py
- run_batch.sh
- run_domain_adaptation.sh
- pair-input.txt
- single-input.txt
- extract.sh
- extractor.py
- anli_task_def.yml
- glue_prepro.py
- glue_task_def.yml
- glue_task_gen_def.yml
- glue_utils.py
- prepro.sh
- run_glue_finetuning.sh
- run_glue_generative_finetuning.sh
- mlm.yml
- mlm_train.json
- mlm_utils.py
- ner_task_def.yml
- ner_utils.py
- prepro.py
- squad_prepro.py
- squad_task_def.yml
- superglue_fairseq.py
- superglue_prepro.py
- superglue_process.sh
- superglue_task_def.yml
- superglue_utils.py
- extract_cat.py
- README.md
- xnli_eval.py
- xnli_prepro.py
- xnli_task_def.yml
- __init__.py
- common_utils.py
- exp_def.py
- cola_encoding.pt
- cola_train.json
- mnli_train.json
- stsb_train.json
- cola_train.json
- mnli_train.json
- stsb_train.json
- cola_dev.json
- cola_test.json
- cola_train.json
- cola_train.tsv
- glue_task_def.yml
- mnli_train.tsv
- stsb_train.tsv
- __init__.py
- common.py
- dropout_wrapper.py
- my_optim.py
- pooler.py
- s4.py
- san.py
- san_model.py
- similarity.py
- sub_layers.py
- __init__.py
- configuration.py
- modeling_t5.py
- tokenization_t5.py
- __init__.py
- configuration.py
- modeling_t5.py
- README.md
- tokenization_t5.py
- __init__.py
- batcher.py
- inference.py
- loss.py
- matcher.py
- model.py
- optim.py
- perturbation.py
- __init__.py
- classification_task.py
- ranking_task.py
- regression_task.py
- seqencelabeling_task.py
- sequence_gen_task.py
- span_classification_task.py
- dev.tsv
- test.tsv
- train.tsv
- dev_matched.tsv
- dev_mismatched.tsv
- test_matched.tsv
- test_mismatched.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- dev.tsv
- test.tsv
- train.tsv
- my_head.sh
- cola_dev.json
- cola_test.json
- cola_train.json
- mnli_matched_dev.json
- mnli_matched_test.json
- mnli_mismatched_dev.json
- mnli_mismatched_test.json
- mnli_train.json
- mrpc_dev.json
- mrpc_test.json
- mrpc_train.json
- qnli_dev.json
- qnli_test.json
- qnli_train.json
- qqp_dev.json
- qqp_test.json
- qqp_train.json
- rte_dev.json
- rte_test.json
- rte_train.json
- sst_dev.json
- sst_test.json
- sst_train.json
- stsb_dev.json
- stsb_test.json
- stsb_train.json
- wnli_dev.json
- wnli_test.json
- wnli_train.json
- _test_train.py
- mnli_task_def.yml
- test.sh
- test_prepro.py
- .gitignore
- .travis.yml
- _config.yml
- calc_metrics.py
- CODE_OF_CONDUCT.md
- download.sh
- int_test_encoder.py
- int_test_prepro_std.py
- LICENSE
- predict.py
- prepare_distillation_data.py
- prepro_gen_std.py
- prepro_std.py
- pretrained_models.py
- README.md
- requirements.txt
- run_toy.sh
- SECURITY.md
- setup.cfg
- SUPPORT.md
- train.py
# Installation Guide
1. Get the code
git clone https://github.com/namisan/mt-dnn
Downloads the entire project code from GitHub to your computer.
cd mt-dnn
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
1. Pull docker </br>
Type this command into your terminal and run it.
2. Run docker </br>
Type this command into your terminal and run it.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python <μ€νν νμΌλͺ
>.py # READMEμμ μ νν μ€ν νμΌλͺ
μ νμΈνμΈμ
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
// repository documentation
Was this content helpful?
(0 ratings)