DeBERTa：注意力分散的增强解码的BERT-Python开发

[{"title":"（ 92 个子文件 114KB ） DeBERTa：注意力分散的增强解码的BERT-Python开发","children":[{"title":"DeBERTa-master","children":[{"title":"DeBERTa","children":[{"title":"data","children":[{"title":"example.py <span style='color:#111;'> 2.87KB </span>","children":null,"spread":false},{"title":"dataloader.py <span style='color:#111;'> 19.49KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 143B </span>","children":null,"spread":false},{"title":"dynamic_dataset.py <span style='color:#111;'> 1.69KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"sift","children":[{"title":"__init__.py <span style='color:#111;'> 20B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"sift.py <span style='color:#111;'> 7.35KB </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 1.38KB </span>","children":null,"spread":false},{"title":"apps","children":[{"title":"models","children":[{"title":"masked_language_model.py <span style='color:#111;'> 4.70KB </span>","children":null,"spread":false},{"title":"multi_choice.py <span style='color:#111;'> 2.61KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 148B </span>","children":null,"spread":false},{"title":"record_qa.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"sequence_classification.py <span style='color:#111;'> 3.17KB </span>","children":null,"spread":false},{"title":"ner.py <span style='color:#111;'> 1.85KB </span>","children":null,"spread":false}],"spread":true},{"title":"tasks","children":[{"title":"task.py <span style='color:#111;'> 3.88KB </span>","children":null,"spread":false},{"title":"superglue_tasks.py <span style='color:#111;'> 45.82KB </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 1.10KB </span>","children":null,"spread":false},{"title":"race_task.py <span style='color:#111;'> 5.97KB </span>","children":null,"spread":false},{"title":"mlm_task.py <span style='color:#111;'> 8.04KB </span>","children":null,"spread":false},{"title":"record_eval.py <span style='color:#111;'> 2.53KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 75B </span>","children":null,"spread":false},{"title":"task_registry.py <span style='color:#111;'> 1.74KB </span>","children":null,"spread":false},{"title":"glue_tasks.py <span style='color:#111;'> 28.04KB </span>","children":null,"spread":false},{"title":"ner_task.py <span style='color:#111;'> 8.38KB </span>","children":null,"spread":false}],"spread":true},{"title":"run.py <span style='color:#111;'> 17.00KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 128B </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"logger_util.py <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false},{"title":"xtqdm.py <span style='color:#111;'> 630B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 122B </span>","children":null,"spread":false},{"title":"jit_tracing.py <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"argument_types.py <span style='color:#111;'> 145B </span>","children":null,"spread":false}],"spread":true},{"title":"deberta","children":[{"title":"cache_utils.py <span style='color:#111;'> 4.90KB </span>","children":null,"spread":false},{"title":"pretrained_models.py <span style='color:#111;'> 2B </span>","children":null,"spread":false},{"title":"tokenizers.py <span style='color:#111;'> 241B </span>","children":null,"spread":false},{"title":"da_utils.py <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false},{"title":"mlm.py <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"nnmodule.py <span style='color:#111;'> 4.58KB </span>","children":null,"spread":false},{"title":"pooling.py <span style='color:#111;'> 2.79KB </span>","children":null,"spread":false},{"title":"deberta.py <span style='color:#111;'> 5.31KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 455B </span>","children":null,"spread":false},{"title":"bert.py <span style='color:#111;'> 12.01KB </span>","children":null,"spread":false},{"title":"disentangled_attention.py <span style='color:#111;'> 11.19KB </span>","children":null,"spread":false},{"title":"ops.py <span style='color:#111;'> 6.46KB </span>","children":null,"spread":false},{"title":"spm_tokenizer.py <span style='color:#111;'> 9.39KB </span>","children":null,"spread":false},{"title":"gpt2_bpe_utils.py <span style='color:#111;'> 5.49KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 4.14KB </span>","children":null,"spread":false},{"title":"gpt2_tokenizer.py <span style='color:#111;'> 6.17KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"docs","children":[{"title":"make.bat <span style='color:#111;'> 799B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 23B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 638B </span>","children":null,"spread":false},{"title":"source","children":[{"title":"conf.py <span style='color:#111;'> 5.52KB </span>","children":null,"spread":false},{"title":"index.rst <span style='color:#111;'> 455B </span>","children":null,"spread":false},{"title":"modules","children":[{"title":"deberta.rst <span style='color:#111;'> 1.28KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"SECURITY.md <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"setup.cfg <span style='color:#111;'> 40B </span>","children":null,"spread":false},{"title":"experiments","children":[{"title":"language_model","children":[{"title":"xlarge.json <span style='color:#111;'> 604B </span>","children":null,"spread":false},{"title":"mlm.sh <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"prepare_data.py <span style='color:#111;'> 1.08KB </span>","children":null,"spread":false},{"title":"xxlarge.json <span style='color:#111;'> 604B </span>","children":null,"spread":false}],"spread":true},{"title":"superglue","children":[{"title":"record.sh <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"copa.sh <span style='color:#111;'> 1.92KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 223B </span>","children":null,"spread":false},{"title":"config.json <span style='color:#111;'> 60B </span>","children":null,"spread":false},{"title":"download_data.sh <span style='color:#111;'> 262B </span>","children":null,"spread":false}],"spread":true},{"title":"glue","children":[{"title":"mnli.sh <span style='color:#111;'> 2.42KB </span>","children":null,"spread":false},{"title":"stsb.sh <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":"sst2.sh <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"patch.diff <span style='color:#111;'> 3.56KB </span>","children":null,"spread":false},{"title":"rte.sh <span style='color:#111;'> 2.12KB </span>","children":null,"spread":false},{"title":"mrpc.sh <span style='color:#111;'> 2.16KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 514B </span>","children":null,"spread":false},{"title":"qnli.sh <span style='color:#111;'> 2.04KB </span>","children":null,"spread":false},{"title":"cola.sh <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":"qqp.sh <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"config.json <span style='color:#111;'> 60B </span>","children":null,"spread":false},{"title":"download_data.sh <span style='color:#111;'> 426B </span>","children":null,"spread":false}],"spread":false},{"title":"my_exp","children":[{"title":"race_task.py <span style='color:#111;'> 6.37KB </span>","children":null,"spread":false},{"title":"run.sh <span style='color:#111;'> 1.97KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 155B </span>","children":null,"spread":false}],"spread":true},{"title":"ner","children":[{"title":"ner.sh <span style='color:#111;'> 2.19KB </span>","children":null,"spread":false},{"title":"config.json <span style='color:#111;'> 60B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"VERSION <span style='color:#111;'> 7B </span>","children":null,"spread":false},{"title":"docker","children":[{"title":"Dockerfile <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"build.sh <span style='color:#111;'> 195B </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 120B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 1.53KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"CODE_OF_CONDUCT.md <span style='color:#111;'> 444B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 14.25KB </span>","children":null,"spread":false},{"title":"run_docker.sh <span style='color:#111;'> 595B </span>","children":null,"spread":false}],"spread":false}],"spread":true}]