[{"title":"( 16 个子文件 12.89MB ) 模型压缩方法与bert压缩的论文.zip","children":[{"title":"Q8BERT Quantized 8Bit BERT.pdf <span style='color:#111;'> 98.65KB </span>","children":null,"spread":false},{"title":"On the efficacy of knowledge distillation.pdf <span style='color:#111;'> 2.31MB </span>","children":null,"spread":false},{"title":"Deep Mutual Learning.pdf <span style='color:#111;'> 1.37MB </span>","children":null,"spread":false},{"title":"BERT and PALs.pdf <span style='color:#111;'> 397.46KB </span>","children":null,"spread":false},{"title":"Distillation-Based Training for Multi-Exit Architectures.pdf <span style='color:#111;'> 573.05KB </span>","children":null,"spread":false},{"title":"Distilling Task-Specific Knowledge from BERT into.pdf <span style='color:#111;'> 1.71MB </span>","children":null,"spread":false},{"title":"A Gift from Knowledge Distillation.pdf <span style='color:#111;'> 640.49KB </span>","children":null,"spread":false},{"title":"TINYBERT.pdf <span style='color:#111;'> 1.14MB </span>","children":null,"spread":false},{"title":"MOBILEBERT.pdf <span style='color:#111;'> 2.65MB </span>","children":null,"spread":false},{"title":"BERT-of-Theseus.pdf <span style='color:#111;'> 716.18KB </span>","children":null,"spread":false},{"title":"DistilBERT.pdf <span style='color:#111;'> 425.86KB </span>","children":null,"spread":false},{"title":"Patient Knowledge Distillation for BERT Model Compression.pdf <span style='color:#111;'> 543.44KB </span>","children":null,"spread":false},{"title":"FITNETS HINTS FOR THIN.pdf <span style='color:#111;'> 260.50KB </span>","children":null,"spread":false},{"title":"Self-training with Noisy Student improves ImageNet classification.pdf <span style='color:#111;'> 2.67MB </span>","children":null,"spread":false},{"title":"Distilling the Knowledge in a Neural Network.pdf <span style='color:#111;'> 104.13KB </span>","children":null,"spread":false},{"title":"FastBERT.pdf <span style='color:#111;'> 813.59KB </span>","children":null,"spread":false}],"spread":true}]