https://github.com/MindSpore-scientific-2/code-3/tree/main/The_RefinedWeb_Dataset_for_Falcon
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.
Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
A Closer Look at Structured Pruning for Neural Network Compression
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Neural Network Pruning with Residual-Connections and Limited-Data
Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Improving the Transferability of Adversarial Examples via Direction Tuning
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
A Simple and Effective Pruning Approach for Large Language Models
A Simple and Effective Pruning Approach for Large Language Models
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.