Dynamic sparse no training: training-free fine-tuning for sparse llms

समान संसाधन

• PockEngine: Sparse and Efficient Fine-tuning in a Pocket
  द्वारा: Zhu, Ligeng, और अन्य
  प्रकाशित: (2024)
• TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
  द्वारा: Tang, Haotian, और अन्य
  प्रकाशित: (2024)
• Data parallelism in training sparse neural networks
  द्वारा: Lee, N, और अन्य
  प्रकाशित: (2020)
• Dictionary training for sparse representation as generalization of K-means clustering
  द्वारा: Sahoo, Sujit Kumar, और अन्य
  प्रकाशित: (2013)
• Dense for the price of sparse: improved performance of sparsely initialized networks via a subspace offset
  द्वारा: Price, I, और अन्य
  प्रकाशित: (2021)