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

Títulos similares

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