LCM-Lab
/

nsa_llama

Text Generation

text-generation-inference

Model card Files Files and versions

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

·

Collection including LCM-Lab/nsa_llama

Elastic-Attention

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers • 17 items • Updated 28 days ago • 3

Paper for LCM-Lab/nsa_llama

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published Jan 24 • 33