LCM-Lab
/

full_xattn_64k_llama3.1-8b_wfrozen

Text Generation

text-generation-inference

Model card Files Files and versions

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

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F32

·

Collection including LCM-Lab/full_xattn_64k_llama3.1-8b_wfrozen

Elastic-Attention

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

Paper for LCM-Lab/full_xattn_64k_llama3.1-8b_wfrozen

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

Paper • 2601.17367 • Published Jan 24 • 34