LCM-Lab
/

full_xattn_64k_qwen3-4b_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: 4

Safetensors

Model size

4B params

Tensor type

F32

·

Model tree for LCM-Lab/full_xattn_64k_qwen3-4b_wfrozen

Base model

Qwen/Qwen3-4B-Base

Finetuned

Finetuned

(471)

this model

Collection including LCM-Lab/full_xattn_64k_qwen3-4b_wfrozen

Elastic-Attention

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers • 17 items • Updated about 1 month ago • 3

Paper for LCM-Lab/full_xattn_64k_qwen3-4b_wfrozen

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

Paper • 2601.17367 • Published Jan 24 • 33