Model Card for Model ID

This repo contains a 2:4 sparse version of the LLaMA2-7B model. Trainied with methods from AAAI25 paper Pruning Large Language Models with Semi-Structural Adaptive Sparse Training.

Same structured as LLaMA2-7B, but weight from linear layer conform to 2:4 sparse pattern.

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Yellowtree/LLaMA2-7B_2-by-4_Sparse

Base model

Finetuned

(1092)

this model