metadata
license: apache-2.0
language:
- en
base_model:
- meta-llama/Llama-2-7b-hf
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.
Model Description
Same structured as LLaMA2-7B, but weight from linear layer conform to 2:4 sparse pattern.