# Language Model Compression

This model is a lightweight distilled version based on Microsoft's Xtremedistil, fine-tuned on the wikitext dataset, suitable for text generation tasks.

This model is a sparse pre-trained model achieving 90% sparsity through weight pruning techniques, suitable for fine-tuning on various language tasks.

This is a sparsely pretrained BERT-Base model achieving 90% weight sparsity through one-shot pruning, suitable for fine-tuning on various language tasks.