The IntelLabs/sqft-phi-3-mini-4k-40-base is a 4 billion parameter language model derived from Microsoft's Phi-3-mini-4k-instruct. It incorporates 40% sparsity using the Wanda pruning method, making it a sparse foundation model. This model is designed for efficient deployment and adaptation, focusing on low-cost model adaptation in low-precision sparse environments. Its primary strength lies in its optimized structure for resource-constrained applications.
No reviews yet. Be the first to review!
Hugging Face