The IntelLabs/sqft-phi-3-mini-4k-60-base is a 4 billion parameter sparse language model derived from Microsoft's Phi-3-mini-4k-instruct. Developed by IntelLabs, this model applies 60% sparsity using the Wanda pruning method, as detailed in the SQFT research. It is designed for efficient deployment and adaptation of low-precision sparse foundation models, making it suitable for resource-constrained environments.
No reviews yet. Be the first to review!
Hugging Face