Reduces LLM size via Wanda or SparseGPT pruning workflows.
npx skills add https://github.com/ricable/mcai --skill model-pruning-ricable
Please help me install this Agent Skill. Skill: model-pruning Source: https://github.com/ricable/mcai/tree/main/.agents/skills/model-pruning Command: npx skills add https://github.com/ricable/mcai --skill model-pruning-ricable
This Skill helps compress large language models without retraining so they use less memory, run faster, and stay accurate enough for practical deployment.
Ask the assistant to prune your target language model to a chosen sparsity level using Wanda or SparseGPT and save the compressed checkpoint.
High-intent search queries and answers about installing and using this skill.
Compress large language models without retraining using one-shot pruning workflows based on Wanda or SparseGPT. This reduces model size and inference cost while maintaining accuracy through layer-wise masking and weight-activation importance scoring.
Apply N:M sparsity to LLMs for hardware-friendly acceleration using structured pruning workflows. This creates accelerator-ready sparse models that deliver inference speedups on compatible hardware while satisfying calibration data handling requirements.
Wanda pruning uses weight and activation scoring for one-shot compression, while SparseGPT offers higher-quality layer-wise compression through reconstruction. Both reduce model size without retraining, but SparseGPT typically preserves more accuracy at higher sparsity levels.
Prune large language models for constrained hardware with minimal accuracy loss using calibration-based pruning. Methods like SparseGPT apply layer-wise masking and importance scoring to preserve model quality while achieving target sparsity levels.
Calibration data handling is required for one-shot pruning workflows. The process uses calibration samples to score weight and activation importance, enabling accurate layer-wise masking when applying Wanda or SparseGPT compression to the target model checkpoint.
Supporter09Prune large language models with Wanda or SparseGPT-style methods.
MesferAliCompress Large Language Models using Wanda and SparseGPT pruning techniques.
lucifertrjCompress machine learning models using distillation, pruning, and quantization.
hiyenwongTrain spiking-mode neural networks using Hopfield-based decomposition.
