view article Article Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach By oopere • Nov 24, 2024 • 2
Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 7 items • Updated Dec 27, 2024
Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 7 items • Updated Dec 27, 2024
Running on CPU Upgrade 12.4k 12.4k Open LLM Leaderboard 🏆 Track, rank and evaluate open LLMs and chatbots
Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 7 items • Updated Dec 27, 2024