Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 6 items • Updated 4 days ago
Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 6 items • Updated 4 days ago
view article Article Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach By oopere • Nov 24 • 1
Llama 3.2 mlp pruned Collection Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. • 6 items • Updated 4 days ago
Shortened LLaMA: A Simple Depth Pruning for Large Language Models Paper • 2402.02834 • Published Feb 5 • 14