view article Article Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach By oopere • Nov 24, 2024 • 1
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 10 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. • 7 items • Updated 10 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. • 7 items • Updated 10 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. • 7 items • Updated 10 days ago