Llama 3.2 mlp pruned Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance. oopere/pruned20-llama-3.2-1B Text Generation • Updated 9 days ago • 37 oopere/pruned40-llama-3.2-1B Text Generation • Updated 28 days ago • 43 oopere/pruned60-llama-3.2-1B Text Generation • Updated Nov 16 • 35 oopere/pruned40-llama-3.2-3b Text Generation • Updated 12 days ago • 31
Interesting LLM Papers Soft-prompt Tuning for Large Language Models to Evaluate Bias Paper • 2306.04735 • Published Jun 7, 2023 • 1
Soft-prompt Tuning for Large Language Models to Evaluate Bias Paper • 2306.04735 • Published Jun 7, 2023 • 1