Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_block_0_disambiguation_qa_Complete Random
file_name: llama_block_0_disambiguation_qa_Complete Random_5000_5.pt
pruning_style: block
community: 0
pruning_ratio: 20
dataset_label: disambiguation_qa
sparsity_ratio: 20
['tasksource/bigbench', 'disambiguation_qa']
finetune: Complete Random
modules_size: 27
modules: ['9_attn.o', '10_mlp.down', '18_attn.o', '29_attn.o', '7_attn.o', '28_mlp.up', '17_mlp.down', '19_mlp.up', '22_mlp.down', '18_attn.q', '23_mlp.down', '15_attn.o', '21_attn.q', '28_attn.q', '9_attn.v', '4_attn.k', '30_mlp.up', '26_attn.q', '26_gate', '29_attn.q', '21_gate', '6_mlp.up', '3_mlp.down', '9_mlp.down', '18_gate', '17_mlp.up', '22_attn.v']
rank: 3
tags: ['model: llama', 'repo_name: llama_block_0_disambiguation_qa_Complete Random', 'file_name: llama_block_0_disambiguation_qa_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: block', 'community: 0', 'pruning_ratio: 20', 'dataset_label: disambiguation_qa', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'disambiguation_qa']", 'finetune: Complete Random', 'modules_size: 27', "modules: ['9_attn.o', '10_mlp.down', '18_attn.o', '29_attn.o', '7_attn.o', '28_mlp.up', '17_mlp.down', '19_mlp.up', '22_mlp.down', '18_attn.q', '23_mlp.down', '15_attn.o', '21_attn.q', '28_attn.q', '9_attn.v', '4_attn.k', '30_mlp.up', '26_attn.q', '26_gate', '29_attn.q', '21_gate', '6_mlp.up', '3_mlp.down', '9_mlp.down', '18_gate', '17_mlp.up', '22_attn.v']", 'rank: 3']
text-generation-inference