Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_channel_3_social_support_Complete Random
file_name: llama_channel_3_social_support_Complete Random_5000_5.pt
pruning_style: channel
community: 3
pruning_ratio: 20
dataset_label: social_support
sparsity_ratio: 20
['tasksource/bigbench', 'social_support']
finetune: Complete Random
modules_size: 30
modules: ['18_mlp.down', '14_gate', '30_attn.o', '4_attn.o', '14_attn.v', '28_attn.q', '11_mlp.down', '10_attn.k', '29_mlp.down', '28_attn.v', '26_attn.k', '7_mlp.up', '9_gate', '18_attn.q', '22_attn.q', '14_attn.o', '15_mlp.up', '6_mlp.up', '11_attn.v', '14_mlp.down', '23_attn.q', '29_mlp.up', '24_attn.q', '5_attn.q', '21_gate', '12_gate', '7_attn.v', '8_attn.k', '10_attn.o', '3_mlp.down']
rank: 2
tags: ['model: llama', 'repo_name: llama_channel_3_social_support_Complete Random', 'file_name: llama_channel_3_social_support_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 3', 'pruning_ratio: 20', 'dataset_label: social_support', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'social_support']", 'finetune: Complete Random', 'modules_size: 30', "modules: ['18_mlp.down', '14_gate', '30_attn.o', '4_attn.o', '14_attn.v', '28_attn.q', '11_mlp.down', '10_attn.k', '29_mlp.down', '28_attn.v', '26_attn.k', '7_mlp.up', '9_gate', '18_attn.q', '22_attn.q', '14_attn.o', '15_mlp.up', '6_mlp.up', '11_attn.v', '14_mlp.down', '23_attn.q', '29_mlp.up', '24_attn.q', '5_attn.q', '21_gate', '12_gate', '7_attn.v', '8_attn.k', '10_attn.o', '3_mlp.down']", 'rank: 2']
text-generation-inference