Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_block_3_mathematical_induction_Complete Random
file_name: llama_block_3_mathematical_induction_Complete Random_5000_5.pt
pruning_style: block
community: 3
pruning_ratio: 20
dataset_label: mathematical_induction
sparsity_ratio: 20
['tasksource/bigbench', 'mathematical_induction']
finetune: Complete Random
modules_size: 18
modules: ['12_attn.o', '4_mlp.down', '6_attn.o', '9_mlp.up', '6_attn.v', '27_mlp.down', '12_mlp.up', '9_attn.k', '18_gate', '12_mlp.down', '17_mlp.up', '17_attn.q', '20_mlp.down', '29_attn.v', '29_attn.k', '20_gate', '15_attn.k', '25_attn.q']
rank: 1
tags: ['model: llama', 'repo_name: llama_block_3_mathematical_induction_Complete Random', 'file_name: llama_block_3_mathematical_induction_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: block', 'community: 3', 'pruning_ratio: 20', 'dataset_label: mathematical_induction', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'mathematical_induction']", 'finetune: Complete Random', 'modules_size: 18', "modules: ['12_attn.o', '4_mlp.down', '6_attn.o', '9_mlp.up', '6_attn.v', '27_mlp.down', '12_mlp.up', '9_attn.k', '18_gate', '12_mlp.down', '17_mlp.up', '17_attn.q', '20_mlp.down', '29_attn.v', '29_attn.k', '20_gate', '15_attn.k', '25_attn.q']", 'rank: 1']
text-generation-inference