Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_block_0_high_school_psychology_Complete Random
file_name: llama_chat_block_0_high_school_psychology_Complete Random_5000_5.pt
pruning_style: block
community: 0
pruning_ratio: 20
dataset_label: high_school_psychology
sparsity_ratio: 20
['tasksource/mmlu', 'high_school_psychology']
finetune: Complete Random
modules_size: 36
modules: ['30_attn.k', '4_attn.v', '6_gate', '20_mlp.down', '8_mlp.down', '5_mlp.up', '4_mlp.up', '12_mlp.down', '14_attn.k', '17_attn.k', '27_mlp.up', '18_mlp.up', '9_attn.k', '26_attn.v', '9_attn.v', '15_mlp.down', '16_mlp.up', '28_gate', '21_mlp.down', '14_mlp.up', '21_gate', '22_gate', '25_mlp.down', '8_mlp.up', '8_gate', '18_attn.v', '7_attn.k', '17_attn.v', '29_gate', '19_mlp.up', '14_attn.v', '7_attn.q', '6_mlp.down', '14_gate', '29_mlp.down', '11_mlp.up']
rank: 1
tags: ['model: llama_chat', 'repo_name: llama_chat_block_0_high_school_psychology_Complete Random', 'file_name: llama_chat_block_0_high_school_psychology_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: block', 'community: 0', 'pruning_ratio: 20', 'dataset_label: high_school_psychology', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'high_school_psychology']", 'finetune: Complete Random', 'modules_size: 36', "modules: ['30_attn.k', '4_attn.v', '6_gate', '20_mlp.down', '8_mlp.down', '5_mlp.up', '4_mlp.up', '12_mlp.down', '14_attn.k', '17_attn.k', '27_mlp.up', '18_mlp.up', '9_attn.k', '26_attn.v', '9_attn.v', '15_mlp.down', '16_mlp.up', '28_gate', '21_mlp.down', '14_mlp.up', '21_gate', '22_gate', '25_mlp.down', '8_mlp.up', '8_gate', '18_attn.v', '7_attn.k', '17_attn.v', '29_gate', '19_mlp.up', '14_attn.v', '7_attn.q', '6_mlp.down', '14_gate', '29_mlp.down', '11_mlp.up']", 'rank: 1']
text-generation-inference