Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_channel_1_analytic_entailment_Complete Random
file_name: vicuna_channel_1_analytic_entailment_Complete Random_5000_5.pt
pruning_style: channel
community: 1
pruning_ratio: 20
dataset_label: analytic_entailment
sparsity_ratio: 20
['tasksource/bigbench', 'analytic_entailment']
finetune: Complete Random
modules_size: 30
modules: ['11_attn.q', '3_gate', '17_mlp.up', '16_attn.v', '14_attn.v', '3_mlp.up', '28_attn.q', '24_attn.q', '23_attn.v', '4_attn.o', '28_mlp.down', '6_attn.k', '27_attn.k', '22_attn.q', '11_mlp.down', '21_mlp.down', '3_mlp.down', '12_gate', '12_attn.k', '11_attn.o', '16_mlp.down', '29_attn.q', '8_attn.k', '25_attn.o', '18_gate', '15_attn.v', '14_gate', '5_attn.k', '13_attn.q', '5_mlp.up']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_channel_1_analytic_entailment_Complete Random', 'file_name: vicuna_channel_1_analytic_entailment_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: channel', 'community: 1', 'pruning_ratio: 20', 'dataset_label: analytic_entailment', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'analytic_entailment']", 'finetune: Complete Random', 'modules_size: 30', "modules: ['11_attn.q', '3_gate', '17_mlp.up', '16_attn.v', '14_attn.v', '3_mlp.up', '28_attn.q', '24_attn.q', '23_attn.v', '4_attn.o', '28_mlp.down', '6_attn.k', '27_attn.k', '22_attn.q', '11_mlp.down', '21_mlp.down', '3_mlp.down', '12_gate', '12_attn.k', '11_attn.o', '16_mlp.down', '29_attn.q', '8_attn.k', '25_attn.o', '18_gate', '15_attn.v', '14_gate', '5_attn.k', '13_attn.q', '5_mlp.up']", 'rank: 1']
text-generation-inference
- SHA256:
- e22a058d42abfdd7725b0c74182ffd006d9e1a465e50e2ddfa052e3bd545337d
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.86 GB
- Xet hash:
- 4e270ce763e549a17d3e003eb08f31e799d386807fe26026383657e55cfb8410
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.