Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_4_suicide_risk_Complete Random
file_name: vicuna_block_4_suicide_risk_Complete Random_5000_5.pt
pruning_style: block
community: 4
pruning_ratio: 20
dataset_label: suicide_risk
sparsity_ratio: 20
['tasksource/bigbench', 'suicide_risk']
finetune: Complete Random
modules_size: 17
modules: ['30_attn.v', '22_mlp.up', '18_mlp.down', '7_mlp.up', '24_gate', '16_mlp.up', '19_attn.q', '9_mlp.down', '27_mlp.up', '21_mlp.down', '21_mlp.up', '9_mlp.up', '24_attn.o', '19_mlp.down', '25_attn.k', '8_attn.v', '6_attn.k']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_block_4_suicide_risk_Complete Random', 'file_name: vicuna_block_4_suicide_risk_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 4', 'pruning_ratio: 20', 'dataset_label: suicide_risk', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'suicide_risk']", 'finetune: Complete Random', 'modules_size: 17', "modules: ['30_attn.v', '22_mlp.up', '18_mlp.down', '7_mlp.up', '24_gate', '16_mlp.up', '19_attn.q', '9_mlp.down', '27_mlp.up', '21_mlp.down', '21_mlp.up', '9_mlp.up', '24_attn.o', '19_mlp.down', '25_attn.k', '8_attn.v', '6_attn.k']", 'rank: 1']
text-generation-inference
- SHA256:
- db9eef6183edcb3981b0eccd9821a2e641cb20730f1423ac4235a4ecec0946a5
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.84 GB
- Xet hash:
- 65a535f1ae66611a52dc4a7444a1a0ff1da516f435f235e84b44c1d0543e64e1
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.