Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_2_unit_interpretation_Community
file_name: vicuna_block_2_unit_interpretation_Community_5000_5.pt
pruning_style: block
community: 2
pruning_ratio: 20
dataset_label: unit_interpretation
sparsity_ratio: 20
['tasksource/bigbench', 'unit_interpretation']
finetune: Community
modules_size: 21
modules: ['11_attn.o', '12_attn.q', '15_attn.k', '15_attn.v', '16_attn.q', '16_attn.v', '17_attn.q', '18_attn.v', '19_attn.q', '21_attn.o', '22_attn.o', '26_attn.k', '26_attn.o', '27_attn.o', '30_attn.o', '30_attn.v', '4_attn.o', '7_attn.o', '7_attn.q', '8_attn.v', '9_attn.k']
rank: 2
tags: ['model: vicuna', 'repo_name: vicuna_block_2_unit_interpretation_Community', 'file_name: vicuna_block_2_unit_interpretation_Community_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: unit_interpretation', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'unit_interpretation']", 'finetune: Community', 'modules_size: 21', "modules: ['11_attn.o', '12_attn.q', '15_attn.k', '15_attn.v', '16_attn.q', '16_attn.v', '17_attn.q', '18_attn.v', '19_attn.q', '21_attn.o', '22_attn.o', '26_attn.k', '26_attn.o', '27_attn.o', '30_attn.o', '30_attn.v', '4_attn.o', '7_attn.o', '7_attn.q', '8_attn.v', '9_attn.k']", 'rank: 2']
text-generation-inference
- SHA256:
- e5f05ab5dccad32ebc13a8236cf47c5d84a55abc83c8d4dd7b77f9f23d40658c
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.86 GB
- Xet hash:
- 723ab47356e49562ac87e1d30424122eb76a0675745b60266f47c8948c028791
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.