Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_3_jurisprudence_Complete Random
file_name: vicuna_block_3_jurisprudence_Complete Random_5000_5.pt
pruning_style: block
community: 3
pruning_ratio: 20
dataset_label: jurisprudence
sparsity_ratio: 20
['tasksource/mmlu', 'jurisprudence']
finetune: Complete Random
modules_size: 23
modules: ['22_mlp.up', '6_mlp.down', '7_attn.o', '5_attn.o', '8_attn.v', '18_gate', '27_attn.o', '3_mlp.up', '28_mlp.down', '15_attn.q', '5_gate', '10_attn.o', '14_attn.o', '4_attn.q', '27_mlp.up', '12_gate', '6_attn.k', '4_attn.o', '27_mlp.down', '11_attn.k', '24_attn.v', '22_mlp.down', '11_attn.o']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_block_3_jurisprudence_Complete Random', 'file_name: vicuna_block_3_jurisprudence_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 3', 'pruning_ratio: 20', 'dataset_label: jurisprudence', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'jurisprudence']", 'finetune: Complete Random', 'modules_size: 23', "modules: ['22_mlp.up', '6_mlp.down', '7_attn.o', '5_attn.o', '8_attn.v', '18_gate', '27_attn.o', '3_mlp.up', '28_mlp.down', '15_attn.q', '5_gate', '10_attn.o', '14_attn.o', '4_attn.q', '27_mlp.up', '12_gate', '6_attn.k', '4_attn.o', '27_mlp.down', '11_attn.k', '24_attn.v', '22_mlp.down', '11_attn.o']", 'rank: 1']
text-generation-inference
- SHA256:
- 28049e53d3f1ff31325002cf23fb15ef805d384711dfca14b69e148e5c7de94f
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.86 GB
- Xet hash:
- f74f804b12a5eb2d43d7c101c5d1c08619548c26f09e643d16e7b68e95c57407
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.