Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_block_2_gre_reading_comprehension_Community
file_name: llama_block_2_gre_reading_comprehension_Community_5000_5.pt
pruning_style: block
community: 2
pruning_ratio: 20
dataset_label: gre_reading_comprehension
sparsity_ratio: 20
['tasksource/bigbench', 'gre_reading_comprehension']
finetune: Community
modules_size: 28
modules: ['11_attn.o', '11_attn.v', '12_attn.k', '12_attn.o', '13_attn.v', '15_attn.q', '17_attn.o', '18_attn.v', '19_attn.k', '19_attn.o', '19_attn.q', '21_attn.q', '23_attn.q', '24_attn.v', '25_attn.q', '26_attn.o', '26_attn.v', '27_attn.q', '27_attn.v', '29_attn.v', '4_attn.q', '4_attn.v', '5_attn.k', '5_attn.o', '5_attn.v', '8_attn.k', '9_attn.o', '9_attn.q']
rank: 1
tags: ['model: llama', 'repo_name: llama_block_2_gre_reading_comprehension_Community', 'file_name: llama_block_2_gre_reading_comprehension_Community_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: gre_reading_comprehension', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'gre_reading_comprehension']", 'finetune: Community', 'modules_size: 28', "modules: ['11_attn.o', '11_attn.v', '12_attn.k', '12_attn.o', '13_attn.v', '15_attn.q', '17_attn.o', '18_attn.v', '19_attn.k', '19_attn.o', '19_attn.q', '21_attn.q', '23_attn.q', '24_attn.v', '25_attn.q', '26_attn.o', '26_attn.v', '27_attn.q', '27_attn.v', '29_attn.v', '4_attn.q', '4_attn.v', '5_attn.k', '5_attn.o', '5_attn.v', '8_attn.k', '9_attn.o', '9_attn.q']", 'rank: 1']
text-generation-inference
- SHA256:
- 8c1e1a7ec87f204891eda685ad2502c035897754dab2e2a052d93aa4959f070b
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.84 GB
- Xet hash:
- b2c8683c705bbb5662cfd9cf96f572ea2cc5c66028c30ea8f4dbc2859bde3ba9
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.