Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_block_1_language_identification_Complete Random
file_name: llama_block_1_language_identification_Complete Random_5000_5.pt
pruning_style: block
community: 1
pruning_ratio: 20
dataset_label: language_identification
sparsity_ratio: 20
['tasksource/bigbench', 'language_identification']
finetune: Complete Random
modules_size: 27
modules: ['26_mlp.up', '18_mlp.down', '28_mlp.up', '15_attn.v', '16_attn.v', '9_gate', '19_gate', '20_mlp.down', '7_mlp.up', '7_mlp.down', '30_gate', '9_mlp.up', '16_mlp.up', '6_mlp.down', '10_attn.o', '4_gate', '3_attn.o', '11_attn.q', '21_attn.k', '14_gate', '26_gate', '21_mlp.down', '29_attn.k', '8_attn.q', '5_mlp.down', '22_mlp.down', '13_mlp.down']
rank: 1
tags: ['model: llama', 'repo_name: llama_block_1_language_identification_Complete Random', 'file_name: llama_block_1_language_identification_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: block', 'community: 1', 'pruning_ratio: 20', 'dataset_label: language_identification', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'language_identification']", 'finetune: Complete Random', 'modules_size: 27', "modules: ['26_mlp.up', '18_mlp.down', '28_mlp.up', '15_attn.v', '16_attn.v', '9_gate', '19_gate', '20_mlp.down', '7_mlp.up', '7_mlp.down', '30_gate', '9_mlp.up', '16_mlp.up', '6_mlp.down', '10_attn.o', '4_gate', '3_attn.o', '11_attn.q', '21_attn.k', '14_gate', '26_gate', '21_mlp.down', '29_attn.k', '8_attn.q', '5_mlp.down', '22_mlp.down', '13_mlp.down']", 'rank: 1']
text-generation-inference
- SHA256:
- c0573752142deeb9d54d3a54f0905a3b6fa85931fc0a0f28d055602423c1542b
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.86 GB
- Xet hash:
- c9afc9b8810ba3808fff0dac80dbbce976baa90bf83c2e2e9fd2e77d66d190ab
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.