Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_1_salient_translation_error_detection_All
file_name: vicuna_block_1_salient_translation_error_detection_All_5000_5.pt
pruning_style: block
community: 1
pruning_ratio: 20
dataset_label: salient_translation_error_detection
sparsity_ratio: 20
['tasksource/bigbench', 'salient_translation_error_detection']
finetune: All
modules_size: 13
modules: ['14_attn.v', '17_attn.k', '17_attn.v', '18_attn.o', '19_attn.v', '21_attn.q', '22_attn.q', '23_attn.v', '24_attn.o', '3_attn.o', '5_attn.k', '8_attn.q', '9_attn.o']
rank: 3
tags: ['model: vicuna', 'repo_name: vicuna_block_1_salient_translation_error_detection_All', 'file_name: vicuna_block_1_salient_translation_error_detection_All_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 1', 'pruning_ratio: 20', 'dataset_label: salient_translation_error_detection', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'salient_translation_error_detection']", 'finetune: All', 'modules_size: 13', "modules: ['14_attn.v', '17_attn.k', '17_attn.v', '18_attn.o', '19_attn.v', '21_attn.q', '22_attn.q', '23_attn.v', '24_attn.o', '3_attn.o', '5_attn.k', '8_attn.q', '9_attn.o']", 'rank: 3']
text-generation-inference
- SHA256:
- 3efe461e625739106b2769d592f396ce628c2db48c7371f7ebd48f54bb044fb7
- Pointer size:
- 135 Bytes
- Size of remote file:
- 2.68 GB
- Xet hash:
- f04cbb536489eda23ecd37c1b062f85a27b3a6a84d9828e087bf3912961c4221
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.