Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_block_3_anachronisms_Community
file_name: llama_chat_block_3_anachronisms_Community_5000_5.pt
pruning_style: block
community: 3
pruning_ratio: 20
dataset_label: anachronisms
sparsity_ratio: 20
['tasksource/bigbench', 'anachronisms']
finetune: Community
modules_size: 22
modules: ['11_attn.k', '11_attn.o', '11_attn.v', '12_attn.v', '18_attn.o', '18_attn.v', '19_attn.k', '20_attn.q', '23_attn.q', '25_attn.q', '25_attn.v', '26_attn.q', '27_attn.q', '28_attn.o', '29_attn.o', '29_attn.q', '29_attn.v', '30_attn.q', '7_attn.o', '8_attn.o', '8_attn.q', '8_attn.v']
rank: 1
tags: ['model: llama_chat', 'repo_name: llama_chat_block_3_anachronisms_Community', 'file_name: llama_chat_block_3_anachronisms_Community_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: block', 'community: 3', 'pruning_ratio: 20', 'dataset_label: anachronisms', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'anachronisms']", 'finetune: Community', 'modules_size: 22', "modules: ['11_attn.k', '11_attn.o', '11_attn.v', '12_attn.v', '18_attn.o', '18_attn.v', '19_attn.k', '20_attn.q', '23_attn.q', '25_attn.q', '25_attn.v', '26_attn.q', '27_attn.q', '28_attn.o', '29_attn.o', '29_attn.q', '29_attn.v', '30_attn.q', '7_attn.o', '8_attn.o', '8_attn.q', '8_attn.v']", 'rank: 1']
text-generation-inference
- SHA256:
- beb1963a6d8d27630275c4bcb2f6070f4a14bbe7ac83255046fd241ea0daea34
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4.86 GB
- Xet backed hash:
- 8acd0fdbbdf146163c1fbd1b1be38ec9c68d6cda9679eb4ff84255ab1611bd47
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.