Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_channel_5_similarities_abstraction_All
file_name: llama_chat_channel_5_similarities_abstraction_All_5000_5.pt
pruning_style: channel
community: 5
pruning_ratio: 20
dataset_label: similarities_abstraction
sparsity_ratio: 20
['tasksource/bigbench', 'similarities_abstraction']
finetune: All
modules_size: 14
modules: ['12_mlp.down', '13_mlp.up', '16_attn.k', '17_attn.k', '21_attn.k', '22_attn.k', '22_attn.q', '26_mlp.up', '27_gate', '29_attn.v', '30_attn.v', '30_mlp.down', '8_attn.q', '9_attn.o']
rank: 2
tags: ['model: llama_chat', 'repo_name: llama_chat_channel_5_similarities_abstraction_All', 'file_name: llama_chat_channel_5_similarities_abstraction_All_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: channel', 'community: 5', 'pruning_ratio: 20', 'dataset_label: similarities_abstraction', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'similarities_abstraction']", 'finetune: All', 'modules_size: 14', "modules: ['12_mlp.down', '13_mlp.up', '16_attn.k', '17_attn.k', '21_attn.k', '22_attn.k', '22_attn.q', '26_mlp.up', '27_gate', '29_attn.v', '30_attn.v', '30_mlp.down', '8_attn.q', '9_attn.o']", 'rank: 2']
text-generation-inference