Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_channel_2_sentence_ambiguity_Complete Random
file_name: llama_channel_2_sentence_ambiguity_Complete Random_5000_5.pt
pruning_style: channel
community: 2
pruning_ratio: 20
dataset_label: sentence_ambiguity
sparsity_ratio: 20
['tasksource/bigbench', 'sentence_ambiguity']
finetune: Complete Random
modules_size: 56
modules: ['9_mlp.up', '18_gate', '10_attn.v', '8_attn.v', '4_attn.q', '30_attn.q', '12_attn.o', '15_attn.v', '10_attn.q', '4_mlp.down', '13_mlp.down', '18_attn.v', '13_attn.q', '27_attn.q', '25_attn.k', '22_mlp.up', '23_gate', '23_attn.v', '25_mlp.up', '9_attn.k', '23_attn.q', '8_gate', '30_gate', '19_gate', '28_attn.k', '13_attn.v', '26_mlp.down', '30_attn.v', '28_attn.q', '28_mlp.down', '19_mlp.down', '18_attn.q', '13_attn.k', '12_mlp.up', '3_attn.q', '12_mlp.down', '24_attn.o', '10_gate', '17_attn.q', '24_gate', '5_attn.o', '4_gate', '21_mlp.up', '26_attn.q', '29_mlp.up', '16_attn.q', '22_attn.v', '19_attn.q', '7_gate', '10_mlp.up', '29_mlp.down', '28_attn.v', '19_attn.k', '23_attn.k', '14_attn.k', '25_gate']
rank: 1
tags: ['model: llama', 'repo_name: llama_channel_2_sentence_ambiguity_Complete Random', 'file_name: llama_channel_2_sentence_ambiguity_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 2', 'pruning_ratio: 20', 'dataset_label: sentence_ambiguity', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'sentence_ambiguity']", 'finetune: Complete Random', 'modules_size: 56', "modules: ['9_mlp.up', '18_gate', '10_attn.v', '8_attn.v', '4_attn.q', '30_attn.q', '12_attn.o', '15_attn.v', '10_attn.q', '4_mlp.down', '13_mlp.down', '18_attn.v', '13_attn.q', '27_attn.q', '25_attn.k', '22_mlp.up', '23_gate', '23_attn.v', '25_mlp.up', '9_attn.k', '23_attn.q', '8_gate', '30_gate', '19_gate', '28_attn.k', '13_attn.v', '26_mlp.down', '30_attn.v', '28_attn.q', '28_mlp.down', '19_mlp.down', '18_attn.q', '13_attn.k', '12_mlp.up', '3_attn.q', '12_mlp.down', '24_attn.o', '10_gate', '17_attn.q', '24_gate', '5_attn.o', '4_gate', '21_mlp.up', '26_attn.q', '29_mlp.up', '16_attn.q', '22_attn.v', '19_attn.q', '7_gate', '10_mlp.up', '29_mlp.down', '28_attn.v', '19_attn.k', '23_attn.k', '14_attn.k', '25_gate']", 'rank: 1']
text-generation-inference
| *.7z filter=lfs diff=lfs merge=lfs -text | |
| *.arrow filter=lfs diff=lfs merge=lfs -text | |
| *.bin filter=lfs diff=lfs merge=lfs -text | |
| *.bz2 filter=lfs diff=lfs merge=lfs -text | |
| *.ckpt filter=lfs diff=lfs merge=lfs -text | |
| *.ftz filter=lfs diff=lfs merge=lfs -text | |
| *.gz filter=lfs diff=lfs merge=lfs -text | |
| *.h5 filter=lfs diff=lfs merge=lfs -text | |
| *.joblib filter=lfs diff=lfs merge=lfs -text | |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text | |
| *.mlmodel filter=lfs diff=lfs merge=lfs -text | |
| *.model filter=lfs diff=lfs merge=lfs -text | |
| *.msgpack filter=lfs diff=lfs merge=lfs -text | |
| *.npy filter=lfs diff=lfs merge=lfs -text | |
| *.npz filter=lfs diff=lfs merge=lfs -text | |
| *.onnx filter=lfs diff=lfs merge=lfs -text | |
| *.ot filter=lfs diff=lfs merge=lfs -text | |
| *.parquet filter=lfs diff=lfs merge=lfs -text | |
| *.pb filter=lfs diff=lfs merge=lfs -text | |
| *.pickle filter=lfs diff=lfs merge=lfs -text | |
| *.pkl filter=lfs diff=lfs merge=lfs -text | |
| *.pt filter=lfs diff=lfs merge=lfs -text | |
| *.pth filter=lfs diff=lfs merge=lfs -text | |
| *.rar filter=lfs diff=lfs merge=lfs -text | |
| *.safetensors filter=lfs diff=lfs merge=lfs -text | |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text | |
| *.tar.* filter=lfs diff=lfs merge=lfs -text | |
| *.tar filter=lfs diff=lfs merge=lfs -text | |
| *.tflite filter=lfs diff=lfs merge=lfs -text | |
| *.tgz filter=lfs diff=lfs merge=lfs -text | |
| *.wasm filter=lfs diff=lfs merge=lfs -text | |
| *.xz filter=lfs diff=lfs merge=lfs -text | |
| *.zip filter=lfs diff=lfs merge=lfs -text | |
| *.zst filter=lfs diff=lfs merge=lfs -text | |
| *tfevents* filter=lfs diff=lfs merge=lfs -text | |