Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_channel_1_human_aging_Complete Random
file_name: llama_chat_channel_1_human_aging_Complete Random_5000_5.pt
pruning_style: channel
community: 1
pruning_ratio: 20
dataset_label: human_aging
sparsity_ratio: 20
['tasksource/mmlu', 'human_aging']
finetune: Complete Random
modules_size: 27
modules: ['7_attn.o', '24_gate', '3_attn.k', '13_mlp.down', '24_mlp.down', '23_mlp.down', '19_attn.o', '4_mlp.down', '8_mlp.up', '18_attn.q', '27_mlp.down', '28_attn.k', '15_gate', '29_attn.o', '25_attn.o', '21_attn.k', '9_attn.v', '26_gate', '27_attn.v', '16_attn.o', '8_attn.v', '20_mlp.up', '4_mlp.up', '7_attn.v', '6_attn.q', '22_attn.v', '10_gate']
rank: 4
tags: ['model: llama_chat', 'repo_name: llama_chat_channel_1_human_aging_Complete Random', 'file_name: llama_chat_channel_1_human_aging_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: channel', 'community: 1', 'pruning_ratio: 20', 'dataset_label: human_aging', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'human_aging']", 'finetune: Complete Random', 'modules_size: 27', "modules: ['7_attn.o', '24_gate', '3_attn.k', '13_mlp.down', '24_mlp.down', '23_mlp.down', '19_attn.o', '4_mlp.down', '8_mlp.up', '18_attn.q', '27_mlp.down', '28_attn.k', '15_gate', '29_attn.o', '25_attn.o', '21_attn.k', '9_attn.v', '26_gate', '27_attn.v', '16_attn.o', '8_attn.v', '20_mlp.up', '4_mlp.up', '7_attn.v', '6_attn.q', '22_attn.v', '10_gate']", 'rank: 4']
text-generation-inference
- SHA256:
- 380d1e710bc86b53cb2fb8323d24817de2ea04ea9037f945e652710e2f7cccb5
- Pointer size:
- 135 Bytes
- Size of remote file:
- 2.68 GB
- Xet hash:
- 2926549916ae88515905acabe67c4cf4a82e4154904519321820967dc22f9cf0
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.