Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_0_implicatures_Complete Random
file_name: vicuna_block_0_implicatures_Complete Random_5000_5.pt
pruning_style: block
community: 0
pruning_ratio: 20
dataset_label: implicatures
sparsity_ratio: 20
['tasksource/bigbench', 'implicatures']
finetune: Complete Random
modules_size: 38
modules: ['26_mlp.up', '13_attn.q', '26_attn.q', '9_attn.o', '10_mlp.down', '18_mlp.down', '27_attn.o', '16_mlp.down', '16_gate', '3_attn.v', '19_attn.v', '8_attn.k', '28_mlp.up', '29_gate', '29_attn.q', '13_mlp.up', '19_gate', '30_mlp.up', '15_gate', '25_attn.k', '11_mlp.down', '15_attn.k', '18_attn.o', '30_attn.v', '24_attn.o', '6_mlp.up', '5_gate', '22_attn.q', '29_mlp.down', '15_attn.q', '25_mlp.up', '17_attn.q', '14_gate', '7_attn.q', '27_mlp.up', '6_attn.q', '13_attn.o', '3_gate']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_block_0_implicatures_Complete Random', 'file_name: vicuna_block_0_implicatures_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 0', 'pruning_ratio: 20', 'dataset_label: implicatures', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'implicatures']", 'finetune: Complete Random', 'modules_size: 38', "modules: ['26_mlp.up', '13_attn.q', '26_attn.q', '9_attn.o', '10_mlp.down', '18_mlp.down', '27_attn.o', '16_mlp.down', '16_gate', '3_attn.v', '19_attn.v', '8_attn.k', '28_mlp.up', '29_gate', '29_attn.q', '13_mlp.up', '19_gate', '30_mlp.up', '15_gate', '25_attn.k', '11_mlp.down', '15_attn.k', '18_attn.o', '30_attn.v', '24_attn.o', '6_mlp.up', '5_gate', '22_attn.q', '29_mlp.down', '15_attn.q', '25_mlp.up', '17_attn.q', '14_gate', '7_attn.q', '27_mlp.up', '6_attn.q', '13_attn.o', '3_gate']", 'rank: 1']
text-generation-inference
File size: 719 Bytes
8274e83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | {
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"do_sample": null,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.52.4",
"use_cache": true,
"vocab_size": 32000
}
|