Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_2_elementary_math_qa_Complete Random
file_name: vicuna_block_2_elementary_math_qa_Complete Random_5000_5.pt
pruning_style: block
community: 2
pruning_ratio: 20
dataset_label: elementary_math_qa
sparsity_ratio: 20
['tasksource/bigbench', 'elementary_math_qa']
finetune: Complete Random
modules_size: 21
modules: ['22_gate', '25_mlp.up', '10_attn.k', '24_mlp.up', '14_gate', '9_gate', '14_attn.k', '14_attn.q', '22_mlp.up', '21_attn.k', '24_gate', '9_attn.o', '27_mlp.down', '12_mlp.up', '14_mlp.up', '3_mlp.up', '28_attn.k', '30_mlp.up', '24_mlp.down', '22_attn.q', '20_attn.k']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_block_2_elementary_math_qa_Complete Random', 'file_name: vicuna_block_2_elementary_math_qa_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: elementary_math_qa', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'elementary_math_qa']", 'finetune: Complete Random', 'modules_size: 21', "modules: ['22_gate', '25_mlp.up', '10_attn.k', '24_mlp.up', '14_gate', '9_gate', '14_attn.k', '14_attn.q', '22_mlp.up', '21_attn.k', '24_gate', '9_attn.o', '27_mlp.down', '12_mlp.up', '14_mlp.up', '3_mlp.up', '28_attn.k', '30_mlp.up', '24_mlp.down', '22_attn.q', '20_attn.k']", 'rank: 1']
text-generation-inference
File size: 719 Bytes
0f32617 | 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
}
|