File size: 1,980 Bytes
b484d47 | 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 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | {
"attention_probs_dropout_prob": 0.1,
"config_tensor": {
"attn": {
"fc": {
"amp": true,
"factorization": "tt",
"per_decomp_rank_ratio_limit": 0.75,
"ranks": 300,
"build_rank_parameters": false,
"set_scale_factors": false,
"shape": [
16,
8,
8,
8,
8,
16
],
"tensorized": true
},
"sub_layers": {
"amp": true,
"factorization": "tt",
"per_decomp_rank_ratio_limit": 0.75,
"ranks": 300,
"build_rank_parameters": false,
"set_scale_factors": false,
"shape": [
16,
8,
8,
8,
8,
16
],
"tensorized": true
}
},
"embedding": {
"tensorized": false
},
"head": {
"tensorized": false
},
"pff": [
{
"amp": true,
"factorization": "tt",
"per_decomp_rank_ratio_limit": 0.75,
"ranks": 300,
"build_rank_parameters": false,
"set_scale_factors": false,
"shape": [
16,
8,
8,
16,
16,
16
],
"tensorized": true
},
{
"amp": true,
"factorization": "tt",
"per_decomp_rank_ratio_limit": 0.75,
"ranks": 300,
"build_rank_parameters": false,
"set_scale_factors": false,
"shape": [
16,
16,
16,
8,
8,
16
],
"tensorized": true
}
],
"pooler": {
"tensorized": false
}
},
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 512,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_all_encoded_layers": false,
"type_vocab_size": 2,
"vocab_size": 30528
}
|