Commit
•
e3517e1
1
Parent(s):
86a6956
增加bge
Browse files
bge-base-en-v1.5/bert4torch_config.json
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"hidden_act": "gelu",
|
| 4 |
+
"hidden_dropout_prob": 0.1,
|
| 5 |
+
"hidden_size": 768,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 3072,
|
| 8 |
+
"layer_norm_eps": 1e-12,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"model": "bert",
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"bos_token_id": 0,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"type_vocab_size": 2,
|
| 18 |
+
"vocab_size": 30522,
|
| 19 |
+
"with_pool": true,
|
| 20 |
+
"pool_strategy": "cls",
|
| 21 |
+
"norm_mode": "torch_buildin",
|
| 22 |
+
"mapping": {
|
| 23 |
+
"embeddings.word_embeddings.weight": "embeddings.word_embeddings.weight",
|
| 24 |
+
"embeddings.position_embeddings.weight": "embeddings.position_embeddings.weight",
|
| 25 |
+
"embeddings.segment_embeddings.weight": "embeddings.token_type_embeddings.weight",
|
| 26 |
+
"embeddings.layerNorm.weight": "embeddings.LayerNorm.weight",
|
| 27 |
+
"embeddings.layerNorm.bias": "embeddings.LayerNorm.bias",
|
| 28 |
+
"pooler.weight": "pooler.dense.weight",
|
| 29 |
+
"pooler.bias": "pooler.dense.bias",
|
| 30 |
+
"encoderLayer.0.multiHeadAttention.q.weight": "encoder.layer.0.attention.self.query.weight",
|
| 31 |
+
"encoderLayer.0.multiHeadAttention.q.bias": "encoder.layer.0.attention.self.query.bias",
|
| 32 |
+
"encoderLayer.0.multiHeadAttention.k.weight": "encoder.layer.0.attention.self.key.weight",
|
| 33 |
+
"encoderLayer.0.multiHeadAttention.k.bias": "encoder.layer.0.attention.self.key.bias",
|
| 34 |
+
"encoderLayer.0.multiHeadAttention.v.weight": "encoder.layer.0.attention.self.value.weight",
|
| 35 |
+
"encoderLayer.0.multiHeadAttention.v.bias": "encoder.layer.0.attention.self.value.bias",
|
| 36 |
+
"encoderLayer.0.multiHeadAttention.o.weight": "encoder.layer.0.attention.output.dense.weight",
|
| 37 |
+
"encoderLayer.0.multiHeadAttention.o.bias": "encoder.layer.0.attention.output.dense.bias",
|
| 38 |
+
"encoderLayer.0.attnLayerNorm.weight": "encoder.layer.0.attention.output.LayerNorm.weight",
|
| 39 |
+
"encoderLayer.0.attnLayerNorm.bias": "encoder.layer.0.attention.output.LayerNorm.bias",
|
| 40 |
+
"encoderLayer.0.feedForward.intermediateDense.weight": "encoder.layer.0.intermediate.dense.weight",
|
| 41 |
+
"encoderLayer.0.feedForward.intermediateDense.bias": "encoder.layer.0.intermediate.dense.bias",
|
| 42 |
+
"encoderLayer.0.feedForward.outputDense.weight": "encoder.layer.0.output.dense.weight",
|
| 43 |
+
"encoderLayer.0.feedForward.outputDense.bias": "encoder.layer.0.output.dense.bias",
|
| 44 |
+
"encoderLayer.0.ffnLayerNorm.weight": "encoder.layer.0.output.LayerNorm.weight",
|
| 45 |
+
"encoderLayer.0.ffnLayerNorm.bias": "encoder.layer.0.output.LayerNorm.bias",
|
| 46 |
+
"encoderLayer.1.multiHeadAttention.q.weight": "encoder.layer.1.attention.self.query.weight",
|
| 47 |
+
"encoderLayer.1.multiHeadAttention.q.bias": "encoder.layer.1.attention.self.query.bias",
|
| 48 |
+
"encoderLayer.1.multiHeadAttention.k.weight": "encoder.layer.1.attention.self.key.weight",
|
| 49 |
+
"encoderLayer.1.multiHeadAttention.k.bias": "encoder.layer.1.attention.self.key.bias",
|
| 50 |
+
"encoderLayer.1.multiHeadAttention.v.weight": "encoder.layer.1.attention.self.value.weight",
|
| 51 |
+
"encoderLayer.1.multiHeadAttention.v.bias": "encoder.layer.1.attention.self.value.bias",
|
| 52 |
+
"encoderLayer.1.multiHeadAttention.o.weight": "encoder.layer.1.attention.output.dense.weight",
|
| 53 |
+
"encoderLayer.1.multiHeadAttention.o.bias": "encoder.layer.1.attention.output.dense.bias",
|
| 54 |
+
"encoderLayer.1.attnLayerNorm.weight": "encoder.layer.1.attention.output.LayerNorm.weight",
|
| 55 |
+
"encoderLayer.1.attnLayerNorm.bias": "encoder.layer.1.attention.output.LayerNorm.bias",
|
| 56 |
+
"encoderLayer.1.feedForward.intermediateDense.weight": "encoder.layer.1.intermediate.dense.weight",
|
| 57 |
+
"encoderLayer.1.feedForward.intermediateDense.bias": "encoder.layer.1.intermediate.dense.bias",
|
| 58 |
+
"encoderLayer.1.feedForward.outputDense.weight": "encoder.layer.1.output.dense.weight",
|
| 59 |
+
"encoderLayer.1.feedForward.outputDense.bias": "encoder.layer.1.output.dense.bias",
|
| 60 |
+
"encoderLayer.1.ffnLayerNorm.weight": "encoder.layer.1.output.LayerNorm.weight",
|
| 61 |
+
"encoderLayer.1.ffnLayerNorm.bias": "encoder.layer.1.output.LayerNorm.bias",
|
| 62 |
+
"encoderLayer.2.multiHeadAttention.q.weight": "encoder.layer.2.attention.self.query.weight",
|
| 63 |
+
"encoderLayer.2.multiHeadAttention.q.bias": "encoder.layer.2.attention.self.query.bias",
|
| 64 |
+
"encoderLayer.2.multiHeadAttention.k.weight": "encoder.layer.2.attention.self.key.weight",
|
| 65 |
+
"encoderLayer.2.multiHeadAttention.k.bias": "encoder.layer.2.attention.self.key.bias",
|
| 66 |
+
"encoderLayer.2.multiHeadAttention.v.weight": "encoder.layer.2.attention.self.value.weight",
|
| 67 |
+
"encoderLayer.2.multiHeadAttention.v.bias": "encoder.layer.2.attention.self.value.bias",
|
| 68 |
+
"encoderLayer.2.multiHeadAttention.o.weight": "encoder.layer.2.attention.output.dense.weight",
|
| 69 |
+
"encoderLayer.2.multiHeadAttention.o.bias": "encoder.layer.2.attention.output.dense.bias",
|
| 70 |
+
"encoderLayer.2.attnLayerNorm.weight": "encoder.layer.2.attention.output.LayerNorm.weight",
|
| 71 |
+
"encoderLayer.2.attnLayerNorm.bias": "encoder.layer.2.attention.output.LayerNorm.bias",
|
| 72 |
+
"encoderLayer.2.feedForward.intermediateDense.weight": "encoder.layer.2.intermediate.dense.weight",
|
| 73 |
+
"encoderLayer.2.feedForward.intermediateDense.bias": "encoder.layer.2.intermediate.dense.bias",
|
| 74 |
+
"encoderLayer.2.feedForward.outputDense.weight": "encoder.layer.2.output.dense.weight",
|
| 75 |
+
"encoderLayer.2.feedForward.outputDense.bias": "encoder.layer.2.output.dense.bias",
|
| 76 |
+
"encoderLayer.2.ffnLayerNorm.weight": "encoder.layer.2.output.LayerNorm.weight",
|
| 77 |
+
"encoderLayer.2.ffnLayerNorm.bias": "encoder.layer.2.output.LayerNorm.bias",
|
| 78 |
+
"encoderLayer.3.multiHeadAttention.q.weight": "encoder.layer.3.attention.self.query.weight",
|
| 79 |
+
"encoderLayer.3.multiHeadAttention.q.bias": "encoder.layer.3.attention.self.query.bias",
|
| 80 |
+
"encoderLayer.3.multiHeadAttention.k.weight": "encoder.layer.3.attention.self.key.weight",
|
| 81 |
+
"encoderLayer.3.multiHeadAttention.k.bias": "encoder.layer.3.attention.self.key.bias",
|
| 82 |
+
"encoderLayer.3.multiHeadAttention.v.weight": "encoder.layer.3.attention.self.value.weight",
|
| 83 |
+
"encoderLayer.3.multiHeadAttention.v.bias": "encoder.layer.3.attention.self.value.bias",
|
| 84 |
+
"encoderLayer.3.multiHeadAttention.o.weight": "encoder.layer.3.attention.output.dense.weight",
|
| 85 |
+
"encoderLayer.3.multiHeadAttention.o.bias": "encoder.layer.3.attention.output.dense.bias",
|
| 86 |
+
"encoderLayer.3.attnLayerNorm.weight": "encoder.layer.3.attention.output.LayerNorm.weight",
|
| 87 |
+
"encoderLayer.3.attnLayerNorm.bias": "encoder.layer.3.attention.output.LayerNorm.bias",
|
| 88 |
+
"encoderLayer.3.feedForward.intermediateDense.weight": "encoder.layer.3.intermediate.dense.weight",
|
| 89 |
+
"encoderLayer.3.feedForward.intermediateDense.bias": "encoder.layer.3.intermediate.dense.bias",
|
| 90 |
+
"encoderLayer.3.feedForward.outputDense.weight": "encoder.layer.3.output.dense.weight",
|
| 91 |
+
"encoderLayer.3.feedForward.outputDense.bias": "encoder.layer.3.output.dense.bias",
|
| 92 |
+
"encoderLayer.3.ffnLayerNorm.weight": "encoder.layer.3.output.LayerNorm.weight",
|
| 93 |
+
"encoderLayer.3.ffnLayerNorm.bias": "encoder.layer.3.output.LayerNorm.bias",
|
| 94 |
+
"encoderLayer.4.multiHeadAttention.q.weight": "encoder.layer.4.attention.self.query.weight",
|
| 95 |
+
"encoderLayer.4.multiHeadAttention.q.bias": "encoder.layer.4.attention.self.query.bias",
|
| 96 |
+
"encoderLayer.4.multiHeadAttention.k.weight": "encoder.layer.4.attention.self.key.weight",
|
| 97 |
+
"encoderLayer.4.multiHeadAttention.k.bias": "encoder.layer.4.attention.self.key.bias",
|
| 98 |
+
"encoderLayer.4.multiHeadAttention.v.weight": "encoder.layer.4.attention.self.value.weight",
|
| 99 |
+
"encoderLayer.4.multiHeadAttention.v.bias": "encoder.layer.4.attention.self.value.bias",
|
| 100 |
+
"encoderLayer.4.multiHeadAttention.o.weight": "encoder.layer.4.attention.output.dense.weight",
|
| 101 |
+
"encoderLayer.4.multiHeadAttention.o.bias": "encoder.layer.4.attention.output.dense.bias",
|
| 102 |
+
"encoderLayer.4.attnLayerNorm.weight": "encoder.layer.4.attention.output.LayerNorm.weight",
|
| 103 |
+
"encoderLayer.4.attnLayerNorm.bias": "encoder.layer.4.attention.output.LayerNorm.bias",
|
| 104 |
+
"encoderLayer.4.feedForward.intermediateDense.weight": "encoder.layer.4.intermediate.dense.weight",
|
| 105 |
+
"encoderLayer.4.feedForward.intermediateDense.bias": "encoder.layer.4.intermediate.dense.bias",
|
| 106 |
+
"encoderLayer.4.feedForward.outputDense.weight": "encoder.layer.4.output.dense.weight",
|
| 107 |
+
"encoderLayer.4.feedForward.outputDense.bias": "encoder.layer.4.output.dense.bias",
|
| 108 |
+
"encoderLayer.4.ffnLayerNorm.weight": "encoder.layer.4.output.LayerNorm.weight",
|
| 109 |
+
"encoderLayer.4.ffnLayerNorm.bias": "encoder.layer.4.output.LayerNorm.bias",
|
| 110 |
+
"encoderLayer.5.multiHeadAttention.q.weight": "encoder.layer.5.attention.self.query.weight",
|
| 111 |
+
"encoderLayer.5.multiHeadAttention.q.bias": "encoder.layer.5.attention.self.query.bias",
|
| 112 |
+
"encoderLayer.5.multiHeadAttention.k.weight": "encoder.layer.5.attention.self.key.weight",
|
| 113 |
+
"encoderLayer.5.multiHeadAttention.k.bias": "encoder.layer.5.attention.self.key.bias",
|
| 114 |
+
"encoderLayer.5.multiHeadAttention.v.weight": "encoder.layer.5.attention.self.value.weight",
|
| 115 |
+
"encoderLayer.5.multiHeadAttention.v.bias": "encoder.layer.5.attention.self.value.bias",
|
| 116 |
+
"encoderLayer.5.multiHeadAttention.o.weight": "encoder.layer.5.attention.output.dense.weight",
|
| 117 |
+
"encoderLayer.5.multiHeadAttention.o.bias": "encoder.layer.5.attention.output.dense.bias",
|
| 118 |
+
"encoderLayer.5.attnLayerNorm.weight": "encoder.layer.5.attention.output.LayerNorm.weight",
|
| 119 |
+
"encoderLayer.5.attnLayerNorm.bias": "encoder.layer.5.attention.output.LayerNorm.bias",
|
| 120 |
+
"encoderLayer.5.feedForward.intermediateDense.weight": "encoder.layer.5.intermediate.dense.weight",
|
| 121 |
+
"encoderLayer.5.feedForward.intermediateDense.bias": "encoder.layer.5.intermediate.dense.bias",
|
| 122 |
+
"encoderLayer.5.feedForward.outputDense.weight": "encoder.layer.5.output.dense.weight",
|
| 123 |
+
"encoderLayer.5.feedForward.outputDense.bias": "encoder.layer.5.output.dense.bias",
|
| 124 |
+
"encoderLayer.5.ffnLayerNorm.weight": "encoder.layer.5.output.LayerNorm.weight",
|
| 125 |
+
"encoderLayer.5.ffnLayerNorm.bias": "encoder.layer.5.output.LayerNorm.bias",
|
| 126 |
+
"encoderLayer.6.multiHeadAttention.q.weight": "encoder.layer.6.attention.self.query.weight",
|
| 127 |
+
"encoderLayer.6.multiHeadAttention.q.bias": "encoder.layer.6.attention.self.query.bias",
|
| 128 |
+
"encoderLayer.6.multiHeadAttention.k.weight": "encoder.layer.6.attention.self.key.weight",
|
| 129 |
+
"encoderLayer.6.multiHeadAttention.k.bias": "encoder.layer.6.attention.self.key.bias",
|
| 130 |
+
"encoderLayer.6.multiHeadAttention.v.weight": "encoder.layer.6.attention.self.value.weight",
|
| 131 |
+
"encoderLayer.6.multiHeadAttention.v.bias": "encoder.layer.6.attention.self.value.bias",
|
| 132 |
+
"encoderLayer.6.multiHeadAttention.o.weight": "encoder.layer.6.attention.output.dense.weight",
|
| 133 |
+
"encoderLayer.6.multiHeadAttention.o.bias": "encoder.layer.6.attention.output.dense.bias",
|
| 134 |
+
"encoderLayer.6.attnLayerNorm.weight": "encoder.layer.6.attention.output.LayerNorm.weight",
|
| 135 |
+
"encoderLayer.6.attnLayerNorm.bias": "encoder.layer.6.attention.output.LayerNorm.bias",
|
| 136 |
+
"encoderLayer.6.feedForward.intermediateDense.weight": "encoder.layer.6.intermediate.dense.weight",
|
| 137 |
+
"encoderLayer.6.feedForward.intermediateDense.bias": "encoder.layer.6.intermediate.dense.bias",
|
| 138 |
+
"encoderLayer.6.feedForward.outputDense.weight": "encoder.layer.6.output.dense.weight",
|
| 139 |
+
"encoderLayer.6.feedForward.outputDense.bias": "encoder.layer.6.output.dense.bias",
|
| 140 |
+
"encoderLayer.6.ffnLayerNorm.weight": "encoder.layer.6.output.LayerNorm.weight",
|
| 141 |
+
"encoderLayer.6.ffnLayerNorm.bias": "encoder.layer.6.output.LayerNorm.bias",
|
| 142 |
+
"encoderLayer.7.multiHeadAttention.q.weight": "encoder.layer.7.attention.self.query.weight",
|
| 143 |
+
"encoderLayer.7.multiHeadAttention.q.bias": "encoder.layer.7.attention.self.query.bias",
|
| 144 |
+
"encoderLayer.7.multiHeadAttention.k.weight": "encoder.layer.7.attention.self.key.weight",
|
| 145 |
+
"encoderLayer.7.multiHeadAttention.k.bias": "encoder.layer.7.attention.self.key.bias",
|
| 146 |
+
"encoderLayer.7.multiHeadAttention.v.weight": "encoder.layer.7.attention.self.value.weight",
|
| 147 |
+
"encoderLayer.7.multiHeadAttention.v.bias": "encoder.layer.7.attention.self.value.bias",
|
| 148 |
+
"encoderLayer.7.multiHeadAttention.o.weight": "encoder.layer.7.attention.output.dense.weight",
|
| 149 |
+
"encoderLayer.7.multiHeadAttention.o.bias": "encoder.layer.7.attention.output.dense.bias",
|
| 150 |
+
"encoderLayer.7.attnLayerNorm.weight": "encoder.layer.7.attention.output.LayerNorm.weight",
|
| 151 |
+
"encoderLayer.7.attnLayerNorm.bias": "encoder.layer.7.attention.output.LayerNorm.bias",
|
| 152 |
+
"encoderLayer.7.feedForward.intermediateDense.weight": "encoder.layer.7.intermediate.dense.weight",
|
| 153 |
+
"encoderLayer.7.feedForward.intermediateDense.bias": "encoder.layer.7.intermediate.dense.bias",
|
| 154 |
+
"encoderLayer.7.feedForward.outputDense.weight": "encoder.layer.7.output.dense.weight",
|
| 155 |
+
"encoderLayer.7.feedForward.outputDense.bias": "encoder.layer.7.output.dense.bias",
|
| 156 |
+
"encoderLayer.7.ffnLayerNorm.weight": "encoder.layer.7.output.LayerNorm.weight",
|
| 157 |
+
"encoderLayer.7.ffnLayerNorm.bias": "encoder.layer.7.output.LayerNorm.bias",
|
| 158 |
+
"encoderLayer.8.multiHeadAttention.q.weight": "encoder.layer.8.attention.self.query.weight",
|
| 159 |
+
"encoderLayer.8.multiHeadAttention.q.bias": "encoder.layer.8.attention.self.query.bias",
|
| 160 |
+
"encoderLayer.8.multiHeadAttention.k.weight": "encoder.layer.8.attention.self.key.weight",
|
| 161 |
+
"encoderLayer.8.multiHeadAttention.k.bias": "encoder.layer.8.attention.self.key.bias",
|
| 162 |
+
"encoderLayer.8.multiHeadAttention.v.weight": "encoder.layer.8.attention.self.value.weight",
|
| 163 |
+
"encoderLayer.8.multiHeadAttention.v.bias": "encoder.layer.8.attention.self.value.bias",
|
| 164 |
+
"encoderLayer.8.multiHeadAttention.o.weight": "encoder.layer.8.attention.output.dense.weight",
|
| 165 |
+
"encoderLayer.8.multiHeadAttention.o.bias": "encoder.layer.8.attention.output.dense.bias",
|
| 166 |
+
"encoderLayer.8.attnLayerNorm.weight": "encoder.layer.8.attention.output.LayerNorm.weight",
|
| 167 |
+
"encoderLayer.8.attnLayerNorm.bias": "encoder.layer.8.attention.output.LayerNorm.bias",
|
| 168 |
+
"encoderLayer.8.feedForward.intermediateDense.weight": "encoder.layer.8.intermediate.dense.weight",
|
| 169 |
+
"encoderLayer.8.feedForward.intermediateDense.bias": "encoder.layer.8.intermediate.dense.bias",
|
| 170 |
+
"encoderLayer.8.feedForward.outputDense.weight": "encoder.layer.8.output.dense.weight",
|
| 171 |
+
"encoderLayer.8.feedForward.outputDense.bias": "encoder.layer.8.output.dense.bias",
|
| 172 |
+
"encoderLayer.8.ffnLayerNorm.weight": "encoder.layer.8.output.LayerNorm.weight",
|
| 173 |
+
"encoderLayer.8.ffnLayerNorm.bias": "encoder.layer.8.output.LayerNorm.bias",
|
| 174 |
+
"encoderLayer.9.multiHeadAttention.q.weight": "encoder.layer.9.attention.self.query.weight",
|
| 175 |
+
"encoderLayer.9.multiHeadAttention.q.bias": "encoder.layer.9.attention.self.query.bias",
|
| 176 |
+
"encoderLayer.9.multiHeadAttention.k.weight": "encoder.layer.9.attention.self.key.weight",
|
| 177 |
+
"encoderLayer.9.multiHeadAttention.k.bias": "encoder.layer.9.attention.self.key.bias",
|
| 178 |
+
"encoderLayer.9.multiHeadAttention.v.weight": "encoder.layer.9.attention.self.value.weight",
|
| 179 |
+
"encoderLayer.9.multiHeadAttention.v.bias": "encoder.layer.9.attention.self.value.bias",
|
| 180 |
+
"encoderLayer.9.multiHeadAttention.o.weight": "encoder.layer.9.attention.output.dense.weight",
|
| 181 |
+
"encoderLayer.9.multiHeadAttention.o.bias": "encoder.layer.9.attention.output.dense.bias",
|
| 182 |
+
"encoderLayer.9.attnLayerNorm.weight": "encoder.layer.9.attention.output.LayerNorm.weight",
|
| 183 |
+
"encoderLayer.9.attnLayerNorm.bias": "encoder.layer.9.attention.output.LayerNorm.bias",
|
| 184 |
+
"encoderLayer.9.feedForward.intermediateDense.weight": "encoder.layer.9.intermediate.dense.weight",
|
| 185 |
+
"encoderLayer.9.feedForward.intermediateDense.bias": "encoder.layer.9.intermediate.dense.bias",
|
| 186 |
+
"encoderLayer.9.feedForward.outputDense.weight": "encoder.layer.9.output.dense.weight",
|
| 187 |
+
"encoderLayer.9.feedForward.outputDense.bias": "encoder.layer.9.output.dense.bias",
|
| 188 |
+
"encoderLayer.9.ffnLayerNorm.weight": "encoder.layer.9.output.LayerNorm.weight",
|
| 189 |
+
"encoderLayer.9.ffnLayerNorm.bias": "encoder.layer.9.output.LayerNorm.bias",
|
| 190 |
+
"encoderLayer.10.multiHeadAttention.q.weight": "encoder.layer.10.attention.self.query.weight",
|
| 191 |
+
"encoderLayer.10.multiHeadAttention.q.bias": "encoder.layer.10.attention.self.query.bias",
|
| 192 |
+
"encoderLayer.10.multiHeadAttention.k.weight": "encoder.layer.10.attention.self.key.weight",
|
| 193 |
+
"encoderLayer.10.multiHeadAttention.k.bias": "encoder.layer.10.attention.self.key.bias",
|
| 194 |
+
"encoderLayer.10.multiHeadAttention.v.weight": "encoder.layer.10.attention.self.value.weight",
|
| 195 |
+
"encoderLayer.10.multiHeadAttention.v.bias": "encoder.layer.10.attention.self.value.bias",
|
| 196 |
+
"encoderLayer.10.multiHeadAttention.o.weight": "encoder.layer.10.attention.output.dense.weight",
|
| 197 |
+
"encoderLayer.10.multiHeadAttention.o.bias": "encoder.layer.10.attention.output.dense.bias",
|
| 198 |
+
"encoderLayer.10.attnLayerNorm.weight": "encoder.layer.10.attention.output.LayerNorm.weight",
|
| 199 |
+
"encoderLayer.10.attnLayerNorm.bias": "encoder.layer.10.attention.output.LayerNorm.bias",
|
| 200 |
+
"encoderLayer.10.feedForward.intermediateDense.weight": "encoder.layer.10.intermediate.dense.weight",
|
| 201 |
+
"encoderLayer.10.feedForward.intermediateDense.bias": "encoder.layer.10.intermediate.dense.bias",
|
| 202 |
+
"encoderLayer.10.feedForward.outputDense.weight": "encoder.layer.10.output.dense.weight",
|
| 203 |
+
"encoderLayer.10.feedForward.outputDense.bias": "encoder.layer.10.output.dense.bias",
|
| 204 |
+
"encoderLayer.10.ffnLayerNorm.weight": "encoder.layer.10.output.LayerNorm.weight",
|
| 205 |
+
"encoderLayer.10.ffnLayerNorm.bias": "encoder.layer.10.output.LayerNorm.bias",
|
| 206 |
+
"encoderLayer.11.multiHeadAttention.q.weight": "encoder.layer.11.attention.self.query.weight",
|
| 207 |
+
"encoderLayer.11.multiHeadAttention.q.bias": "encoder.layer.11.attention.self.query.bias",
|
| 208 |
+
"encoderLayer.11.multiHeadAttention.k.weight": "encoder.layer.11.attention.self.key.weight",
|
| 209 |
+
"encoderLayer.11.multiHeadAttention.k.bias": "encoder.layer.11.attention.self.key.bias",
|
| 210 |
+
"encoderLayer.11.multiHeadAttention.v.weight": "encoder.layer.11.attention.self.value.weight",
|
| 211 |
+
"encoderLayer.11.multiHeadAttention.v.bias": "encoder.layer.11.attention.self.value.bias",
|
| 212 |
+
"encoderLayer.11.multiHeadAttention.o.weight": "encoder.layer.11.attention.output.dense.weight",
|
| 213 |
+
"encoderLayer.11.multiHeadAttention.o.bias": "encoder.layer.11.attention.output.dense.bias",
|
| 214 |
+
"encoderLayer.11.attnLayerNorm.weight": "encoder.layer.11.attention.output.LayerNorm.weight",
|
| 215 |
+
"encoderLayer.11.attnLayerNorm.bias": "encoder.layer.11.attention.output.LayerNorm.bias",
|
| 216 |
+
"encoderLayer.11.feedForward.intermediateDense.weight": "encoder.layer.11.intermediate.dense.weight",
|
| 217 |
+
"encoderLayer.11.feedForward.intermediateDense.bias": "encoder.layer.11.intermediate.dense.bias",
|
| 218 |
+
"encoderLayer.11.feedForward.outputDense.weight": "encoder.layer.11.output.dense.weight",
|
| 219 |
+
"encoderLayer.11.feedForward.outputDense.bias": "encoder.layer.11.output.dense.bias",
|
| 220 |
+
"encoderLayer.11.ffnLayerNorm.weight": "encoder.layer.11.output.LayerNorm.weight",
|
| 221 |
+
"encoderLayer.11.ffnLayerNorm.bias": "encoder.layer.11.output.LayerNorm.bias"
|
| 222 |
+
}
|
| 223 |
+
}
|
bge-base-zh-v1.5/bert4torch_config.json
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"hidden_act": "gelu",
|
| 4 |
+
"hidden_dropout_prob": 0.1,
|
| 5 |
+
"hidden_size": 768,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 3072,
|
| 8 |
+
"layer_norm_eps": 1e-12,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"model": "bert",
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"bos_token_id": 0,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"type_vocab_size": 2,
|
| 18 |
+
"vocab_size": 21128,
|
| 19 |
+
"with_pool": true,
|
| 20 |
+
"pool_strategy": "cls",
|
| 21 |
+
"norm_mode": "torch_buildin",
|
| 22 |
+
"mapping": {
|
| 23 |
+
"embeddings.word_embeddings.weight": "embeddings.word_embeddings.weight",
|
| 24 |
+
"embeddings.position_embeddings.weight": "embeddings.position_embeddings.weight",
|
| 25 |
+
"embeddings.segment_embeddings.weight": "embeddings.token_type_embeddings.weight",
|
| 26 |
+
"embeddings.layerNorm.weight": "embeddings.LayerNorm.weight",
|
| 27 |
+
"embeddings.layerNorm.bias": "embeddings.LayerNorm.bias",
|
| 28 |
+
"pooler.weight": "pooler.dense.weight",
|
| 29 |
+
"pooler.bias": "pooler.dense.bias",
|
| 30 |
+
"encoderLayer.0.multiHeadAttention.q.weight": "encoder.layer.0.attention.self.query.weight",
|
| 31 |
+
"encoderLayer.0.multiHeadAttention.q.bias": "encoder.layer.0.attention.self.query.bias",
|
| 32 |
+
"encoderLayer.0.multiHeadAttention.k.weight": "encoder.layer.0.attention.self.key.weight",
|
| 33 |
+
"encoderLayer.0.multiHeadAttention.k.bias": "encoder.layer.0.attention.self.key.bias",
|
| 34 |
+
"encoderLayer.0.multiHeadAttention.v.weight": "encoder.layer.0.attention.self.value.weight",
|
| 35 |
+
"encoderLayer.0.multiHeadAttention.v.bias": "encoder.layer.0.attention.self.value.bias",
|
| 36 |
+
"encoderLayer.0.multiHeadAttention.o.weight": "encoder.layer.0.attention.output.dense.weight",
|
| 37 |
+
"encoderLayer.0.multiHeadAttention.o.bias": "encoder.layer.0.attention.output.dense.bias",
|
| 38 |
+
"encoderLayer.0.attnLayerNorm.weight": "encoder.layer.0.attention.output.LayerNorm.weight",
|
| 39 |
+
"encoderLayer.0.attnLayerNorm.bias": "encoder.layer.0.attention.output.LayerNorm.bias",
|
| 40 |
+
"encoderLayer.0.feedForward.intermediateDense.weight": "encoder.layer.0.intermediate.dense.weight",
|
| 41 |
+
"encoderLayer.0.feedForward.intermediateDense.bias": "encoder.layer.0.intermediate.dense.bias",
|
| 42 |
+
"encoderLayer.0.feedForward.outputDense.weight": "encoder.layer.0.output.dense.weight",
|
| 43 |
+
"encoderLayer.0.feedForward.outputDense.bias": "encoder.layer.0.output.dense.bias",
|
| 44 |
+
"encoderLayer.0.ffnLayerNorm.weight": "encoder.layer.0.output.LayerNorm.weight",
|
| 45 |
+
"encoderLayer.0.ffnLayerNorm.bias": "encoder.layer.0.output.LayerNorm.bias",
|
| 46 |
+
"encoderLayer.1.multiHeadAttention.q.weight": "encoder.layer.1.attention.self.query.weight",
|
| 47 |
+
"encoderLayer.1.multiHeadAttention.q.bias": "encoder.layer.1.attention.self.query.bias",
|
| 48 |
+
"encoderLayer.1.multiHeadAttention.k.weight": "encoder.layer.1.attention.self.key.weight",
|
| 49 |
+
"encoderLayer.1.multiHeadAttention.k.bias": "encoder.layer.1.attention.self.key.bias",
|
| 50 |
+
"encoderLayer.1.multiHeadAttention.v.weight": "encoder.layer.1.attention.self.value.weight",
|
| 51 |
+
"encoderLayer.1.multiHeadAttention.v.bias": "encoder.layer.1.attention.self.value.bias",
|
| 52 |
+
"encoderLayer.1.multiHeadAttention.o.weight": "encoder.layer.1.attention.output.dense.weight",
|
| 53 |
+
"encoderLayer.1.multiHeadAttention.o.bias": "encoder.layer.1.attention.output.dense.bias",
|
| 54 |
+
"encoderLayer.1.attnLayerNorm.weight": "encoder.layer.1.attention.output.LayerNorm.weight",
|
| 55 |
+
"encoderLayer.1.attnLayerNorm.bias": "encoder.layer.1.attention.output.LayerNorm.bias",
|
| 56 |
+
"encoderLayer.1.feedForward.intermediateDense.weight": "encoder.layer.1.intermediate.dense.weight",
|
| 57 |
+
"encoderLayer.1.feedForward.intermediateDense.bias": "encoder.layer.1.intermediate.dense.bias",
|
| 58 |
+
"encoderLayer.1.feedForward.outputDense.weight": "encoder.layer.1.output.dense.weight",
|
| 59 |
+
"encoderLayer.1.feedForward.outputDense.bias": "encoder.layer.1.output.dense.bias",
|
| 60 |
+
"encoderLayer.1.ffnLayerNorm.weight": "encoder.layer.1.output.LayerNorm.weight",
|
| 61 |
+
"encoderLayer.1.ffnLayerNorm.bias": "encoder.layer.1.output.LayerNorm.bias",
|
| 62 |
+
"encoderLayer.2.multiHeadAttention.q.weight": "encoder.layer.2.attention.self.query.weight",
|
| 63 |
+
"encoderLayer.2.multiHeadAttention.q.bias": "encoder.layer.2.attention.self.query.bias",
|
| 64 |
+
"encoderLayer.2.multiHeadAttention.k.weight": "encoder.layer.2.attention.self.key.weight",
|
| 65 |
+
"encoderLayer.2.multiHeadAttention.k.bias": "encoder.layer.2.attention.self.key.bias",
|
| 66 |
+
"encoderLayer.2.multiHeadAttention.v.weight": "encoder.layer.2.attention.self.value.weight",
|
| 67 |
+
"encoderLayer.2.multiHeadAttention.v.bias": "encoder.layer.2.attention.self.value.bias",
|
| 68 |
+
"encoderLayer.2.multiHeadAttention.o.weight": "encoder.layer.2.attention.output.dense.weight",
|
| 69 |
+
"encoderLayer.2.multiHeadAttention.o.bias": "encoder.layer.2.attention.output.dense.bias",
|
| 70 |
+
"encoderLayer.2.attnLayerNorm.weight": "encoder.layer.2.attention.output.LayerNorm.weight",
|
| 71 |
+
"encoderLayer.2.attnLayerNorm.bias": "encoder.layer.2.attention.output.LayerNorm.bias",
|
| 72 |
+
"encoderLayer.2.feedForward.intermediateDense.weight": "encoder.layer.2.intermediate.dense.weight",
|
| 73 |
+
"encoderLayer.2.feedForward.intermediateDense.bias": "encoder.layer.2.intermediate.dense.bias",
|
| 74 |
+
"encoderLayer.2.feedForward.outputDense.weight": "encoder.layer.2.output.dense.weight",
|
| 75 |
+
"encoderLayer.2.feedForward.outputDense.bias": "encoder.layer.2.output.dense.bias",
|
| 76 |
+
"encoderLayer.2.ffnLayerNorm.weight": "encoder.layer.2.output.LayerNorm.weight",
|
| 77 |
+
"encoderLayer.2.ffnLayerNorm.bias": "encoder.layer.2.output.LayerNorm.bias",
|
| 78 |
+
"encoderLayer.3.multiHeadAttention.q.weight": "encoder.layer.3.attention.self.query.weight",
|
| 79 |
+
"encoderLayer.3.multiHeadAttention.q.bias": "encoder.layer.3.attention.self.query.bias",
|
| 80 |
+
"encoderLayer.3.multiHeadAttention.k.weight": "encoder.layer.3.attention.self.key.weight",
|
| 81 |
+
"encoderLayer.3.multiHeadAttention.k.bias": "encoder.layer.3.attention.self.key.bias",
|
| 82 |
+
"encoderLayer.3.multiHeadAttention.v.weight": "encoder.layer.3.attention.self.value.weight",
|
| 83 |
+
"encoderLayer.3.multiHeadAttention.v.bias": "encoder.layer.3.attention.self.value.bias",
|
| 84 |
+
"encoderLayer.3.multiHeadAttention.o.weight": "encoder.layer.3.attention.output.dense.weight",
|
| 85 |
+
"encoderLayer.3.multiHeadAttention.o.bias": "encoder.layer.3.attention.output.dense.bias",
|
| 86 |
+
"encoderLayer.3.attnLayerNorm.weight": "encoder.layer.3.attention.output.LayerNorm.weight",
|
| 87 |
+
"encoderLayer.3.attnLayerNorm.bias": "encoder.layer.3.attention.output.LayerNorm.bias",
|
| 88 |
+
"encoderLayer.3.feedForward.intermediateDense.weight": "encoder.layer.3.intermediate.dense.weight",
|
| 89 |
+
"encoderLayer.3.feedForward.intermediateDense.bias": "encoder.layer.3.intermediate.dense.bias",
|
| 90 |
+
"encoderLayer.3.feedForward.outputDense.weight": "encoder.layer.3.output.dense.weight",
|
| 91 |
+
"encoderLayer.3.feedForward.outputDense.bias": "encoder.layer.3.output.dense.bias",
|
| 92 |
+
"encoderLayer.3.ffnLayerNorm.weight": "encoder.layer.3.output.LayerNorm.weight",
|
| 93 |
+
"encoderLayer.3.ffnLayerNorm.bias": "encoder.layer.3.output.LayerNorm.bias",
|
| 94 |
+
"encoderLayer.4.multiHeadAttention.q.weight": "encoder.layer.4.attention.self.query.weight",
|
| 95 |
+
"encoderLayer.4.multiHeadAttention.q.bias": "encoder.layer.4.attention.self.query.bias",
|
| 96 |
+
"encoderLayer.4.multiHeadAttention.k.weight": "encoder.layer.4.attention.self.key.weight",
|
| 97 |
+
"encoderLayer.4.multiHeadAttention.k.bias": "encoder.layer.4.attention.self.key.bias",
|
| 98 |
+
"encoderLayer.4.multiHeadAttention.v.weight": "encoder.layer.4.attention.self.value.weight",
|
| 99 |
+
"encoderLayer.4.multiHeadAttention.v.bias": "encoder.layer.4.attention.self.value.bias",
|
| 100 |
+
"encoderLayer.4.multiHeadAttention.o.weight": "encoder.layer.4.attention.output.dense.weight",
|
| 101 |
+
"encoderLayer.4.multiHeadAttention.o.bias": "encoder.layer.4.attention.output.dense.bias",
|
| 102 |
+
"encoderLayer.4.attnLayerNorm.weight": "encoder.layer.4.attention.output.LayerNorm.weight",
|
| 103 |
+
"encoderLayer.4.attnLayerNorm.bias": "encoder.layer.4.attention.output.LayerNorm.bias",
|
| 104 |
+
"encoderLayer.4.feedForward.intermediateDense.weight": "encoder.layer.4.intermediate.dense.weight",
|
| 105 |
+
"encoderLayer.4.feedForward.intermediateDense.bias": "encoder.layer.4.intermediate.dense.bias",
|
| 106 |
+
"encoderLayer.4.feedForward.outputDense.weight": "encoder.layer.4.output.dense.weight",
|
| 107 |
+
"encoderLayer.4.feedForward.outputDense.bias": "encoder.layer.4.output.dense.bias",
|
| 108 |
+
"encoderLayer.4.ffnLayerNorm.weight": "encoder.layer.4.output.LayerNorm.weight",
|
| 109 |
+
"encoderLayer.4.ffnLayerNorm.bias": "encoder.layer.4.output.LayerNorm.bias",
|
| 110 |
+
"encoderLayer.5.multiHeadAttention.q.weight": "encoder.layer.5.attention.self.query.weight",
|
| 111 |
+
"encoderLayer.5.multiHeadAttention.q.bias": "encoder.layer.5.attention.self.query.bias",
|
| 112 |
+
"encoderLayer.5.multiHeadAttention.k.weight": "encoder.layer.5.attention.self.key.weight",
|
| 113 |
+
"encoderLayer.5.multiHeadAttention.k.bias": "encoder.layer.5.attention.self.key.bias",
|
| 114 |
+
"encoderLayer.5.multiHeadAttention.v.weight": "encoder.layer.5.attention.self.value.weight",
|
| 115 |
+
"encoderLayer.5.multiHeadAttention.v.bias": "encoder.layer.5.attention.self.value.bias",
|
| 116 |
+
"encoderLayer.5.multiHeadAttention.o.weight": "encoder.layer.5.attention.output.dense.weight",
|
| 117 |
+
"encoderLayer.5.multiHeadAttention.o.bias": "encoder.layer.5.attention.output.dense.bias",
|
| 118 |
+
"encoderLayer.5.attnLayerNorm.weight": "encoder.layer.5.attention.output.LayerNorm.weight",
|
| 119 |
+
"encoderLayer.5.attnLayerNorm.bias": "encoder.layer.5.attention.output.LayerNorm.bias",
|
| 120 |
+
"encoderLayer.5.feedForward.intermediateDense.weight": "encoder.layer.5.intermediate.dense.weight",
|
| 121 |
+
"encoderLayer.5.feedForward.intermediateDense.bias": "encoder.layer.5.intermediate.dense.bias",
|
| 122 |
+
"encoderLayer.5.feedForward.outputDense.weight": "encoder.layer.5.output.dense.weight",
|
| 123 |
+
"encoderLayer.5.feedForward.outputDense.bias": "encoder.layer.5.output.dense.bias",
|
| 124 |
+
"encoderLayer.5.ffnLayerNorm.weight": "encoder.layer.5.output.LayerNorm.weight",
|
| 125 |
+
"encoderLayer.5.ffnLayerNorm.bias": "encoder.layer.5.output.LayerNorm.bias",
|
| 126 |
+
"encoderLayer.6.multiHeadAttention.q.weight": "encoder.layer.6.attention.self.query.weight",
|
| 127 |
+
"encoderLayer.6.multiHeadAttention.q.bias": "encoder.layer.6.attention.self.query.bias",
|
| 128 |
+
"encoderLayer.6.multiHeadAttention.k.weight": "encoder.layer.6.attention.self.key.weight",
|
| 129 |
+
"encoderLayer.6.multiHeadAttention.k.bias": "encoder.layer.6.attention.self.key.bias",
|
| 130 |
+
"encoderLayer.6.multiHeadAttention.v.weight": "encoder.layer.6.attention.self.value.weight",
|
| 131 |
+
"encoderLayer.6.multiHeadAttention.v.bias": "encoder.layer.6.attention.self.value.bias",
|
| 132 |
+
"encoderLayer.6.multiHeadAttention.o.weight": "encoder.layer.6.attention.output.dense.weight",
|
| 133 |
+
"encoderLayer.6.multiHeadAttention.o.bias": "encoder.layer.6.attention.output.dense.bias",
|
| 134 |
+
"encoderLayer.6.attnLayerNorm.weight": "encoder.layer.6.attention.output.LayerNorm.weight",
|
| 135 |
+
"encoderLayer.6.attnLayerNorm.bias": "encoder.layer.6.attention.output.LayerNorm.bias",
|
| 136 |
+
"encoderLayer.6.feedForward.intermediateDense.weight": "encoder.layer.6.intermediate.dense.weight",
|
| 137 |
+
"encoderLayer.6.feedForward.intermediateDense.bias": "encoder.layer.6.intermediate.dense.bias",
|
| 138 |
+
"encoderLayer.6.feedForward.outputDense.weight": "encoder.layer.6.output.dense.weight",
|
| 139 |
+
"encoderLayer.6.feedForward.outputDense.bias": "encoder.layer.6.output.dense.bias",
|
| 140 |
+
"encoderLayer.6.ffnLayerNorm.weight": "encoder.layer.6.output.LayerNorm.weight",
|
| 141 |
+
"encoderLayer.6.ffnLayerNorm.bias": "encoder.layer.6.output.LayerNorm.bias",
|
| 142 |
+
"encoderLayer.7.multiHeadAttention.q.weight": "encoder.layer.7.attention.self.query.weight",
|
| 143 |
+
"encoderLayer.7.multiHeadAttention.q.bias": "encoder.layer.7.attention.self.query.bias",
|
| 144 |
+
"encoderLayer.7.multiHeadAttention.k.weight": "encoder.layer.7.attention.self.key.weight",
|
| 145 |
+
"encoderLayer.7.multiHeadAttention.k.bias": "encoder.layer.7.attention.self.key.bias",
|
| 146 |
+
"encoderLayer.7.multiHeadAttention.v.weight": "encoder.layer.7.attention.self.value.weight",
|
| 147 |
+
"encoderLayer.7.multiHeadAttention.v.bias": "encoder.layer.7.attention.self.value.bias",
|
| 148 |
+
"encoderLayer.7.multiHeadAttention.o.weight": "encoder.layer.7.attention.output.dense.weight",
|
| 149 |
+
"encoderLayer.7.multiHeadAttention.o.bias": "encoder.layer.7.attention.output.dense.bias",
|
| 150 |
+
"encoderLayer.7.attnLayerNorm.weight": "encoder.layer.7.attention.output.LayerNorm.weight",
|
| 151 |
+
"encoderLayer.7.attnLayerNorm.bias": "encoder.layer.7.attention.output.LayerNorm.bias",
|
| 152 |
+
"encoderLayer.7.feedForward.intermediateDense.weight": "encoder.layer.7.intermediate.dense.weight",
|
| 153 |
+
"encoderLayer.7.feedForward.intermediateDense.bias": "encoder.layer.7.intermediate.dense.bias",
|
| 154 |
+
"encoderLayer.7.feedForward.outputDense.weight": "encoder.layer.7.output.dense.weight",
|
| 155 |
+
"encoderLayer.7.feedForward.outputDense.bias": "encoder.layer.7.output.dense.bias",
|
| 156 |
+
"encoderLayer.7.ffnLayerNorm.weight": "encoder.layer.7.output.LayerNorm.weight",
|
| 157 |
+
"encoderLayer.7.ffnLayerNorm.bias": "encoder.layer.7.output.LayerNorm.bias",
|
| 158 |
+
"encoderLayer.8.multiHeadAttention.q.weight": "encoder.layer.8.attention.self.query.weight",
|
| 159 |
+
"encoderLayer.8.multiHeadAttention.q.bias": "encoder.layer.8.attention.self.query.bias",
|
| 160 |
+
"encoderLayer.8.multiHeadAttention.k.weight": "encoder.layer.8.attention.self.key.weight",
|
| 161 |
+
"encoderLayer.8.multiHeadAttention.k.bias": "encoder.layer.8.attention.self.key.bias",
|
| 162 |
+
"encoderLayer.8.multiHeadAttention.v.weight": "encoder.layer.8.attention.self.value.weight",
|
| 163 |
+
"encoderLayer.8.multiHeadAttention.v.bias": "encoder.layer.8.attention.self.value.bias",
|
| 164 |
+
"encoderLayer.8.multiHeadAttention.o.weight": "encoder.layer.8.attention.output.dense.weight",
|
| 165 |
+
"encoderLayer.8.multiHeadAttention.o.bias": "encoder.layer.8.attention.output.dense.bias",
|
| 166 |
+
"encoderLayer.8.attnLayerNorm.weight": "encoder.layer.8.attention.output.LayerNorm.weight",
|
| 167 |
+
"encoderLayer.8.attnLayerNorm.bias": "encoder.layer.8.attention.output.LayerNorm.bias",
|
| 168 |
+
"encoderLayer.8.feedForward.intermediateDense.weight": "encoder.layer.8.intermediate.dense.weight",
|
| 169 |
+
"encoderLayer.8.feedForward.intermediateDense.bias": "encoder.layer.8.intermediate.dense.bias",
|
| 170 |
+
"encoderLayer.8.feedForward.outputDense.weight": "encoder.layer.8.output.dense.weight",
|
| 171 |
+
"encoderLayer.8.feedForward.outputDense.bias": "encoder.layer.8.output.dense.bias",
|
| 172 |
+
"encoderLayer.8.ffnLayerNorm.weight": "encoder.layer.8.output.LayerNorm.weight",
|
| 173 |
+
"encoderLayer.8.ffnLayerNorm.bias": "encoder.layer.8.output.LayerNorm.bias",
|
| 174 |
+
"encoderLayer.9.multiHeadAttention.q.weight": "encoder.layer.9.attention.self.query.weight",
|
| 175 |
+
"encoderLayer.9.multiHeadAttention.q.bias": "encoder.layer.9.attention.self.query.bias",
|
| 176 |
+
"encoderLayer.9.multiHeadAttention.k.weight": "encoder.layer.9.attention.self.key.weight",
|
| 177 |
+
"encoderLayer.9.multiHeadAttention.k.bias": "encoder.layer.9.attention.self.key.bias",
|
| 178 |
+
"encoderLayer.9.multiHeadAttention.v.weight": "encoder.layer.9.attention.self.value.weight",
|
| 179 |
+
"encoderLayer.9.multiHeadAttention.v.bias": "encoder.layer.9.attention.self.value.bias",
|
| 180 |
+
"encoderLayer.9.multiHeadAttention.o.weight": "encoder.layer.9.attention.output.dense.weight",
|
| 181 |
+
"encoderLayer.9.multiHeadAttention.o.bias": "encoder.layer.9.attention.output.dense.bias",
|
| 182 |
+
"encoderLayer.9.attnLayerNorm.weight": "encoder.layer.9.attention.output.LayerNorm.weight",
|
| 183 |
+
"encoderLayer.9.attnLayerNorm.bias": "encoder.layer.9.attention.output.LayerNorm.bias",
|
| 184 |
+
"encoderLayer.9.feedForward.intermediateDense.weight": "encoder.layer.9.intermediate.dense.weight",
|
| 185 |
+
"encoderLayer.9.feedForward.intermediateDense.bias": "encoder.layer.9.intermediate.dense.bias",
|
| 186 |
+
"encoderLayer.9.feedForward.outputDense.weight": "encoder.layer.9.output.dense.weight",
|
| 187 |
+
"encoderLayer.9.feedForward.outputDense.bias": "encoder.layer.9.output.dense.bias",
|
| 188 |
+
"encoderLayer.9.ffnLayerNorm.weight": "encoder.layer.9.output.LayerNorm.weight",
|
| 189 |
+
"encoderLayer.9.ffnLayerNorm.bias": "encoder.layer.9.output.LayerNorm.bias",
|
| 190 |
+
"encoderLayer.10.multiHeadAttention.q.weight": "encoder.layer.10.attention.self.query.weight",
|
| 191 |
+
"encoderLayer.10.multiHeadAttention.q.bias": "encoder.layer.10.attention.self.query.bias",
|
| 192 |
+
"encoderLayer.10.multiHeadAttention.k.weight": "encoder.layer.10.attention.self.key.weight",
|
| 193 |
+
"encoderLayer.10.multiHeadAttention.k.bias": "encoder.layer.10.attention.self.key.bias",
|
| 194 |
+
"encoderLayer.10.multiHeadAttention.v.weight": "encoder.layer.10.attention.self.value.weight",
|
| 195 |
+
"encoderLayer.10.multiHeadAttention.v.bias": "encoder.layer.10.attention.self.value.bias",
|
| 196 |
+
"encoderLayer.10.multiHeadAttention.o.weight": "encoder.layer.10.attention.output.dense.weight",
|
| 197 |
+
"encoderLayer.10.multiHeadAttention.o.bias": "encoder.layer.10.attention.output.dense.bias",
|
| 198 |
+
"encoderLayer.10.attnLayerNorm.weight": "encoder.layer.10.attention.output.LayerNorm.weight",
|
| 199 |
+
"encoderLayer.10.attnLayerNorm.bias": "encoder.layer.10.attention.output.LayerNorm.bias",
|
| 200 |
+
"encoderLayer.10.feedForward.intermediateDense.weight": "encoder.layer.10.intermediate.dense.weight",
|
| 201 |
+
"encoderLayer.10.feedForward.intermediateDense.bias": "encoder.layer.10.intermediate.dense.bias",
|
| 202 |
+
"encoderLayer.10.feedForward.outputDense.weight": "encoder.layer.10.output.dense.weight",
|
| 203 |
+
"encoderLayer.10.feedForward.outputDense.bias": "encoder.layer.10.output.dense.bias",
|
| 204 |
+
"encoderLayer.10.ffnLayerNorm.weight": "encoder.layer.10.output.LayerNorm.weight",
|
| 205 |
+
"encoderLayer.10.ffnLayerNorm.bias": "encoder.layer.10.output.LayerNorm.bias",
|
| 206 |
+
"encoderLayer.11.multiHeadAttention.q.weight": "encoder.layer.11.attention.self.query.weight",
|
| 207 |
+
"encoderLayer.11.multiHeadAttention.q.bias": "encoder.layer.11.attention.self.query.bias",
|
| 208 |
+
"encoderLayer.11.multiHeadAttention.k.weight": "encoder.layer.11.attention.self.key.weight",
|
| 209 |
+
"encoderLayer.11.multiHeadAttention.k.bias": "encoder.layer.11.attention.self.key.bias",
|
| 210 |
+
"encoderLayer.11.multiHeadAttention.v.weight": "encoder.layer.11.attention.self.value.weight",
|
| 211 |
+
"encoderLayer.11.multiHeadAttention.v.bias": "encoder.layer.11.attention.self.value.bias",
|
| 212 |
+
"encoderLayer.11.multiHeadAttention.o.weight": "encoder.layer.11.attention.output.dense.weight",
|
| 213 |
+
"encoderLayer.11.multiHeadAttention.o.bias": "encoder.layer.11.attention.output.dense.bias",
|
| 214 |
+
"encoderLayer.11.attnLayerNorm.weight": "encoder.layer.11.attention.output.LayerNorm.weight",
|
| 215 |
+
"encoderLayer.11.attnLayerNorm.bias": "encoder.layer.11.attention.output.LayerNorm.bias",
|
| 216 |
+
"encoderLayer.11.feedForward.intermediateDense.weight": "encoder.layer.11.intermediate.dense.weight",
|
| 217 |
+
"encoderLayer.11.feedForward.intermediateDense.bias": "encoder.layer.11.intermediate.dense.bias",
|
| 218 |
+
"encoderLayer.11.feedForward.outputDense.weight": "encoder.layer.11.output.dense.weight",
|
| 219 |
+
"encoderLayer.11.feedForward.outputDense.bias": "encoder.layer.11.output.dense.bias",
|
| 220 |
+
"encoderLayer.11.ffnLayerNorm.weight": "encoder.layer.11.output.LayerNorm.weight",
|
| 221 |
+
"encoderLayer.11.ffnLayerNorm.bias": "encoder.layer.11.output.LayerNorm.bias"
|
| 222 |
+
}
|
| 223 |
+
}
|
bge-small-en-v1.5/bert4torch_config.json
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"hidden_act": "gelu",
|
| 4 |
+
"hidden_dropout_prob": 0.1,
|
| 5 |
+
"hidden_size": 384,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 1536,
|
| 8 |
+
"layer_norm_eps": 1e-12,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"model": "bert",
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 12,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"torch_dtype": "float32",
|
| 15 |
+
"type_vocab_size": 2,
|
| 16 |
+
"vocab_size": 30522,
|
| 17 |
+
"with_pool": true,
|
| 18 |
+
"pool_strategy": "cls",
|
| 19 |
+
"norm_mode": "torch_buildin",
|
| 20 |
+
"mapping": {
|
| 21 |
+
"embeddings.word_embeddings.weight": "embeddings.word_embeddings.weight",
|
| 22 |
+
"embeddings.position_embeddings.weight": "embeddings.position_embeddings.weight",
|
| 23 |
+
"embeddings.segment_embeddings.weight": "embeddings.token_type_embeddings.weight",
|
| 24 |
+
"embeddings.layerNorm.weight": "embeddings.LayerNorm.weight",
|
| 25 |
+
"embeddings.layerNorm.bias": "embeddings.LayerNorm.bias",
|
| 26 |
+
"pooler.weight": "pooler.dense.weight",
|
| 27 |
+
"pooler.bias": "pooler.dense.bias",
|
| 28 |
+
"encoderLayer.0.multiHeadAttention.q.weight": "encoder.layer.0.attention.self.query.weight",
|
| 29 |
+
"encoderLayer.0.multiHeadAttention.q.bias": "encoder.layer.0.attention.self.query.bias",
|
| 30 |
+
"encoderLayer.0.multiHeadAttention.k.weight": "encoder.layer.0.attention.self.key.weight",
|
| 31 |
+
"encoderLayer.0.multiHeadAttention.k.bias": "encoder.layer.0.attention.self.key.bias",
|
| 32 |
+
"encoderLayer.0.multiHeadAttention.v.weight": "encoder.layer.0.attention.self.value.weight",
|
| 33 |
+
"encoderLayer.0.multiHeadAttention.v.bias": "encoder.layer.0.attention.self.value.bias",
|
| 34 |
+
"encoderLayer.0.multiHeadAttention.o.weight": "encoder.layer.0.attention.output.dense.weight",
|
| 35 |
+
"encoderLayer.0.multiHeadAttention.o.bias": "encoder.layer.0.attention.output.dense.bias",
|
| 36 |
+
"encoderLayer.0.attnLayerNorm.weight": "encoder.layer.0.attention.output.LayerNorm.weight",
|
| 37 |
+
"encoderLayer.0.attnLayerNorm.bias": "encoder.layer.0.attention.output.LayerNorm.bias",
|
| 38 |
+
"encoderLayer.0.feedForward.intermediateDense.weight": "encoder.layer.0.intermediate.dense.weight",
|
| 39 |
+
"encoderLayer.0.feedForward.intermediateDense.bias": "encoder.layer.0.intermediate.dense.bias",
|
| 40 |
+
"encoderLayer.0.feedForward.outputDense.weight": "encoder.layer.0.output.dense.weight",
|
| 41 |
+
"encoderLayer.0.feedForward.outputDense.bias": "encoder.layer.0.output.dense.bias",
|
| 42 |
+
"encoderLayer.0.ffnLayerNorm.weight": "encoder.layer.0.output.LayerNorm.weight",
|
| 43 |
+
"encoderLayer.0.ffnLayerNorm.bias": "encoder.layer.0.output.LayerNorm.bias",
|
| 44 |
+
"encoderLayer.1.multiHeadAttention.q.weight": "encoder.layer.1.attention.self.query.weight",
|
| 45 |
+
"encoderLayer.1.multiHeadAttention.q.bias": "encoder.layer.1.attention.self.query.bias",
|
| 46 |
+
"encoderLayer.1.multiHeadAttention.k.weight": "encoder.layer.1.attention.self.key.weight",
|
| 47 |
+
"encoderLayer.1.multiHeadAttention.k.bias": "encoder.layer.1.attention.self.key.bias",
|
| 48 |
+
"encoderLayer.1.multiHeadAttention.v.weight": "encoder.layer.1.attention.self.value.weight",
|
| 49 |
+
"encoderLayer.1.multiHeadAttention.v.bias": "encoder.layer.1.attention.self.value.bias",
|
| 50 |
+
"encoderLayer.1.multiHeadAttention.o.weight": "encoder.layer.1.attention.output.dense.weight",
|
| 51 |
+
"encoderLayer.1.multiHeadAttention.o.bias": "encoder.layer.1.attention.output.dense.bias",
|
| 52 |
+
"encoderLayer.1.attnLayerNorm.weight": "encoder.layer.1.attention.output.LayerNorm.weight",
|
| 53 |
+
"encoderLayer.1.attnLayerNorm.bias": "encoder.layer.1.attention.output.LayerNorm.bias",
|
| 54 |
+
"encoderLayer.1.feedForward.intermediateDense.weight": "encoder.layer.1.intermediate.dense.weight",
|
| 55 |
+
"encoderLayer.1.feedForward.intermediateDense.bias": "encoder.layer.1.intermediate.dense.bias",
|
| 56 |
+
"encoderLayer.1.feedForward.outputDense.weight": "encoder.layer.1.output.dense.weight",
|
| 57 |
+
"encoderLayer.1.feedForward.outputDense.bias": "encoder.layer.1.output.dense.bias",
|
| 58 |
+
"encoderLayer.1.ffnLayerNorm.weight": "encoder.layer.1.output.LayerNorm.weight",
|
| 59 |
+
"encoderLayer.1.ffnLayerNorm.bias": "encoder.layer.1.output.LayerNorm.bias",
|
| 60 |
+
"encoderLayer.2.multiHeadAttention.q.weight": "encoder.layer.2.attention.self.query.weight",
|
| 61 |
+
"encoderLayer.2.multiHeadAttention.q.bias": "encoder.layer.2.attention.self.query.bias",
|
| 62 |
+
"encoderLayer.2.multiHeadAttention.k.weight": "encoder.layer.2.attention.self.key.weight",
|
| 63 |
+
"encoderLayer.2.multiHeadAttention.k.bias": "encoder.layer.2.attention.self.key.bias",
|
| 64 |
+
"encoderLayer.2.multiHeadAttention.v.weight": "encoder.layer.2.attention.self.value.weight",
|
| 65 |
+
"encoderLayer.2.multiHeadAttention.v.bias": "encoder.layer.2.attention.self.value.bias",
|
| 66 |
+
"encoderLayer.2.multiHeadAttention.o.weight": "encoder.layer.2.attention.output.dense.weight",
|
| 67 |
+
"encoderLayer.2.multiHeadAttention.o.bias": "encoder.layer.2.attention.output.dense.bias",
|
| 68 |
+
"encoderLayer.2.attnLayerNorm.weight": "encoder.layer.2.attention.output.LayerNorm.weight",
|
| 69 |
+
"encoderLayer.2.attnLayerNorm.bias": "encoder.layer.2.attention.output.LayerNorm.bias",
|
| 70 |
+
"encoderLayer.2.feedForward.intermediateDense.weight": "encoder.layer.2.intermediate.dense.weight",
|
| 71 |
+
"encoderLayer.2.feedForward.intermediateDense.bias": "encoder.layer.2.intermediate.dense.bias",
|
| 72 |
+
"encoderLayer.2.feedForward.outputDense.weight": "encoder.layer.2.output.dense.weight",
|
| 73 |
+
"encoderLayer.2.feedForward.outputDense.bias": "encoder.layer.2.output.dense.bias",
|
| 74 |
+
"encoderLayer.2.ffnLayerNorm.weight": "encoder.layer.2.output.LayerNorm.weight",
|
| 75 |
+
"encoderLayer.2.ffnLayerNorm.bias": "encoder.layer.2.output.LayerNorm.bias",
|
| 76 |
+
"encoderLayer.3.multiHeadAttention.q.weight": "encoder.layer.3.attention.self.query.weight",
|
| 77 |
+
"encoderLayer.3.multiHeadAttention.q.bias": "encoder.layer.3.attention.self.query.bias",
|
| 78 |
+
"encoderLayer.3.multiHeadAttention.k.weight": "encoder.layer.3.attention.self.key.weight",
|
| 79 |
+
"encoderLayer.3.multiHeadAttention.k.bias": "encoder.layer.3.attention.self.key.bias",
|
| 80 |
+
"encoderLayer.3.multiHeadAttention.v.weight": "encoder.layer.3.attention.self.value.weight",
|
| 81 |
+
"encoderLayer.3.multiHeadAttention.v.bias": "encoder.layer.3.attention.self.value.bias",
|
| 82 |
+
"encoderLayer.3.multiHeadAttention.o.weight": "encoder.layer.3.attention.output.dense.weight",
|
| 83 |
+
"encoderLayer.3.multiHeadAttention.o.bias": "encoder.layer.3.attention.output.dense.bias",
|
| 84 |
+
"encoderLayer.3.attnLayerNorm.weight": "encoder.layer.3.attention.output.LayerNorm.weight",
|
| 85 |
+
"encoderLayer.3.attnLayerNorm.bias": "encoder.layer.3.attention.output.LayerNorm.bias",
|
| 86 |
+
"encoderLayer.3.feedForward.intermediateDense.weight": "encoder.layer.3.intermediate.dense.weight",
|
| 87 |
+
"encoderLayer.3.feedForward.intermediateDense.bias": "encoder.layer.3.intermediate.dense.bias",
|
| 88 |
+
"encoderLayer.3.feedForward.outputDense.weight": "encoder.layer.3.output.dense.weight",
|
| 89 |
+
"encoderLayer.3.feedForward.outputDense.bias": "encoder.layer.3.output.dense.bias",
|
| 90 |
+
"encoderLayer.3.ffnLayerNorm.weight": "encoder.layer.3.output.LayerNorm.weight",
|
| 91 |
+
"encoderLayer.3.ffnLayerNorm.bias": "encoder.layer.3.output.LayerNorm.bias",
|
| 92 |
+
"encoderLayer.4.multiHeadAttention.q.weight": "encoder.layer.4.attention.self.query.weight",
|
| 93 |
+
"encoderLayer.4.multiHeadAttention.q.bias": "encoder.layer.4.attention.self.query.bias",
|
| 94 |
+
"encoderLayer.4.multiHeadAttention.k.weight": "encoder.layer.4.attention.self.key.weight",
|
| 95 |
+
"encoderLayer.4.multiHeadAttention.k.bias": "encoder.layer.4.attention.self.key.bias",
|
| 96 |
+
"encoderLayer.4.multiHeadAttention.v.weight": "encoder.layer.4.attention.self.value.weight",
|
| 97 |
+
"encoderLayer.4.multiHeadAttention.v.bias": "encoder.layer.4.attention.self.value.bias",
|
| 98 |
+
"encoderLayer.4.multiHeadAttention.o.weight": "encoder.layer.4.attention.output.dense.weight",
|
| 99 |
+
"encoderLayer.4.multiHeadAttention.o.bias": "encoder.layer.4.attention.output.dense.bias",
|
| 100 |
+
"encoderLayer.4.attnLayerNorm.weight": "encoder.layer.4.attention.output.LayerNorm.weight",
|
| 101 |
+
"encoderLayer.4.attnLayerNorm.bias": "encoder.layer.4.attention.output.LayerNorm.bias",
|
| 102 |
+
"encoderLayer.4.feedForward.intermediateDense.weight": "encoder.layer.4.intermediate.dense.weight",
|
| 103 |
+
"encoderLayer.4.feedForward.intermediateDense.bias": "encoder.layer.4.intermediate.dense.bias",
|
| 104 |
+
"encoderLayer.4.feedForward.outputDense.weight": "encoder.layer.4.output.dense.weight",
|
| 105 |
+
"encoderLayer.4.feedForward.outputDense.bias": "encoder.layer.4.output.dense.bias",
|
| 106 |
+
"encoderLayer.4.ffnLayerNorm.weight": "encoder.layer.4.output.LayerNorm.weight",
|
| 107 |
+
"encoderLayer.4.ffnLayerNorm.bias": "encoder.layer.4.output.LayerNorm.bias",
|
| 108 |
+
"encoderLayer.5.multiHeadAttention.q.weight": "encoder.layer.5.attention.self.query.weight",
|
| 109 |
+
"encoderLayer.5.multiHeadAttention.q.bias": "encoder.layer.5.attention.self.query.bias",
|
| 110 |
+
"encoderLayer.5.multiHeadAttention.k.weight": "encoder.layer.5.attention.self.key.weight",
|
| 111 |
+
"encoderLayer.5.multiHeadAttention.k.bias": "encoder.layer.5.attention.self.key.bias",
|
| 112 |
+
"encoderLayer.5.multiHeadAttention.v.weight": "encoder.layer.5.attention.self.value.weight",
|
| 113 |
+
"encoderLayer.5.multiHeadAttention.v.bias": "encoder.layer.5.attention.self.value.bias",
|
| 114 |
+
"encoderLayer.5.multiHeadAttention.o.weight": "encoder.layer.5.attention.output.dense.weight",
|
| 115 |
+
"encoderLayer.5.multiHeadAttention.o.bias": "encoder.layer.5.attention.output.dense.bias",
|
| 116 |
+
"encoderLayer.5.attnLayerNorm.weight": "encoder.layer.5.attention.output.LayerNorm.weight",
|
| 117 |
+
"encoderLayer.5.attnLayerNorm.bias": "encoder.layer.5.attention.output.LayerNorm.bias",
|
| 118 |
+
"encoderLayer.5.feedForward.intermediateDense.weight": "encoder.layer.5.intermediate.dense.weight",
|
| 119 |
+
"encoderLayer.5.feedForward.intermediateDense.bias": "encoder.layer.5.intermediate.dense.bias",
|
| 120 |
+
"encoderLayer.5.feedForward.outputDense.weight": "encoder.layer.5.output.dense.weight",
|
| 121 |
+
"encoderLayer.5.feedForward.outputDense.bias": "encoder.layer.5.output.dense.bias",
|
| 122 |
+
"encoderLayer.5.ffnLayerNorm.weight": "encoder.layer.5.output.LayerNorm.weight",
|
| 123 |
+
"encoderLayer.5.ffnLayerNorm.bias": "encoder.layer.5.output.LayerNorm.bias",
|
| 124 |
+
"encoderLayer.6.multiHeadAttention.q.weight": "encoder.layer.6.attention.self.query.weight",
|
| 125 |
+
"encoderLayer.6.multiHeadAttention.q.bias": "encoder.layer.6.attention.self.query.bias",
|
| 126 |
+
"encoderLayer.6.multiHeadAttention.k.weight": "encoder.layer.6.attention.self.key.weight",
|
| 127 |
+
"encoderLayer.6.multiHeadAttention.k.bias": "encoder.layer.6.attention.self.key.bias",
|
| 128 |
+
"encoderLayer.6.multiHeadAttention.v.weight": "encoder.layer.6.attention.self.value.weight",
|
| 129 |
+
"encoderLayer.6.multiHeadAttention.v.bias": "encoder.layer.6.attention.self.value.bias",
|
| 130 |
+
"encoderLayer.6.multiHeadAttention.o.weight": "encoder.layer.6.attention.output.dense.weight",
|
| 131 |
+
"encoderLayer.6.multiHeadAttention.o.bias": "encoder.layer.6.attention.output.dense.bias",
|
| 132 |
+
"encoderLayer.6.attnLayerNorm.weight": "encoder.layer.6.attention.output.LayerNorm.weight",
|
| 133 |
+
"encoderLayer.6.attnLayerNorm.bias": "encoder.layer.6.attention.output.LayerNorm.bias",
|
| 134 |
+
"encoderLayer.6.feedForward.intermediateDense.weight": "encoder.layer.6.intermediate.dense.weight",
|
| 135 |
+
"encoderLayer.6.feedForward.intermediateDense.bias": "encoder.layer.6.intermediate.dense.bias",
|
| 136 |
+
"encoderLayer.6.feedForward.outputDense.weight": "encoder.layer.6.output.dense.weight",
|
| 137 |
+
"encoderLayer.6.feedForward.outputDense.bias": "encoder.layer.6.output.dense.bias",
|
| 138 |
+
"encoderLayer.6.ffnLayerNorm.weight": "encoder.layer.6.output.LayerNorm.weight",
|
| 139 |
+
"encoderLayer.6.ffnLayerNorm.bias": "encoder.layer.6.output.LayerNorm.bias",
|
| 140 |
+
"encoderLayer.7.multiHeadAttention.q.weight": "encoder.layer.7.attention.self.query.weight",
|
| 141 |
+
"encoderLayer.7.multiHeadAttention.q.bias": "encoder.layer.7.attention.self.query.bias",
|
| 142 |
+
"encoderLayer.7.multiHeadAttention.k.weight": "encoder.layer.7.attention.self.key.weight",
|
| 143 |
+
"encoderLayer.7.multiHeadAttention.k.bias": "encoder.layer.7.attention.self.key.bias",
|
| 144 |
+
"encoderLayer.7.multiHeadAttention.v.weight": "encoder.layer.7.attention.self.value.weight",
|
| 145 |
+
"encoderLayer.7.multiHeadAttention.v.bias": "encoder.layer.7.attention.self.value.bias",
|
| 146 |
+
"encoderLayer.7.multiHeadAttention.o.weight": "encoder.layer.7.attention.output.dense.weight",
|
| 147 |
+
"encoderLayer.7.multiHeadAttention.o.bias": "encoder.layer.7.attention.output.dense.bias",
|
| 148 |
+
"encoderLayer.7.attnLayerNorm.weight": "encoder.layer.7.attention.output.LayerNorm.weight",
|
| 149 |
+
"encoderLayer.7.attnLayerNorm.bias": "encoder.layer.7.attention.output.LayerNorm.bias",
|
| 150 |
+
"encoderLayer.7.feedForward.intermediateDense.weight": "encoder.layer.7.intermediate.dense.weight",
|
| 151 |
+
"encoderLayer.7.feedForward.intermediateDense.bias": "encoder.layer.7.intermediate.dense.bias",
|
| 152 |
+
"encoderLayer.7.feedForward.outputDense.weight": "encoder.layer.7.output.dense.weight",
|
| 153 |
+
"encoderLayer.7.feedForward.outputDense.bias": "encoder.layer.7.output.dense.bias",
|
| 154 |
+
"encoderLayer.7.ffnLayerNorm.weight": "encoder.layer.7.output.LayerNorm.weight",
|
| 155 |
+
"encoderLayer.7.ffnLayerNorm.bias": "encoder.layer.7.output.LayerNorm.bias",
|
| 156 |
+
"encoderLayer.8.multiHeadAttention.q.weight": "encoder.layer.8.attention.self.query.weight",
|
| 157 |
+
"encoderLayer.8.multiHeadAttention.q.bias": "encoder.layer.8.attention.self.query.bias",
|
| 158 |
+
"encoderLayer.8.multiHeadAttention.k.weight": "encoder.layer.8.attention.self.key.weight",
|
| 159 |
+
"encoderLayer.8.multiHeadAttention.k.bias": "encoder.layer.8.attention.self.key.bias",
|
| 160 |
+
"encoderLayer.8.multiHeadAttention.v.weight": "encoder.layer.8.attention.self.value.weight",
|
| 161 |
+
"encoderLayer.8.multiHeadAttention.v.bias": "encoder.layer.8.attention.self.value.bias",
|
| 162 |
+
"encoderLayer.8.multiHeadAttention.o.weight": "encoder.layer.8.attention.output.dense.weight",
|
| 163 |
+
"encoderLayer.8.multiHeadAttention.o.bias": "encoder.layer.8.attention.output.dense.bias",
|
| 164 |
+
"encoderLayer.8.attnLayerNorm.weight": "encoder.layer.8.attention.output.LayerNorm.weight",
|
| 165 |
+
"encoderLayer.8.attnLayerNorm.bias": "encoder.layer.8.attention.output.LayerNorm.bias",
|
| 166 |
+
"encoderLayer.8.feedForward.intermediateDense.weight": "encoder.layer.8.intermediate.dense.weight",
|
| 167 |
+
"encoderLayer.8.feedForward.intermediateDense.bias": "encoder.layer.8.intermediate.dense.bias",
|
| 168 |
+
"encoderLayer.8.feedForward.outputDense.weight": "encoder.layer.8.output.dense.weight",
|
| 169 |
+
"encoderLayer.8.feedForward.outputDense.bias": "encoder.layer.8.output.dense.bias",
|
| 170 |
+
"encoderLayer.8.ffnLayerNorm.weight": "encoder.layer.8.output.LayerNorm.weight",
|
| 171 |
+
"encoderLayer.8.ffnLayerNorm.bias": "encoder.layer.8.output.LayerNorm.bias",
|
| 172 |
+
"encoderLayer.9.multiHeadAttention.q.weight": "encoder.layer.9.attention.self.query.weight",
|
| 173 |
+
"encoderLayer.9.multiHeadAttention.q.bias": "encoder.layer.9.attention.self.query.bias",
|
| 174 |
+
"encoderLayer.9.multiHeadAttention.k.weight": "encoder.layer.9.attention.self.key.weight",
|
| 175 |
+
"encoderLayer.9.multiHeadAttention.k.bias": "encoder.layer.9.attention.self.key.bias",
|
| 176 |
+
"encoderLayer.9.multiHeadAttention.v.weight": "encoder.layer.9.attention.self.value.weight",
|
| 177 |
+
"encoderLayer.9.multiHeadAttention.v.bias": "encoder.layer.9.attention.self.value.bias",
|
| 178 |
+
"encoderLayer.9.multiHeadAttention.o.weight": "encoder.layer.9.attention.output.dense.weight",
|
| 179 |
+
"encoderLayer.9.multiHeadAttention.o.bias": "encoder.layer.9.attention.output.dense.bias",
|
| 180 |
+
"encoderLayer.9.attnLayerNorm.weight": "encoder.layer.9.attention.output.LayerNorm.weight",
|
| 181 |
+
"encoderLayer.9.attnLayerNorm.bias": "encoder.layer.9.attention.output.LayerNorm.bias",
|
| 182 |
+
"encoderLayer.9.feedForward.intermediateDense.weight": "encoder.layer.9.intermediate.dense.weight",
|
| 183 |
+
"encoderLayer.9.feedForward.intermediateDense.bias": "encoder.layer.9.intermediate.dense.bias",
|
| 184 |
+
"encoderLayer.9.feedForward.outputDense.weight": "encoder.layer.9.output.dense.weight",
|
| 185 |
+
"encoderLayer.9.feedForward.outputDense.bias": "encoder.layer.9.output.dense.bias",
|
| 186 |
+
"encoderLayer.9.ffnLayerNorm.weight": "encoder.layer.9.output.LayerNorm.weight",
|
| 187 |
+
"encoderLayer.9.ffnLayerNorm.bias": "encoder.layer.9.output.LayerNorm.bias",
|
| 188 |
+
"encoderLayer.10.multiHeadAttention.q.weight": "encoder.layer.10.attention.self.query.weight",
|
| 189 |
+
"encoderLayer.10.multiHeadAttention.q.bias": "encoder.layer.10.attention.self.query.bias",
|
| 190 |
+
"encoderLayer.10.multiHeadAttention.k.weight": "encoder.layer.10.attention.self.key.weight",
|
| 191 |
+
"encoderLayer.10.multiHeadAttention.k.bias": "encoder.layer.10.attention.self.key.bias",
|
| 192 |
+
"encoderLayer.10.multiHeadAttention.v.weight": "encoder.layer.10.attention.self.value.weight",
|
| 193 |
+
"encoderLayer.10.multiHeadAttention.v.bias": "encoder.layer.10.attention.self.value.bias",
|
| 194 |
+
"encoderLayer.10.multiHeadAttention.o.weight": "encoder.layer.10.attention.output.dense.weight",
|
| 195 |
+
"encoderLayer.10.multiHeadAttention.o.bias": "encoder.layer.10.attention.output.dense.bias",
|
| 196 |
+
"encoderLayer.10.attnLayerNorm.weight": "encoder.layer.10.attention.output.LayerNorm.weight",
|
| 197 |
+
"encoderLayer.10.attnLayerNorm.bias": "encoder.layer.10.attention.output.LayerNorm.bias",
|
| 198 |
+
"encoderLayer.10.feedForward.intermediateDense.weight": "encoder.layer.10.intermediate.dense.weight",
|
| 199 |
+
"encoderLayer.10.feedForward.intermediateDense.bias": "encoder.layer.10.intermediate.dense.bias",
|
| 200 |
+
"encoderLayer.10.feedForward.outputDense.weight": "encoder.layer.10.output.dense.weight",
|
| 201 |
+
"encoderLayer.10.feedForward.outputDense.bias": "encoder.layer.10.output.dense.bias",
|
| 202 |
+
"encoderLayer.10.ffnLayerNorm.weight": "encoder.layer.10.output.LayerNorm.weight",
|
| 203 |
+
"encoderLayer.10.ffnLayerNorm.bias": "encoder.layer.10.output.LayerNorm.bias",
|
| 204 |
+
"encoderLayer.11.multiHeadAttention.q.weight": "encoder.layer.11.attention.self.query.weight",
|
| 205 |
+
"encoderLayer.11.multiHeadAttention.q.bias": "encoder.layer.11.attention.self.query.bias",
|
| 206 |
+
"encoderLayer.11.multiHeadAttention.k.weight": "encoder.layer.11.attention.self.key.weight",
|
| 207 |
+
"encoderLayer.11.multiHeadAttention.k.bias": "encoder.layer.11.attention.self.key.bias",
|
| 208 |
+
"encoderLayer.11.multiHeadAttention.v.weight": "encoder.layer.11.attention.self.value.weight",
|
| 209 |
+
"encoderLayer.11.multiHeadAttention.v.bias": "encoder.layer.11.attention.self.value.bias",
|
| 210 |
+
"encoderLayer.11.multiHeadAttention.o.weight": "encoder.layer.11.attention.output.dense.weight",
|
| 211 |
+
"encoderLayer.11.multiHeadAttention.o.bias": "encoder.layer.11.attention.output.dense.bias",
|
| 212 |
+
"encoderLayer.11.attnLayerNorm.weight": "encoder.layer.11.attention.output.LayerNorm.weight",
|
| 213 |
+
"encoderLayer.11.attnLayerNorm.bias": "encoder.layer.11.attention.output.LayerNorm.bias",
|
| 214 |
+
"encoderLayer.11.feedForward.intermediateDense.weight": "encoder.layer.11.intermediate.dense.weight",
|
| 215 |
+
"encoderLayer.11.feedForward.intermediateDense.bias": "encoder.layer.11.intermediate.dense.bias",
|
| 216 |
+
"encoderLayer.11.feedForward.outputDense.weight": "encoder.layer.11.output.dense.weight",
|
| 217 |
+
"encoderLayer.11.feedForward.outputDense.bias": "encoder.layer.11.output.dense.bias",
|
| 218 |
+
"encoderLayer.11.ffnLayerNorm.weight": "encoder.layer.11.output.LayerNorm.weight",
|
| 219 |
+
"encoderLayer.11.ffnLayerNorm.bias": "encoder.layer.11.output.LayerNorm.bias"
|
| 220 |
+
}
|
| 221 |
+
}
|
bge-small-zh-v1.5/bert4torch_config.json
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"hidden_act": "gelu",
|
| 4 |
+
"hidden_dropout_prob": 0.1,
|
| 5 |
+
"hidden_size": 512,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 2048,
|
| 8 |
+
"layer_norm_eps": 1e-12,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"model": "bert",
|
| 11 |
+
"num_attention_heads": 8,
|
| 12 |
+
"num_hidden_layers": 4,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"torch_dtype": "float32",
|
| 15 |
+
"type_vocab_size": 2,
|
| 16 |
+
"vocab_size": 21128,
|
| 17 |
+
"with_pool": true,
|
| 18 |
+
"pool_strategy": "cls",
|
| 19 |
+
"norm_mode": "torch_buildin",
|
| 20 |
+
"mapping": {
|
| 21 |
+
"embeddings.word_embeddings.weight": "embeddings.word_embeddings.weight",
|
| 22 |
+
"embeddings.position_embeddings.weight": "embeddings.position_embeddings.weight",
|
| 23 |
+
"embeddings.segment_embeddings.weight": "embeddings.token_type_embeddings.weight",
|
| 24 |
+
"embeddings.layerNorm.weight": "embeddings.LayerNorm.weight",
|
| 25 |
+
"embeddings.layerNorm.bias": "embeddings.LayerNorm.bias",
|
| 26 |
+
"pooler.weight": "pooler.dense.weight",
|
| 27 |
+
"pooler.bias": "pooler.dense.bias",
|
| 28 |
+
"encoderLayer.0.multiHeadAttention.q.weight": "encoder.layer.0.attention.self.query.weight",
|
| 29 |
+
"encoderLayer.0.multiHeadAttention.q.bias": "encoder.layer.0.attention.self.query.bias",
|
| 30 |
+
"encoderLayer.0.multiHeadAttention.k.weight": "encoder.layer.0.attention.self.key.weight",
|
| 31 |
+
"encoderLayer.0.multiHeadAttention.k.bias": "encoder.layer.0.attention.self.key.bias",
|
| 32 |
+
"encoderLayer.0.multiHeadAttention.v.weight": "encoder.layer.0.attention.self.value.weight",
|
| 33 |
+
"encoderLayer.0.multiHeadAttention.v.bias": "encoder.layer.0.attention.self.value.bias",
|
| 34 |
+
"encoderLayer.0.multiHeadAttention.o.weight": "encoder.layer.0.attention.output.dense.weight",
|
| 35 |
+
"encoderLayer.0.multiHeadAttention.o.bias": "encoder.layer.0.attention.output.dense.bias",
|
| 36 |
+
"encoderLayer.0.attnLayerNorm.weight": "encoder.layer.0.attention.output.LayerNorm.weight",
|
| 37 |
+
"encoderLayer.0.attnLayerNorm.bias": "encoder.layer.0.attention.output.LayerNorm.bias",
|
| 38 |
+
"encoderLayer.0.feedForward.intermediateDense.weight": "encoder.layer.0.intermediate.dense.weight",
|
| 39 |
+
"encoderLayer.0.feedForward.intermediateDense.bias": "encoder.layer.0.intermediate.dense.bias",
|
| 40 |
+
"encoderLayer.0.feedForward.outputDense.weight": "encoder.layer.0.output.dense.weight",
|
| 41 |
+
"encoderLayer.0.feedForward.outputDense.bias": "encoder.layer.0.output.dense.bias",
|
| 42 |
+
"encoderLayer.0.ffnLayerNorm.weight": "encoder.layer.0.output.LayerNorm.weight",
|
| 43 |
+
"encoderLayer.0.ffnLayerNorm.bias": "encoder.layer.0.output.LayerNorm.bias",
|
| 44 |
+
"encoderLayer.1.multiHeadAttention.q.weight": "encoder.layer.1.attention.self.query.weight",
|
| 45 |
+
"encoderLayer.1.multiHeadAttention.q.bias": "encoder.layer.1.attention.self.query.bias",
|
| 46 |
+
"encoderLayer.1.multiHeadAttention.k.weight": "encoder.layer.1.attention.self.key.weight",
|
| 47 |
+
"encoderLayer.1.multiHeadAttention.k.bias": "encoder.layer.1.attention.self.key.bias",
|
| 48 |
+
"encoderLayer.1.multiHeadAttention.v.weight": "encoder.layer.1.attention.self.value.weight",
|
| 49 |
+
"encoderLayer.1.multiHeadAttention.v.bias": "encoder.layer.1.attention.self.value.bias",
|
| 50 |
+
"encoderLayer.1.multiHeadAttention.o.weight": "encoder.layer.1.attention.output.dense.weight",
|
| 51 |
+
"encoderLayer.1.multiHeadAttention.o.bias": "encoder.layer.1.attention.output.dense.bias",
|
| 52 |
+
"encoderLayer.1.attnLayerNorm.weight": "encoder.layer.1.attention.output.LayerNorm.weight",
|
| 53 |
+
"encoderLayer.1.attnLayerNorm.bias": "encoder.layer.1.attention.output.LayerNorm.bias",
|
| 54 |
+
"encoderLayer.1.feedForward.intermediateDense.weight": "encoder.layer.1.intermediate.dense.weight",
|
| 55 |
+
"encoderLayer.1.feedForward.intermediateDense.bias": "encoder.layer.1.intermediate.dense.bias",
|
| 56 |
+
"encoderLayer.1.feedForward.outputDense.weight": "encoder.layer.1.output.dense.weight",
|
| 57 |
+
"encoderLayer.1.feedForward.outputDense.bias": "encoder.layer.1.output.dense.bias",
|
| 58 |
+
"encoderLayer.1.ffnLayerNorm.weight": "encoder.layer.1.output.LayerNorm.weight",
|
| 59 |
+
"encoderLayer.1.ffnLayerNorm.bias": "encoder.layer.1.output.LayerNorm.bias",
|
| 60 |
+
"encoderLayer.2.multiHeadAttention.q.weight": "encoder.layer.2.attention.self.query.weight",
|
| 61 |
+
"encoderLayer.2.multiHeadAttention.q.bias": "encoder.layer.2.attention.self.query.bias",
|
| 62 |
+
"encoderLayer.2.multiHeadAttention.k.weight": "encoder.layer.2.attention.self.key.weight",
|
| 63 |
+
"encoderLayer.2.multiHeadAttention.k.bias": "encoder.layer.2.attention.self.key.bias",
|
| 64 |
+
"encoderLayer.2.multiHeadAttention.v.weight": "encoder.layer.2.attention.self.value.weight",
|
| 65 |
+
"encoderLayer.2.multiHeadAttention.v.bias": "encoder.layer.2.attention.self.value.bias",
|
| 66 |
+
"encoderLayer.2.multiHeadAttention.o.weight": "encoder.layer.2.attention.output.dense.weight",
|
| 67 |
+
"encoderLayer.2.multiHeadAttention.o.bias": "encoder.layer.2.attention.output.dense.bias",
|
| 68 |
+
"encoderLayer.2.attnLayerNorm.weight": "encoder.layer.2.attention.output.LayerNorm.weight",
|
| 69 |
+
"encoderLayer.2.attnLayerNorm.bias": "encoder.layer.2.attention.output.LayerNorm.bias",
|
| 70 |
+
"encoderLayer.2.feedForward.intermediateDense.weight": "encoder.layer.2.intermediate.dense.weight",
|
| 71 |
+
"encoderLayer.2.feedForward.intermediateDense.bias": "encoder.layer.2.intermediate.dense.bias",
|
| 72 |
+
"encoderLayer.2.feedForward.outputDense.weight": "encoder.layer.2.output.dense.weight",
|
| 73 |
+
"encoderLayer.2.feedForward.outputDense.bias": "encoder.layer.2.output.dense.bias",
|
| 74 |
+
"encoderLayer.2.ffnLayerNorm.weight": "encoder.layer.2.output.LayerNorm.weight",
|
| 75 |
+
"encoderLayer.2.ffnLayerNorm.bias": "encoder.layer.2.output.LayerNorm.bias",
|
| 76 |
+
"encoderLayer.3.multiHeadAttention.q.weight": "encoder.layer.3.attention.self.query.weight",
|
| 77 |
+
"encoderLayer.3.multiHeadAttention.q.bias": "encoder.layer.3.attention.self.query.bias",
|
| 78 |
+
"encoderLayer.3.multiHeadAttention.k.weight": "encoder.layer.3.attention.self.key.weight",
|
| 79 |
+
"encoderLayer.3.multiHeadAttention.k.bias": "encoder.layer.3.attention.self.key.bias",
|
| 80 |
+
"encoderLayer.3.multiHeadAttention.v.weight": "encoder.layer.3.attention.self.value.weight",
|
| 81 |
+
"encoderLayer.3.multiHeadAttention.v.bias": "encoder.layer.3.attention.self.value.bias",
|
| 82 |
+
"encoderLayer.3.multiHeadAttention.o.weight": "encoder.layer.3.attention.output.dense.weight",
|
| 83 |
+
"encoderLayer.3.multiHeadAttention.o.bias": "encoder.layer.3.attention.output.dense.bias",
|
| 84 |
+
"encoderLayer.3.attnLayerNorm.weight": "encoder.layer.3.attention.output.LayerNorm.weight",
|
| 85 |
+
"encoderLayer.3.attnLayerNorm.bias": "encoder.layer.3.attention.output.LayerNorm.bias",
|
| 86 |
+
"encoderLayer.3.feedForward.intermediateDense.weight": "encoder.layer.3.intermediate.dense.weight",
|
| 87 |
+
"encoderLayer.3.feedForward.intermediateDense.bias": "encoder.layer.3.intermediate.dense.bias",
|
| 88 |
+
"encoderLayer.3.feedForward.outputDense.weight": "encoder.layer.3.output.dense.weight",
|
| 89 |
+
"encoderLayer.3.feedForward.outputDense.bias": "encoder.layer.3.output.dense.bias",
|
| 90 |
+
"encoderLayer.3.ffnLayerNorm.weight": "encoder.layer.3.output.LayerNorm.weight",
|
| 91 |
+
"encoderLayer.3.ffnLayerNorm.bias": "encoder.layer.3.output.LayerNorm.bias",
|
| 92 |
+
"encoderLayer.4.multiHeadAttention.q.weight": "encoder.layer.4.attention.self.query.weight",
|
| 93 |
+
"encoderLayer.4.multiHeadAttention.q.bias": "encoder.layer.4.attention.self.query.bias",
|
| 94 |
+
"encoderLayer.4.multiHeadAttention.k.weight": "encoder.layer.4.attention.self.key.weight",
|
| 95 |
+
"encoderLayer.4.multiHeadAttention.k.bias": "encoder.layer.4.attention.self.key.bias",
|
| 96 |
+
"encoderLayer.4.multiHeadAttention.v.weight": "encoder.layer.4.attention.self.value.weight",
|
| 97 |
+
"encoderLayer.4.multiHeadAttention.v.bias": "encoder.layer.4.attention.self.value.bias",
|
| 98 |
+
"encoderLayer.4.multiHeadAttention.o.weight": "encoder.layer.4.attention.output.dense.weight",
|
| 99 |
+
"encoderLayer.4.multiHeadAttention.o.bias": "encoder.layer.4.attention.output.dense.bias",
|
| 100 |
+
"encoderLayer.4.attnLayerNorm.weight": "encoder.layer.4.attention.output.LayerNorm.weight",
|
| 101 |
+
"encoderLayer.4.attnLayerNorm.bias": "encoder.layer.4.attention.output.LayerNorm.bias",
|
| 102 |
+
"encoderLayer.4.feedForward.intermediateDense.weight": "encoder.layer.4.intermediate.dense.weight",
|
| 103 |
+
"encoderLayer.4.feedForward.intermediateDense.bias": "encoder.layer.4.intermediate.dense.bias",
|
| 104 |
+
"encoderLayer.4.feedForward.outputDense.weight": "encoder.layer.4.output.dense.weight",
|
| 105 |
+
"encoderLayer.4.feedForward.outputDense.bias": "encoder.layer.4.output.dense.bias",
|
| 106 |
+
"encoderLayer.4.ffnLayerNorm.weight": "encoder.layer.4.output.LayerNorm.weight",
|
| 107 |
+
"encoderLayer.4.ffnLayerNorm.bias": "encoder.layer.4.output.LayerNorm.bias",
|
| 108 |
+
"encoderLayer.5.multiHeadAttention.q.weight": "encoder.layer.5.attention.self.query.weight",
|
| 109 |
+
"encoderLayer.5.multiHeadAttention.q.bias": "encoder.layer.5.attention.self.query.bias",
|
| 110 |
+
"encoderLayer.5.multiHeadAttention.k.weight": "encoder.layer.5.attention.self.key.weight",
|
| 111 |
+
"encoderLayer.5.multiHeadAttention.k.bias": "encoder.layer.5.attention.self.key.bias",
|
| 112 |
+
"encoderLayer.5.multiHeadAttention.v.weight": "encoder.layer.5.attention.self.value.weight",
|
| 113 |
+
"encoderLayer.5.multiHeadAttention.v.bias": "encoder.layer.5.attention.self.value.bias",
|
| 114 |
+
"encoderLayer.5.multiHeadAttention.o.weight": "encoder.layer.5.attention.output.dense.weight",
|
| 115 |
+
"encoderLayer.5.multiHeadAttention.o.bias": "encoder.layer.5.attention.output.dense.bias",
|
| 116 |
+
"encoderLayer.5.attnLayerNorm.weight": "encoder.layer.5.attention.output.LayerNorm.weight",
|
| 117 |
+
"encoderLayer.5.attnLayerNorm.bias": "encoder.layer.5.attention.output.LayerNorm.bias",
|
| 118 |
+
"encoderLayer.5.feedForward.intermediateDense.weight": "encoder.layer.5.intermediate.dense.weight",
|
| 119 |
+
"encoderLayer.5.feedForward.intermediateDense.bias": "encoder.layer.5.intermediate.dense.bias",
|
| 120 |
+
"encoderLayer.5.feedForward.outputDense.weight": "encoder.layer.5.output.dense.weight",
|
| 121 |
+
"encoderLayer.5.feedForward.outputDense.bias": "encoder.layer.5.output.dense.bias",
|
| 122 |
+
"encoderLayer.5.ffnLayerNorm.weight": "encoder.layer.5.output.LayerNorm.weight",
|
| 123 |
+
"encoderLayer.5.ffnLayerNorm.bias": "encoder.layer.5.output.LayerNorm.bias",
|
| 124 |
+
"encoderLayer.6.multiHeadAttention.q.weight": "encoder.layer.6.attention.self.query.weight",
|
| 125 |
+
"encoderLayer.6.multiHeadAttention.q.bias": "encoder.layer.6.attention.self.query.bias",
|
| 126 |
+
"encoderLayer.6.multiHeadAttention.k.weight": "encoder.layer.6.attention.self.key.weight",
|
| 127 |
+
"encoderLayer.6.multiHeadAttention.k.bias": "encoder.layer.6.attention.self.key.bias",
|
| 128 |
+
"encoderLayer.6.multiHeadAttention.v.weight": "encoder.layer.6.attention.self.value.weight",
|
| 129 |
+
"encoderLayer.6.multiHeadAttention.v.bias": "encoder.layer.6.attention.self.value.bias",
|
| 130 |
+
"encoderLayer.6.multiHeadAttention.o.weight": "encoder.layer.6.attention.output.dense.weight",
|
| 131 |
+
"encoderLayer.6.multiHeadAttention.o.bias": "encoder.layer.6.attention.output.dense.bias",
|
| 132 |
+
"encoderLayer.6.attnLayerNorm.weight": "encoder.layer.6.attention.output.LayerNorm.weight",
|
| 133 |
+
"encoderLayer.6.attnLayerNorm.bias": "encoder.layer.6.attention.output.LayerNorm.bias",
|
| 134 |
+
"encoderLayer.6.feedForward.intermediateDense.weight": "encoder.layer.6.intermediate.dense.weight",
|
| 135 |
+
"encoderLayer.6.feedForward.intermediateDense.bias": "encoder.layer.6.intermediate.dense.bias",
|
| 136 |
+
"encoderLayer.6.feedForward.outputDense.weight": "encoder.layer.6.output.dense.weight",
|
| 137 |
+
"encoderLayer.6.feedForward.outputDense.bias": "encoder.layer.6.output.dense.bias",
|
| 138 |
+
"encoderLayer.6.ffnLayerNorm.weight": "encoder.layer.6.output.LayerNorm.weight",
|
| 139 |
+
"encoderLayer.6.ffnLayerNorm.bias": "encoder.layer.6.output.LayerNorm.bias",
|
| 140 |
+
"encoderLayer.7.multiHeadAttention.q.weight": "encoder.layer.7.attention.self.query.weight",
|
| 141 |
+
"encoderLayer.7.multiHeadAttention.q.bias": "encoder.layer.7.attention.self.query.bias",
|
| 142 |
+
"encoderLayer.7.multiHeadAttention.k.weight": "encoder.layer.7.attention.self.key.weight",
|
| 143 |
+
"encoderLayer.7.multiHeadAttention.k.bias": "encoder.layer.7.attention.self.key.bias",
|
| 144 |
+
"encoderLayer.7.multiHeadAttention.v.weight": "encoder.layer.7.attention.self.value.weight",
|
| 145 |
+
"encoderLayer.7.multiHeadAttention.v.bias": "encoder.layer.7.attention.self.value.bias",
|
| 146 |
+
"encoderLayer.7.multiHeadAttention.o.weight": "encoder.layer.7.attention.output.dense.weight",
|
| 147 |
+
"encoderLayer.7.multiHeadAttention.o.bias": "encoder.layer.7.attention.output.dense.bias",
|
| 148 |
+
"encoderLayer.7.attnLayerNorm.weight": "encoder.layer.7.attention.output.LayerNorm.weight",
|
| 149 |
+
"encoderLayer.7.attnLayerNorm.bias": "encoder.layer.7.attention.output.LayerNorm.bias",
|
| 150 |
+
"encoderLayer.7.feedForward.intermediateDense.weight": "encoder.layer.7.intermediate.dense.weight",
|
| 151 |
+
"encoderLayer.7.feedForward.intermediateDense.bias": "encoder.layer.7.intermediate.dense.bias",
|
| 152 |
+
"encoderLayer.7.feedForward.outputDense.weight": "encoder.layer.7.output.dense.weight",
|
| 153 |
+
"encoderLayer.7.feedForward.outputDense.bias": "encoder.layer.7.output.dense.bias",
|
| 154 |
+
"encoderLayer.7.ffnLayerNorm.weight": "encoder.layer.7.output.LayerNorm.weight",
|
| 155 |
+
"encoderLayer.7.ffnLayerNorm.bias": "encoder.layer.7.output.LayerNorm.bias",
|
| 156 |
+
"encoderLayer.8.multiHeadAttention.q.weight": "encoder.layer.8.attention.self.query.weight",
|
| 157 |
+
"encoderLayer.8.multiHeadAttention.q.bias": "encoder.layer.8.attention.self.query.bias",
|
| 158 |
+
"encoderLayer.8.multiHeadAttention.k.weight": "encoder.layer.8.attention.self.key.weight",
|
| 159 |
+
"encoderLayer.8.multiHeadAttention.k.bias": "encoder.layer.8.attention.self.key.bias",
|
| 160 |
+
"encoderLayer.8.multiHeadAttention.v.weight": "encoder.layer.8.attention.self.value.weight",
|
| 161 |
+
"encoderLayer.8.multiHeadAttention.v.bias": "encoder.layer.8.attention.self.value.bias",
|
| 162 |
+
"encoderLayer.8.multiHeadAttention.o.weight": "encoder.layer.8.attention.output.dense.weight",
|
| 163 |
+
"encoderLayer.8.multiHeadAttention.o.bias": "encoder.layer.8.attention.output.dense.bias",
|
| 164 |
+
"encoderLayer.8.attnLayerNorm.weight": "encoder.layer.8.attention.output.LayerNorm.weight",
|
| 165 |
+
"encoderLayer.8.attnLayerNorm.bias": "encoder.layer.8.attention.output.LayerNorm.bias",
|
| 166 |
+
"encoderLayer.8.feedForward.intermediateDense.weight": "encoder.layer.8.intermediate.dense.weight",
|
| 167 |
+
"encoderLayer.8.feedForward.intermediateDense.bias": "encoder.layer.8.intermediate.dense.bias",
|
| 168 |
+
"encoderLayer.8.feedForward.outputDense.weight": "encoder.layer.8.output.dense.weight",
|
| 169 |
+
"encoderLayer.8.feedForward.outputDense.bias": "encoder.layer.8.output.dense.bias",
|
| 170 |
+
"encoderLayer.8.ffnLayerNorm.weight": "encoder.layer.8.output.LayerNorm.weight",
|
| 171 |
+
"encoderLayer.8.ffnLayerNorm.bias": "encoder.layer.8.output.LayerNorm.bias",
|
| 172 |
+
"encoderLayer.9.multiHeadAttention.q.weight": "encoder.layer.9.attention.self.query.weight",
|
| 173 |
+
"encoderLayer.9.multiHeadAttention.q.bias": "encoder.layer.9.attention.self.query.bias",
|
| 174 |
+
"encoderLayer.9.multiHeadAttention.k.weight": "encoder.layer.9.attention.self.key.weight",
|
| 175 |
+
"encoderLayer.9.multiHeadAttention.k.bias": "encoder.layer.9.attention.self.key.bias",
|
| 176 |
+
"encoderLayer.9.multiHeadAttention.v.weight": "encoder.layer.9.attention.self.value.weight",
|
| 177 |
+
"encoderLayer.9.multiHeadAttention.v.bias": "encoder.layer.9.attention.self.value.bias",
|
| 178 |
+
"encoderLayer.9.multiHeadAttention.o.weight": "encoder.layer.9.attention.output.dense.weight",
|
| 179 |
+
"encoderLayer.9.multiHeadAttention.o.bias": "encoder.layer.9.attention.output.dense.bias",
|
| 180 |
+
"encoderLayer.9.attnLayerNorm.weight": "encoder.layer.9.attention.output.LayerNorm.weight",
|
| 181 |
+
"encoderLayer.9.attnLayerNorm.bias": "encoder.layer.9.attention.output.LayerNorm.bias",
|
| 182 |
+
"encoderLayer.9.feedForward.intermediateDense.weight": "encoder.layer.9.intermediate.dense.weight",
|
| 183 |
+
"encoderLayer.9.feedForward.intermediateDense.bias": "encoder.layer.9.intermediate.dense.bias",
|
| 184 |
+
"encoderLayer.9.feedForward.outputDense.weight": "encoder.layer.9.output.dense.weight",
|
| 185 |
+
"encoderLayer.9.feedForward.outputDense.bias": "encoder.layer.9.output.dense.bias",
|
| 186 |
+
"encoderLayer.9.ffnLayerNorm.weight": "encoder.layer.9.output.LayerNorm.weight",
|
| 187 |
+
"encoderLayer.9.ffnLayerNorm.bias": "encoder.layer.9.output.LayerNorm.bias",
|
| 188 |
+
"encoderLayer.10.multiHeadAttention.q.weight": "encoder.layer.10.attention.self.query.weight",
|
| 189 |
+
"encoderLayer.10.multiHeadAttention.q.bias": "encoder.layer.10.attention.self.query.bias",
|
| 190 |
+
"encoderLayer.10.multiHeadAttention.k.weight": "encoder.layer.10.attention.self.key.weight",
|
| 191 |
+
"encoderLayer.10.multiHeadAttention.k.bias": "encoder.layer.10.attention.self.key.bias",
|
| 192 |
+
"encoderLayer.10.multiHeadAttention.v.weight": "encoder.layer.10.attention.self.value.weight",
|
| 193 |
+
"encoderLayer.10.multiHeadAttention.v.bias": "encoder.layer.10.attention.self.value.bias",
|
| 194 |
+
"encoderLayer.10.multiHeadAttention.o.weight": "encoder.layer.10.attention.output.dense.weight",
|
| 195 |
+
"encoderLayer.10.multiHeadAttention.o.bias": "encoder.layer.10.attention.output.dense.bias",
|
| 196 |
+
"encoderLayer.10.attnLayerNorm.weight": "encoder.layer.10.attention.output.LayerNorm.weight",
|
| 197 |
+
"encoderLayer.10.attnLayerNorm.bias": "encoder.layer.10.attention.output.LayerNorm.bias",
|
| 198 |
+
"encoderLayer.10.feedForward.intermediateDense.weight": "encoder.layer.10.intermediate.dense.weight",
|
| 199 |
+
"encoderLayer.10.feedForward.intermediateDense.bias": "encoder.layer.10.intermediate.dense.bias",
|
| 200 |
+
"encoderLayer.10.feedForward.outputDense.weight": "encoder.layer.10.output.dense.weight",
|
| 201 |
+
"encoderLayer.10.feedForward.outputDense.bias": "encoder.layer.10.output.dense.bias",
|
| 202 |
+
"encoderLayer.10.ffnLayerNorm.weight": "encoder.layer.10.output.LayerNorm.weight",
|
| 203 |
+
"encoderLayer.10.ffnLayerNorm.bias": "encoder.layer.10.output.LayerNorm.bias",
|
| 204 |
+
"encoderLayer.11.multiHeadAttention.q.weight": "encoder.layer.11.attention.self.query.weight",
|
| 205 |
+
"encoderLayer.11.multiHeadAttention.q.bias": "encoder.layer.11.attention.self.query.bias",
|
| 206 |
+
"encoderLayer.11.multiHeadAttention.k.weight": "encoder.layer.11.attention.self.key.weight",
|
| 207 |
+
"encoderLayer.11.multiHeadAttention.k.bias": "encoder.layer.11.attention.self.key.bias",
|
| 208 |
+
"encoderLayer.11.multiHeadAttention.v.weight": "encoder.layer.11.attention.self.value.weight",
|
| 209 |
+
"encoderLayer.11.multiHeadAttention.v.bias": "encoder.layer.11.attention.self.value.bias",
|
| 210 |
+
"encoderLayer.11.multiHeadAttention.o.weight": "encoder.layer.11.attention.output.dense.weight",
|
| 211 |
+
"encoderLayer.11.multiHeadAttention.o.bias": "encoder.layer.11.attention.output.dense.bias",
|
| 212 |
+
"encoderLayer.11.attnLayerNorm.weight": "encoder.layer.11.attention.output.LayerNorm.weight",
|
| 213 |
+
"encoderLayer.11.attnLayerNorm.bias": "encoder.layer.11.attention.output.LayerNorm.bias",
|
| 214 |
+
"encoderLayer.11.feedForward.intermediateDense.weight": "encoder.layer.11.intermediate.dense.weight",
|
| 215 |
+
"encoderLayer.11.feedForward.intermediateDense.bias": "encoder.layer.11.intermediate.dense.bias",
|
| 216 |
+
"encoderLayer.11.feedForward.outputDense.weight": "encoder.layer.11.output.dense.weight",
|
| 217 |
+
"encoderLayer.11.feedForward.outputDense.bias": "encoder.layer.11.output.dense.bias",
|
| 218 |
+
"encoderLayer.11.ffnLayerNorm.weight": "encoder.layer.11.output.LayerNorm.weight",
|
| 219 |
+
"encoderLayer.11.ffnLayerNorm.bias": "encoder.layer.11.output.LayerNorm.bias"
|
| 220 |
+
}
|
| 221 |
+
}
|