Upload LeanAlbertForPreTraining
Browse files- config.json +42 -0
- pytorch_model-00001-of-00004.bin +3 -0
- pytorch_model-00002-of-00004.bin +3 -0
- pytorch_model-00003-of-00004.bin +3 -0
- pytorch_model-00004-of-00004.bin +3 -0
- pytorch_model.bin.index.json +410 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"adapter_dim": 0,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LeanAlbertForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"attn_qkv_bias": true,
|
| 8 |
+
"block_size": 0,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"classifier_dropout_prob": 0.1,
|
| 11 |
+
"embedding_size": 128,
|
| 12 |
+
"eos_token_id": 3,
|
| 13 |
+
"hidden_act": "gelu_fused",
|
| 14 |
+
"hidden_act_gated": true,
|
| 15 |
+
"hidden_dropout_prob": 0,
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"inner_group_num": 1,
|
| 19 |
+
"intermediate_size": 16384,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"lowrank_dim": 0,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"num_attention_heads": 64,
|
| 24 |
+
"num_hidden_groups": 32,
|
| 25 |
+
"num_hidden_layers": 32,
|
| 26 |
+
"num_inner_groups": 1,
|
| 27 |
+
"num_inner_matrices": 1,
|
| 28 |
+
"num_memory_blocks": 0,
|
| 29 |
+
"num_shared_matrices": 1,
|
| 30 |
+
"out_proj_bias": true,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "rotary",
|
| 33 |
+
"rotary_embedding_base": 10000,
|
| 34 |
+
"sandwich_norm": false,
|
| 35 |
+
"share_large_matrices": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"total_num_layer_groups": 32,
|
| 38 |
+
"total_shared_matrix_sets": 1,
|
| 39 |
+
"transformers_version": "4.24.0",
|
| 40 |
+
"type_vocab_size": 2,
|
| 41 |
+
"vocab_size": 50005
|
| 42 |
+
}
|
pytorch_model-00001-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20855d68e88294c3a3c16ba6a79e8373509cceb85c0a5396adc80bfb188a3037
|
| 3 |
+
size 1104232557
|
pytorch_model-00002-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14405235c03af56e11049a02633e0cc113b29e7ddaa70402c05a24152ab87a53
|
| 3 |
+
size 1076280999
|
pytorch_model-00003-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7c671915cdd977db5ca86852e249483958c8e8032de06487c23609df63a15f1
|
| 3 |
+
size 1076280999
|
pytorch_model-00004-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:303cd9f0601ab7774d7c2eb7b3f903408035ed6afa800786380c8138b1c97484
|
| 3 |
+
size 1170017317
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 34491661488
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"albert.embeddings.embedding_hidden_mapping.bias": "pytorch_model-00001-of-00004.bin",
|
| 7 |
+
"albert.embeddings.embedding_hidden_mapping.weight": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"albert.embeddings.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"albert.embeddings.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"albert.embeddings.token_type_embeddings.weight": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"albert.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"albert.pooler.bias": "pytorch_model-00004-of-00004.bin",
|
| 13 |
+
"albert.pooler.weight": "pytorch_model-00004-of-00004.bin",
|
| 14 |
+
"albert.transformer.layer_groups.0.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"albert.transformer.layer_groups.0.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"albert.transformer.layer_groups.0.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"albert.transformer.layer_groups.0.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"albert.transformer.layer_groups.0.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"albert.transformer.layer_groups.0.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"albert.transformer.layer_groups.0.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"albert.transformer.layer_groups.1.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"albert.transformer.layer_groups.1.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"albert.transformer.layer_groups.1.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"albert.transformer.layer_groups.1.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"albert.transformer.layer_groups.1.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"albert.transformer.layer_groups.1.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 33 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 34 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 35 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 36 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 37 |
+
"albert.transformer.layer_groups.1.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 38 |
+
"albert.transformer.layer_groups.10.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 39 |
+
"albert.transformer.layer_groups.10.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 40 |
+
"albert.transformer.layer_groups.10.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 41 |
+
"albert.transformer.layer_groups.10.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 42 |
+
"albert.transformer.layer_groups.10.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 43 |
+
"albert.transformer.layer_groups.10.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 44 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 45 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 46 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 47 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 48 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 49 |
+
"albert.transformer.layer_groups.10.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 50 |
+
"albert.transformer.layer_groups.11.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 51 |
+
"albert.transformer.layer_groups.11.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 52 |
+
"albert.transformer.layer_groups.11.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 53 |
+
"albert.transformer.layer_groups.11.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 54 |
+
"albert.transformer.layer_groups.11.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 55 |
+
"albert.transformer.layer_groups.11.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 56 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 57 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 58 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 59 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 60 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 61 |
+
"albert.transformer.layer_groups.11.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 62 |
+
"albert.transformer.layer_groups.12.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 63 |
+
"albert.transformer.layer_groups.12.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 64 |
+
"albert.transformer.layer_groups.12.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 65 |
+
"albert.transformer.layer_groups.12.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 66 |
+
"albert.transformer.layer_groups.12.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 67 |
+
"albert.transformer.layer_groups.12.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 68 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 69 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 70 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 71 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 72 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 73 |
+
"albert.transformer.layer_groups.12.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 74 |
+
"albert.transformer.layer_groups.13.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 75 |
+
"albert.transformer.layer_groups.13.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 76 |
+
"albert.transformer.layer_groups.13.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 77 |
+
"albert.transformer.layer_groups.13.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"albert.transformer.layer_groups.13.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"albert.transformer.layer_groups.13.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"albert.transformer.layer_groups.13.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"albert.transformer.layer_groups.14.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"albert.transformer.layer_groups.14.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"albert.transformer.layer_groups.14.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 89 |
+
"albert.transformer.layer_groups.14.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 90 |
+
"albert.transformer.layer_groups.14.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 91 |
+
"albert.transformer.layer_groups.14.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 92 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 93 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 94 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 95 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 96 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 97 |
+
"albert.transformer.layer_groups.14.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 98 |
+
"albert.transformer.layer_groups.15.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 99 |
+
"albert.transformer.layer_groups.15.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 100 |
+
"albert.transformer.layer_groups.15.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"albert.transformer.layer_groups.15.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"albert.transformer.layer_groups.15.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"albert.transformer.layer_groups.15.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"albert.transformer.layer_groups.15.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"albert.transformer.layer_groups.16.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"albert.transformer.layer_groups.16.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"albert.transformer.layer_groups.16.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"albert.transformer.layer_groups.16.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"albert.transformer.layer_groups.16.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"albert.transformer.layer_groups.16.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"albert.transformer.layer_groups.16.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"albert.transformer.layer_groups.17.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"albert.transformer.layer_groups.17.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"albert.transformer.layer_groups.17.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"albert.transformer.layer_groups.17.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"albert.transformer.layer_groups.17.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"albert.transformer.layer_groups.17.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 129 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 130 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 132 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 133 |
+
"albert.transformer.layer_groups.17.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"albert.transformer.layer_groups.18.layers.0.attention.dense_out.bias": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"albert.transformer.layer_groups.18.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"albert.transformer.layer_groups.18.layers.0.attention.dense_qkv.bias": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"albert.transformer.layer_groups.18.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"albert.transformer.layer_groups.18.layers.0.attention.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"albert.transformer.layer_groups.18.layers.0.attention.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 141 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 142 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.dense_i2h.bias": "pytorch_model-00002-of-00004.bin",
|
| 143 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 144 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 145 |
+
"albert.transformer.layer_groups.18.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 146 |
+
"albert.transformer.layer_groups.19.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 147 |
+
"albert.transformer.layer_groups.19.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 148 |
+
"albert.transformer.layer_groups.19.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 149 |
+
"albert.transformer.layer_groups.19.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 150 |
+
"albert.transformer.layer_groups.19.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 151 |
+
"albert.transformer.layer_groups.19.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 152 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 153 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 154 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 155 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 156 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 157 |
+
"albert.transformer.layer_groups.19.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 158 |
+
"albert.transformer.layer_groups.2.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 159 |
+
"albert.transformer.layer_groups.2.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 160 |
+
"albert.transformer.layer_groups.2.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 161 |
+
"albert.transformer.layer_groups.2.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 162 |
+
"albert.transformer.layer_groups.2.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 163 |
+
"albert.transformer.layer_groups.2.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 164 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 165 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 166 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 167 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 168 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 169 |
+
"albert.transformer.layer_groups.2.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 170 |
+
"albert.transformer.layer_groups.20.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 171 |
+
"albert.transformer.layer_groups.20.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 172 |
+
"albert.transformer.layer_groups.20.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 173 |
+
"albert.transformer.layer_groups.20.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 174 |
+
"albert.transformer.layer_groups.20.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 175 |
+
"albert.transformer.layer_groups.20.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 176 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 177 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 178 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 179 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 180 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 181 |
+
"albert.transformer.layer_groups.20.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 182 |
+
"albert.transformer.layer_groups.21.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 183 |
+
"albert.transformer.layer_groups.21.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 184 |
+
"albert.transformer.layer_groups.21.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 185 |
+
"albert.transformer.layer_groups.21.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 186 |
+
"albert.transformer.layer_groups.21.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 187 |
+
"albert.transformer.layer_groups.21.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 188 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 189 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 190 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 191 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 192 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 193 |
+
"albert.transformer.layer_groups.21.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 194 |
+
"albert.transformer.layer_groups.22.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 195 |
+
"albert.transformer.layer_groups.22.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 196 |
+
"albert.transformer.layer_groups.22.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 197 |
+
"albert.transformer.layer_groups.22.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 198 |
+
"albert.transformer.layer_groups.22.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 199 |
+
"albert.transformer.layer_groups.22.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 200 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 201 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 202 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 203 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 204 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 205 |
+
"albert.transformer.layer_groups.22.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 206 |
+
"albert.transformer.layer_groups.23.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 207 |
+
"albert.transformer.layer_groups.23.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 208 |
+
"albert.transformer.layer_groups.23.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 209 |
+
"albert.transformer.layer_groups.23.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 210 |
+
"albert.transformer.layer_groups.23.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 211 |
+
"albert.transformer.layer_groups.23.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 212 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 213 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 214 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 215 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 216 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 217 |
+
"albert.transformer.layer_groups.23.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 218 |
+
"albert.transformer.layer_groups.24.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 219 |
+
"albert.transformer.layer_groups.24.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 220 |
+
"albert.transformer.layer_groups.24.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 221 |
+
"albert.transformer.layer_groups.24.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 222 |
+
"albert.transformer.layer_groups.24.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 223 |
+
"albert.transformer.layer_groups.24.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 224 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 225 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 226 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 227 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 228 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 229 |
+
"albert.transformer.layer_groups.24.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 230 |
+
"albert.transformer.layer_groups.25.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 231 |
+
"albert.transformer.layer_groups.25.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 232 |
+
"albert.transformer.layer_groups.25.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 233 |
+
"albert.transformer.layer_groups.25.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 234 |
+
"albert.transformer.layer_groups.25.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 235 |
+
"albert.transformer.layer_groups.25.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 236 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 237 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 238 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 239 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 240 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 241 |
+
"albert.transformer.layer_groups.25.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 242 |
+
"albert.transformer.layer_groups.26.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 243 |
+
"albert.transformer.layer_groups.26.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 244 |
+
"albert.transformer.layer_groups.26.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 245 |
+
"albert.transformer.layer_groups.26.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 246 |
+
"albert.transformer.layer_groups.26.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 247 |
+
"albert.transformer.layer_groups.26.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 248 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.dense_h2o.bias": "pytorch_model-00003-of-00004.bin",
|
| 249 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 250 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 251 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 252 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 253 |
+
"albert.transformer.layer_groups.26.layers.0.ffn.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 254 |
+
"albert.transformer.layer_groups.27.layers.0.attention.dense_out.bias": "pytorch_model-00003-of-00004.bin",
|
| 255 |
+
"albert.transformer.layer_groups.27.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 256 |
+
"albert.transformer.layer_groups.27.layers.0.attention.dense_qkv.bias": "pytorch_model-00003-of-00004.bin",
|
| 257 |
+
"albert.transformer.layer_groups.27.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00003-of-00004.bin",
|
| 258 |
+
"albert.transformer.layer_groups.27.layers.0.attention.layer_norm.bias": "pytorch_model-00003-of-00004.bin",
|
| 259 |
+
"albert.transformer.layer_groups.27.layers.0.attention.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
|
| 260 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.dense_h2o.bias": "pytorch_model-00004-of-00004.bin",
|
| 261 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 262 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.dense_i2h.bias": "pytorch_model-00003-of-00004.bin",
|
| 263 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 264 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 265 |
+
"albert.transformer.layer_groups.27.layers.0.ffn.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 266 |
+
"albert.transformer.layer_groups.28.layers.0.attention.dense_out.bias": "pytorch_model-00004-of-00004.bin",
|
| 267 |
+
"albert.transformer.layer_groups.28.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 268 |
+
"albert.transformer.layer_groups.28.layers.0.attention.dense_qkv.bias": "pytorch_model-00004-of-00004.bin",
|
| 269 |
+
"albert.transformer.layer_groups.28.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 270 |
+
"albert.transformer.layer_groups.28.layers.0.attention.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 271 |
+
"albert.transformer.layer_groups.28.layers.0.attention.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 272 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.dense_h2o.bias": "pytorch_model-00004-of-00004.bin",
|
| 273 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 274 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.dense_i2h.bias": "pytorch_model-00004-of-00004.bin",
|
| 275 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 276 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 277 |
+
"albert.transformer.layer_groups.28.layers.0.ffn.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 278 |
+
"albert.transformer.layer_groups.29.layers.0.attention.dense_out.bias": "pytorch_model-00004-of-00004.bin",
|
| 279 |
+
"albert.transformer.layer_groups.29.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 280 |
+
"albert.transformer.layer_groups.29.layers.0.attention.dense_qkv.bias": "pytorch_model-00004-of-00004.bin",
|
| 281 |
+
"albert.transformer.layer_groups.29.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 282 |
+
"albert.transformer.layer_groups.29.layers.0.attention.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 283 |
+
"albert.transformer.layer_groups.29.layers.0.attention.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 284 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.dense_h2o.bias": "pytorch_model-00004-of-00004.bin",
|
| 285 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 286 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.dense_i2h.bias": "pytorch_model-00004-of-00004.bin",
|
| 287 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 288 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 289 |
+
"albert.transformer.layer_groups.29.layers.0.ffn.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 290 |
+
"albert.transformer.layer_groups.3.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 291 |
+
"albert.transformer.layer_groups.3.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 292 |
+
"albert.transformer.layer_groups.3.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 293 |
+
"albert.transformer.layer_groups.3.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 294 |
+
"albert.transformer.layer_groups.3.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 295 |
+
"albert.transformer.layer_groups.3.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 296 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 297 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 298 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 299 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 300 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 301 |
+
"albert.transformer.layer_groups.3.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 302 |
+
"albert.transformer.layer_groups.30.layers.0.attention.dense_out.bias": "pytorch_model-00004-of-00004.bin",
|
| 303 |
+
"albert.transformer.layer_groups.30.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 304 |
+
"albert.transformer.layer_groups.30.layers.0.attention.dense_qkv.bias": "pytorch_model-00004-of-00004.bin",
|
| 305 |
+
"albert.transformer.layer_groups.30.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 306 |
+
"albert.transformer.layer_groups.30.layers.0.attention.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 307 |
+
"albert.transformer.layer_groups.30.layers.0.attention.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 308 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.dense_h2o.bias": "pytorch_model-00004-of-00004.bin",
|
| 309 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 310 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.dense_i2h.bias": "pytorch_model-00004-of-00004.bin",
|
| 311 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 312 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 313 |
+
"albert.transformer.layer_groups.30.layers.0.ffn.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 314 |
+
"albert.transformer.layer_groups.31.layers.0.attention.dense_out.bias": "pytorch_model-00004-of-00004.bin",
|
| 315 |
+
"albert.transformer.layer_groups.31.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 316 |
+
"albert.transformer.layer_groups.31.layers.0.attention.dense_qkv.bias": "pytorch_model-00004-of-00004.bin",
|
| 317 |
+
"albert.transformer.layer_groups.31.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 318 |
+
"albert.transformer.layer_groups.31.layers.0.attention.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 319 |
+
"albert.transformer.layer_groups.31.layers.0.attention.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 320 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.dense_h2o.bias": "pytorch_model-00004-of-00004.bin",
|
| 321 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 322 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.dense_i2h.bias": "pytorch_model-00004-of-00004.bin",
|
| 323 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00004-of-00004.bin",
|
| 324 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 325 |
+
"albert.transformer.layer_groups.31.layers.0.ffn.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 326 |
+
"albert.transformer.layer_groups.4.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 327 |
+
"albert.transformer.layer_groups.4.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 328 |
+
"albert.transformer.layer_groups.4.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 329 |
+
"albert.transformer.layer_groups.4.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 330 |
+
"albert.transformer.layer_groups.4.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 331 |
+
"albert.transformer.layer_groups.4.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 332 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 333 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 334 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 335 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 336 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 337 |
+
"albert.transformer.layer_groups.4.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 338 |
+
"albert.transformer.layer_groups.5.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 339 |
+
"albert.transformer.layer_groups.5.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 340 |
+
"albert.transformer.layer_groups.5.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 341 |
+
"albert.transformer.layer_groups.5.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 342 |
+
"albert.transformer.layer_groups.5.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 343 |
+
"albert.transformer.layer_groups.5.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 344 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 345 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 346 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 347 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 348 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 349 |
+
"albert.transformer.layer_groups.5.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 350 |
+
"albert.transformer.layer_groups.6.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 351 |
+
"albert.transformer.layer_groups.6.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 352 |
+
"albert.transformer.layer_groups.6.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 353 |
+
"albert.transformer.layer_groups.6.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 354 |
+
"albert.transformer.layer_groups.6.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 355 |
+
"albert.transformer.layer_groups.6.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 356 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 357 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 358 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 359 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 360 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 361 |
+
"albert.transformer.layer_groups.6.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 362 |
+
"albert.transformer.layer_groups.7.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 363 |
+
"albert.transformer.layer_groups.7.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 364 |
+
"albert.transformer.layer_groups.7.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 365 |
+
"albert.transformer.layer_groups.7.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 366 |
+
"albert.transformer.layer_groups.7.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 367 |
+
"albert.transformer.layer_groups.7.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 368 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 369 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 370 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 371 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 372 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 373 |
+
"albert.transformer.layer_groups.7.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 374 |
+
"albert.transformer.layer_groups.8.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 375 |
+
"albert.transformer.layer_groups.8.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 376 |
+
"albert.transformer.layer_groups.8.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 377 |
+
"albert.transformer.layer_groups.8.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 378 |
+
"albert.transformer.layer_groups.8.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 379 |
+
"albert.transformer.layer_groups.8.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 380 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.dense_h2o.bias": "pytorch_model-00001-of-00004.bin",
|
| 381 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 382 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 383 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 384 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 385 |
+
"albert.transformer.layer_groups.8.layers.0.ffn.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 386 |
+
"albert.transformer.layer_groups.9.layers.0.attention.dense_out.bias": "pytorch_model-00001-of-00004.bin",
|
| 387 |
+
"albert.transformer.layer_groups.9.layers.0.attention.dense_out.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 388 |
+
"albert.transformer.layer_groups.9.layers.0.attention.dense_qkv.bias": "pytorch_model-00001-of-00004.bin",
|
| 389 |
+
"albert.transformer.layer_groups.9.layers.0.attention.dense_qkv.shared_matrix.weight": "pytorch_model-00001-of-00004.bin",
|
| 390 |
+
"albert.transformer.layer_groups.9.layers.0.attention.layer_norm.bias": "pytorch_model-00001-of-00004.bin",
|
| 391 |
+
"albert.transformer.layer_groups.9.layers.0.attention.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
|
| 392 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.dense_h2o.bias": "pytorch_model-00002-of-00004.bin",
|
| 393 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.dense_h2o.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 394 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.dense_i2h.bias": "pytorch_model-00001-of-00004.bin",
|
| 395 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.dense_i2h.shared_matrix.weight": "pytorch_model-00002-of-00004.bin",
|
| 396 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.layer_norm.bias": "pytorch_model-00002-of-00004.bin",
|
| 397 |
+
"albert.transformer.layer_groups.9.layers.0.ffn.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
|
| 398 |
+
"albert.transformer.post_layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 399 |
+
"albert.transformer.post_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 400 |
+
"predictions.bias": "pytorch_model-00004-of-00004.bin",
|
| 401 |
+
"predictions.decoder.bias": "pytorch_model-00004-of-00004.bin",
|
| 402 |
+
"predictions.decoder.weight": "pytorch_model-00004-of-00004.bin",
|
| 403 |
+
"predictions.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 404 |
+
"predictions.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 405 |
+
"predictions.layer_norm.bias": "pytorch_model-00004-of-00004.bin",
|
| 406 |
+
"predictions.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 407 |
+
"sop_classifier.classifier.bias": "pytorch_model-00004-of-00004.bin",
|
| 408 |
+
"sop_classifier.classifier.weight": "pytorch_model-00004-of-00004.bin"
|
| 409 |
+
}
|
| 410 |
+
}
|