cong.fu
commited on
Commit
•
d6e771e
1
Parent(s):
3a4a3e6
Use bfloat16
Browse files- config.json +2 -2
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +367 -367
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path":
|
| 3 |
"apply_residual_connection_post_layernorm": false,
|
| 4 |
"architectures": [
|
| 5 |
"BloomForCausalLM"
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"skip_bias_add": true,
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
-
"torch_dtype": "
|
| 28 |
"transformers_version": "4.28.1",
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./",
|
| 3 |
"apply_residual_connection_post_layernorm": false,
|
| 4 |
"architectures": [
|
| 5 |
"BloomForCausalLM"
|
|
|
|
| 24 |
"skip_bias_add": true,
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
"transformers_version": "4.28.1",
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d01fae79bac015623296a8e8c17e238bb878ff334a4326a128898c470c00d24
|
| 3 |
+
size 9974654870
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637c6aa1f5e012a6c16919b6007bbb167055a2a3235ffc2b65d6512385b38ee4
|
| 3 |
+
size 6215469038
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,373 +1,373 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "pytorch_model-
|
| 7 |
-
"transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-
|
| 8 |
-
"transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-
|
| 9 |
-
"transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 10 |
-
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 11 |
-
"transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 12 |
-
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 13 |
-
"transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 14 |
-
"transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 15 |
-
"transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 16 |
-
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 17 |
-
"transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 18 |
-
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 19 |
-
"transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-
|
| 20 |
-
"transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-
|
| 21 |
-
"transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 22 |
-
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 23 |
-
"transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 24 |
-
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 25 |
-
"transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 26 |
-
"transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 27 |
-
"transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 28 |
-
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 29 |
-
"transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 30 |
-
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 31 |
-
"transformer.h.10.input_layernorm.bias": "pytorch_model-
|
| 32 |
-
"transformer.h.10.input_layernorm.weight": "pytorch_model-
|
| 33 |
-
"transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 34 |
-
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 35 |
-
"transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 36 |
-
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 37 |
-
"transformer.h.10.post_attention_layernorm.bias": "pytorch_model-
|
| 38 |
-
"transformer.h.10.post_attention_layernorm.weight": "pytorch_model-
|
| 39 |
-
"transformer.h.10.self_attention.dense.bias": "pytorch_model-
|
| 40 |
-
"transformer.h.10.self_attention.dense.weight": "pytorch_model-
|
| 41 |
-
"transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-
|
| 42 |
-
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-
|
| 43 |
-
"transformer.h.11.input_layernorm.bias": "pytorch_model-
|
| 44 |
-
"transformer.h.11.input_layernorm.weight": "pytorch_model-
|
| 45 |
-
"transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 46 |
-
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 47 |
-
"transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 48 |
-
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 49 |
-
"transformer.h.11.post_attention_layernorm.bias": "pytorch_model-
|
| 50 |
-
"transformer.h.11.post_attention_layernorm.weight": "pytorch_model-
|
| 51 |
-
"transformer.h.11.self_attention.dense.bias": "pytorch_model-
|
| 52 |
-
"transformer.h.11.self_attention.dense.weight": "pytorch_model-
|
| 53 |
-
"transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-
|
| 54 |
-
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-
|
| 55 |
-
"transformer.h.12.input_layernorm.bias": "pytorch_model-
|
| 56 |
-
"transformer.h.12.input_layernorm.weight": "pytorch_model-
|
| 57 |
-
"transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 58 |
-
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 59 |
-
"transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 60 |
-
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 61 |
-
"transformer.h.12.post_attention_layernorm.bias": "pytorch_model-
|
| 62 |
-
"transformer.h.12.post_attention_layernorm.weight": "pytorch_model-
|
| 63 |
-
"transformer.h.12.self_attention.dense.bias": "pytorch_model-
|
| 64 |
-
"transformer.h.12.self_attention.dense.weight": "pytorch_model-
|
| 65 |
-
"transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-
|
| 66 |
-
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-
|
| 67 |
-
"transformer.h.13.input_layernorm.bias": "pytorch_model-
|
| 68 |
-
"transformer.h.13.input_layernorm.weight": "pytorch_model-
|
| 69 |
-
"transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 70 |
-
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 71 |
-
"transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 72 |
-
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 73 |
-
"transformer.h.13.post_attention_layernorm.bias": "pytorch_model-
|
| 74 |
-
"transformer.h.13.post_attention_layernorm.weight": "pytorch_model-
|
| 75 |
-
"transformer.h.13.self_attention.dense.bias": "pytorch_model-
|
| 76 |
-
"transformer.h.13.self_attention.dense.weight": "pytorch_model-
|
| 77 |
-
"transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-
|
| 78 |
-
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-
|
| 79 |
-
"transformer.h.14.input_layernorm.bias": "pytorch_model-
|
| 80 |
-
"transformer.h.14.input_layernorm.weight": "pytorch_model-
|
| 81 |
-
"transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 82 |
-
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 83 |
-
"transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 84 |
-
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 85 |
-
"transformer.h.14.post_attention_layernorm.bias": "pytorch_model-
|
| 86 |
-
"transformer.h.14.post_attention_layernorm.weight": "pytorch_model-
|
| 87 |
-
"transformer.h.14.self_attention.dense.bias": "pytorch_model-
|
| 88 |
-
"transformer.h.14.self_attention.dense.weight": "pytorch_model-
|
| 89 |
-
"transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-
|
| 90 |
-
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-
|
| 91 |
-
"transformer.h.15.input_layernorm.bias": "pytorch_model-
|
| 92 |
-
"transformer.h.15.input_layernorm.weight": "pytorch_model-
|
| 93 |
-
"transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 94 |
-
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 95 |
-
"transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 96 |
-
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 97 |
-
"transformer.h.15.post_attention_layernorm.bias": "pytorch_model-
|
| 98 |
-
"transformer.h.15.post_attention_layernorm.weight": "pytorch_model-
|
| 99 |
-
"transformer.h.15.self_attention.dense.bias": "pytorch_model-
|
| 100 |
-
"transformer.h.15.self_attention.dense.weight": "pytorch_model-
|
| 101 |
-
"transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-
|
| 102 |
-
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-
|
| 103 |
-
"transformer.h.16.input_layernorm.bias": "pytorch_model-
|
| 104 |
-
"transformer.h.16.input_layernorm.weight": "pytorch_model-
|
| 105 |
-
"transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 106 |
-
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 107 |
-
"transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 108 |
-
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 109 |
-
"transformer.h.16.post_attention_layernorm.bias": "pytorch_model-
|
| 110 |
-
"transformer.h.16.post_attention_layernorm.weight": "pytorch_model-
|
| 111 |
-
"transformer.h.16.self_attention.dense.bias": "pytorch_model-
|
| 112 |
-
"transformer.h.16.self_attention.dense.weight": "pytorch_model-
|
| 113 |
-
"transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-
|
| 114 |
-
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-
|
| 115 |
-
"transformer.h.17.input_layernorm.bias": "pytorch_model-
|
| 116 |
-
"transformer.h.17.input_layernorm.weight": "pytorch_model-
|
| 117 |
-
"transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 118 |
-
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 119 |
-
"transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 120 |
-
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 121 |
-
"transformer.h.17.post_attention_layernorm.bias": "pytorch_model-
|
| 122 |
-
"transformer.h.17.post_attention_layernorm.weight": "pytorch_model-
|
| 123 |
-
"transformer.h.17.self_attention.dense.bias": "pytorch_model-
|
| 124 |
-
"transformer.h.17.self_attention.dense.weight": "pytorch_model-
|
| 125 |
-
"transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-
|
| 126 |
-
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-
|
| 127 |
-
"transformer.h.18.input_layernorm.bias": "pytorch_model-
|
| 128 |
-
"transformer.h.18.input_layernorm.weight": "pytorch_model-
|
| 129 |
-
"transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 130 |
-
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 131 |
-
"transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 132 |
-
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 133 |
-
"transformer.h.18.post_attention_layernorm.bias": "pytorch_model-
|
| 134 |
-
"transformer.h.18.post_attention_layernorm.weight": "pytorch_model-
|
| 135 |
-
"transformer.h.18.self_attention.dense.bias": "pytorch_model-
|
| 136 |
-
"transformer.h.18.self_attention.dense.weight": "pytorch_model-
|
| 137 |
-
"transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-
|
| 138 |
-
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-
|
| 139 |
-
"transformer.h.19.input_layernorm.bias": "pytorch_model-
|
| 140 |
-
"transformer.h.19.input_layernorm.weight": "pytorch_model-
|
| 141 |
-
"transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 142 |
-
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 143 |
-
"transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 144 |
-
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 145 |
-
"transformer.h.19.post_attention_layernorm.bias": "pytorch_model-
|
| 146 |
-
"transformer.h.19.post_attention_layernorm.weight": "pytorch_model-
|
| 147 |
-
"transformer.h.19.self_attention.dense.bias": "pytorch_model-
|
| 148 |
-
"transformer.h.19.self_attention.dense.weight": "pytorch_model-
|
| 149 |
-
"transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-
|
| 150 |
-
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-
|
| 151 |
-
"transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-
|
| 152 |
-
"transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-
|
| 153 |
-
"transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 154 |
-
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 155 |
-
"transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 156 |
-
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 157 |
-
"transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 158 |
-
"transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 159 |
-
"transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 160 |
-
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 161 |
-
"transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 162 |
-
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 163 |
-
"transformer.h.20.input_layernorm.bias": "pytorch_model-
|
| 164 |
-
"transformer.h.20.input_layernorm.weight": "pytorch_model-
|
| 165 |
-
"transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 166 |
-
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 167 |
-
"transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 168 |
-
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 169 |
-
"transformer.h.20.post_attention_layernorm.bias": "pytorch_model-
|
| 170 |
-
"transformer.h.20.post_attention_layernorm.weight": "pytorch_model-
|
| 171 |
-
"transformer.h.20.self_attention.dense.bias": "pytorch_model-
|
| 172 |
-
"transformer.h.20.self_attention.dense.weight": "pytorch_model-
|
| 173 |
-
"transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-
|
| 174 |
-
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-
|
| 175 |
-
"transformer.h.21.input_layernorm.bias": "pytorch_model-
|
| 176 |
-
"transformer.h.21.input_layernorm.weight": "pytorch_model-
|
| 177 |
-
"transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 178 |
-
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 179 |
-
"transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 180 |
-
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 181 |
-
"transformer.h.21.post_attention_layernorm.bias": "pytorch_model-
|
| 182 |
-
"transformer.h.21.post_attention_layernorm.weight": "pytorch_model-
|
| 183 |
-
"transformer.h.21.self_attention.dense.bias": "pytorch_model-
|
| 184 |
-
"transformer.h.21.self_attention.dense.weight": "pytorch_model-
|
| 185 |
-
"transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-
|
| 186 |
-
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-
|
| 187 |
-
"transformer.h.22.input_layernorm.bias": "pytorch_model-
|
| 188 |
-
"transformer.h.22.input_layernorm.weight": "pytorch_model-
|
| 189 |
-
"transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 190 |
-
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 191 |
-
"transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 192 |
-
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 193 |
-
"transformer.h.22.post_attention_layernorm.bias": "pytorch_model-
|
| 194 |
-
"transformer.h.22.post_attention_layernorm.weight": "pytorch_model-
|
| 195 |
-
"transformer.h.22.self_attention.dense.bias": "pytorch_model-
|
| 196 |
-
"transformer.h.22.self_attention.dense.weight": "pytorch_model-
|
| 197 |
-
"transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-
|
| 198 |
-
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-
|
| 199 |
-
"transformer.h.23.input_layernorm.bias": "pytorch_model-
|
| 200 |
-
"transformer.h.23.input_layernorm.weight": "pytorch_model-
|
| 201 |
-
"transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 202 |
-
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 203 |
-
"transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 204 |
-
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 205 |
-
"transformer.h.23.post_attention_layernorm.bias": "pytorch_model-
|
| 206 |
-
"transformer.h.23.post_attention_layernorm.weight": "pytorch_model-
|
| 207 |
-
"transformer.h.23.self_attention.dense.bias": "pytorch_model-
|
| 208 |
-
"transformer.h.23.self_attention.dense.weight": "pytorch_model-
|
| 209 |
-
"transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-
|
| 210 |
-
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-
|
| 211 |
-
"transformer.h.24.input_layernorm.bias": "pytorch_model-
|
| 212 |
-
"transformer.h.24.input_layernorm.weight": "pytorch_model-
|
| 213 |
-
"transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 214 |
-
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 215 |
-
"transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 216 |
-
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 217 |
-
"transformer.h.24.post_attention_layernorm.bias": "pytorch_model-
|
| 218 |
-
"transformer.h.24.post_attention_layernorm.weight": "pytorch_model-
|
| 219 |
-
"transformer.h.24.self_attention.dense.bias": "pytorch_model-
|
| 220 |
-
"transformer.h.24.self_attention.dense.weight": "pytorch_model-
|
| 221 |
-
"transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-
|
| 222 |
-
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-
|
| 223 |
-
"transformer.h.25.input_layernorm.bias": "pytorch_model-
|
| 224 |
-
"transformer.h.25.input_layernorm.weight": "pytorch_model-
|
| 225 |
-
"transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 226 |
-
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 227 |
-
"transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 228 |
-
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 229 |
-
"transformer.h.25.post_attention_layernorm.bias": "pytorch_model-
|
| 230 |
-
"transformer.h.25.post_attention_layernorm.weight": "pytorch_model-
|
| 231 |
-
"transformer.h.25.self_attention.dense.bias": "pytorch_model-
|
| 232 |
-
"transformer.h.25.self_attention.dense.weight": "pytorch_model-
|
| 233 |
-
"transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-
|
| 234 |
-
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-
|
| 235 |
-
"transformer.h.26.input_layernorm.bias": "pytorch_model-
|
| 236 |
-
"transformer.h.26.input_layernorm.weight": "pytorch_model-
|
| 237 |
-
"transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 238 |
-
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 239 |
-
"transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 240 |
-
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 241 |
-
"transformer.h.26.post_attention_layernorm.bias": "pytorch_model-
|
| 242 |
-
"transformer.h.26.post_attention_layernorm.weight": "pytorch_model-
|
| 243 |
-
"transformer.h.26.self_attention.dense.bias": "pytorch_model-
|
| 244 |
-
"transformer.h.26.self_attention.dense.weight": "pytorch_model-
|
| 245 |
-
"transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-
|
| 246 |
-
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-
|
| 247 |
-
"transformer.h.27.input_layernorm.bias": "pytorch_model-
|
| 248 |
-
"transformer.h.27.input_layernorm.weight": "pytorch_model-
|
| 249 |
-
"transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 250 |
-
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 251 |
-
"transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 252 |
-
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 253 |
-
"transformer.h.27.post_attention_layernorm.bias": "pytorch_model-
|
| 254 |
-
"transformer.h.27.post_attention_layernorm.weight": "pytorch_model-
|
| 255 |
-
"transformer.h.27.self_attention.dense.bias": "pytorch_model-
|
| 256 |
-
"transformer.h.27.self_attention.dense.weight": "pytorch_model-
|
| 257 |
-
"transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-
|
| 258 |
-
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-
|
| 259 |
-
"transformer.h.28.input_layernorm.bias": "pytorch_model-
|
| 260 |
-
"transformer.h.28.input_layernorm.weight": "pytorch_model-
|
| 261 |
-
"transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 262 |
-
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 263 |
-
"transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 264 |
-
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 265 |
-
"transformer.h.28.post_attention_layernorm.bias": "pytorch_model-
|
| 266 |
-
"transformer.h.28.post_attention_layernorm.weight": "pytorch_model-
|
| 267 |
-
"transformer.h.28.self_attention.dense.bias": "pytorch_model-
|
| 268 |
-
"transformer.h.28.self_attention.dense.weight": "pytorch_model-
|
| 269 |
-
"transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-
|
| 270 |
-
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-
|
| 271 |
-
"transformer.h.29.input_layernorm.bias": "pytorch_model-
|
| 272 |
-
"transformer.h.29.input_layernorm.weight": "pytorch_model-
|
| 273 |
-
"transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 274 |
-
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 275 |
-
"transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 276 |
-
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 277 |
-
"transformer.h.29.post_attention_layernorm.bias": "pytorch_model-
|
| 278 |
-
"transformer.h.29.post_attention_layernorm.weight": "pytorch_model-
|
| 279 |
-
"transformer.h.29.self_attention.dense.bias": "pytorch_model-
|
| 280 |
-
"transformer.h.29.self_attention.dense.weight": "pytorch_model-
|
| 281 |
-
"transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-
|
| 282 |
-
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-
|
| 283 |
-
"transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-
|
| 284 |
-
"transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-
|
| 285 |
-
"transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 286 |
-
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 287 |
-
"transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 288 |
-
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 289 |
-
"transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 290 |
-
"transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 291 |
-
"transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 292 |
-
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 293 |
-
"transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 294 |
-
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 295 |
-
"transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-
|
| 296 |
-
"transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-
|
| 297 |
-
"transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 298 |
-
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 299 |
-
"transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 300 |
-
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 301 |
-
"transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 302 |
-
"transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 303 |
-
"transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 304 |
-
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 305 |
-
"transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 306 |
-
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 307 |
-
"transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-
|
| 308 |
-
"transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-
|
| 309 |
-
"transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 310 |
-
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 311 |
-
"transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 312 |
-
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 313 |
-
"transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 314 |
-
"transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 315 |
-
"transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 316 |
-
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 317 |
-
"transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 318 |
-
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 319 |
-
"transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-
|
| 320 |
-
"transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-
|
| 321 |
-
"transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-
|
| 322 |
-
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
| 323 |
-
"transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-
|
| 324 |
-
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
| 325 |
-
"transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-
|
| 326 |
-
"transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 327 |
-
"transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-
|
| 328 |
-
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-
|
| 329 |
-
"transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 330 |
-
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 331 |
-
"transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-
|
| 332 |
-
"transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-
|
| 333 |
-
"transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 334 |
-
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 335 |
-
"transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 336 |
-
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 337 |
-
"transformer.h.7.post_attention_layernorm.bias": "pytorch_model-
|
| 338 |
-
"transformer.h.7.post_attention_layernorm.weight": "pytorch_model-
|
| 339 |
-
"transformer.h.7.self_attention.dense.bias": "pytorch_model-
|
| 340 |
-
"transformer.h.7.self_attention.dense.weight": "pytorch_model-
|
| 341 |
-
"transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-
|
| 342 |
-
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
| 343 |
-
"transformer.h.8.input_layernorm.bias": "pytorch_model-
|
| 344 |
-
"transformer.h.8.input_layernorm.weight": "pytorch_model-
|
| 345 |
-
"transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 346 |
-
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 347 |
-
"transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 348 |
-
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 349 |
-
"transformer.h.8.post_attention_layernorm.bias": "pytorch_model-
|
| 350 |
-
"transformer.h.8.post_attention_layernorm.weight": "pytorch_model-
|
| 351 |
-
"transformer.h.8.self_attention.dense.bias": "pytorch_model-
|
| 352 |
-
"transformer.h.8.self_attention.dense.weight": "pytorch_model-
|
| 353 |
-
"transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-
|
| 354 |
-
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-
|
| 355 |
-
"transformer.h.9.input_layernorm.bias": "pytorch_model-
|
| 356 |
-
"transformer.h.9.input_layernorm.weight": "pytorch_model-
|
| 357 |
-
"transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-
|
| 358 |
-
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-
|
| 359 |
-
"transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-
|
| 360 |
-
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-
|
| 361 |
-
"transformer.h.9.post_attention_layernorm.bias": "pytorch_model-
|
| 362 |
-
"transformer.h.9.post_attention_layernorm.weight": "pytorch_model-
|
| 363 |
-
"transformer.h.9.self_attention.dense.bias": "pytorch_model-
|
| 364 |
-
"transformer.h.9.self_attention.dense.weight": "pytorch_model-
|
| 365 |
-
"transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-
|
| 366 |
-
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-
|
| 367 |
-
"transformer.ln_f.bias": "pytorch_model-
|
| 368 |
-
"transformer.ln_f.weight": "pytorch_model-
|
| 369 |
-
"transformer.word_embeddings.weight": "pytorch_model-00001-of-
|
| 370 |
-
"transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-
|
| 371 |
-
"transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-
|
| 372 |
}
|
| 373 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 16189997056
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
| 7 |
+
"transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 88 |
+
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 89 |
+
"transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 92 |
+
"transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 93 |
+
"transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 94 |
+
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 101 |
+
"transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 102 |
+
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 103 |
+
"transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 104 |
+
"transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 105 |
+
"transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 106 |
+
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 107 |
+
"transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 108 |
+
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 109 |
+
"transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 110 |
+
"transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 111 |
+
"transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 112 |
+
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 113 |
+
"transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 114 |
+
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 115 |
+
"transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 123 |
+
"transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 124 |
+
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 125 |
+
"transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 126 |
+
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 127 |
+
"transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 128 |
+
"transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 129 |
+
"transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 130 |
+
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 131 |
+
"transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 132 |
+
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 133 |
+
"transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 134 |
+
"transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 135 |
+
"transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 136 |
+
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 137 |
+
"transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 138 |
+
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 139 |
+
"transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 140 |
+
"transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 141 |
+
"transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 142 |
+
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 143 |
+
"transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 144 |
+
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 145 |
+
"transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 146 |
+
"transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 147 |
+
"transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 148 |
+
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 149 |
+
"transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 150 |
+
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
+
"transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 154 |
+
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
+
"transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
+
"transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 158 |
+
"transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
+
"transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 160 |
+
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 162 |
+
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 163 |
+
"transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 166 |
+
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 167 |
+
"transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 168 |
+
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 169 |
+
"transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 170 |
+
"transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 171 |
+
"transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 172 |
+
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 173 |
+
"transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 174 |
+
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 175 |
+
"transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 176 |
+
"transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 177 |
+
"transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 178 |
+
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 216 |
+
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 217 |
+
"transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 218 |
+
"transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 219 |
+
"transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 220 |
+
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 221 |
+
"transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 222 |
+
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 223 |
+
"transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 224 |
+
"transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 243 |
+
"transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 244 |
+
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 245 |
+
"transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 246 |
+
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 247 |
+
"transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 248 |
+
"transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 249 |
+
"transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 250 |
+
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 251 |
+
"transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 252 |
+
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 253 |
+
"transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 254 |
+
"transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 255 |
+
"transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 256 |
+
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 257 |
+
"transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 258 |
+
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 259 |
+
"transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 260 |
+
"transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 261 |
+
"transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 262 |
+
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 263 |
+
"transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 264 |
+
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 265 |
+
"transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 266 |
+
"transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 267 |
+
"transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 268 |
+
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 269 |
+
"transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 270 |
+
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 271 |
+
"transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 272 |
+
"transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 273 |
+
"transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
| 274 |
+
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
| 275 |
+
"transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
| 276 |
+
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
| 277 |
+
"transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
| 278 |
+
"transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 279 |
+
"transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
| 280 |
+
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
| 281 |
+
"transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
| 282 |
+
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
| 283 |
+
"transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 284 |
+
"transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 285 |
+
"transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 286 |
+
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 287 |
+
"transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 288 |
+
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 289 |
+
"transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 290 |
+
"transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 291 |
+
"transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 292 |
+
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 293 |
+
"transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 294 |
+
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 295 |
+
"transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 296 |
+
"transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 297 |
+
"transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 298 |
+
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 299 |
+
"transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 300 |
+
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 301 |
+
"transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 302 |
+
"transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 303 |
+
"transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 304 |
+
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 305 |
+
"transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 306 |
+
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 307 |
+
"transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 308 |
+
"transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 322 |
+
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 323 |
+
"transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 324 |
+
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 325 |
+
"transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 326 |
+
"transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 327 |
+
"transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 328 |
+
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 329 |
+
"transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 330 |
+
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 331 |
+
"transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 332 |
+
"transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 333 |
+
"transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 334 |
+
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 335 |
+
"transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 336 |
+
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 337 |
+
"transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 338 |
+
"transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 339 |
+
"transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 340 |
+
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 341 |
+
"transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 342 |
+
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 343 |
+
"transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 344 |
+
"transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 345 |
+
"transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 346 |
+
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 347 |
+
"transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 348 |
+
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 349 |
+
"transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 350 |
+
"transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 351 |
+
"transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 352 |
+
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 353 |
+
"transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 354 |
+
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 355 |
+
"transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 356 |
+
"transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 357 |
+
"transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
| 358 |
+
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
| 359 |
+
"transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
| 360 |
+
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
| 361 |
+
"transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 362 |
+
"transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 363 |
+
"transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
| 364 |
+
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
| 365 |
+
"transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
| 366 |
+
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
| 367 |
+
"transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
|
| 368 |
+
"transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
|
| 369 |
+
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
|
| 370 |
+
"transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 371 |
+
"transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
|
| 372 |
}
|
| 373 |
}
|