Upload folder using huggingface_hub
Browse files- config.json +2 -2
- generation_config.json +1 -1
- pytorch_model-00001-of-00009.bin +3 -0
- pytorch_model-00002-of-00009.bin +3 -0
- pytorch_model-00003-of-00009.bin +3 -0
- pytorch_model-00004-of-00009.bin +3 -0
- pytorch_model-00005-of-00009.bin +3 -0
- pytorch_model-00006-of-00009.bin +3 -0
- pytorch_model-00007-of-00009.bin +3 -0
- pytorch_model-00008-of-00009.bin +3 -0
- pytorch_model-00009-of-00009.bin +3 -0
- pytorch_model.bin.index.json +485 -485
config.json
CHANGED
@@ -22,8 +22,8 @@
|
|
22 |
"n_head_kv": 8,
|
23 |
"n_layer": 60,
|
24 |
"parallel_attn": true,
|
25 |
-
"torch_dtype": "
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 65025
|
29 |
}
|
|
|
22 |
"n_head_kv": 8,
|
23 |
"n_layer": 60,
|
24 |
"parallel_attn": true,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.28.1",
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 65025
|
29 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
}
|
pytorch_model-00001-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97cade97d491c63b4ca25ea42643a1f82eebb4449de557d00ee16fa2998813e
|
3 |
+
size 9504786525
|
pytorch_model-00002-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a62a1a4e93feac55014272c1bfc6dcc845fbe3f3241745f69fdda0b458ed91
|
3 |
+
size 9513159151
|
pytorch_model-00003-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:249f63046b72a2469ecc5678752e2bff5b8a0d43f559f90778b545f364c27d9b
|
3 |
+
size 9513159151
|
pytorch_model-00004-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fda8200f0b5c1358f1461d31402e535783d418cfa221d92451ec8b3f51c769c
|
3 |
+
size 9513159151
|
pytorch_model-00005-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:741baf6c6473f8254c24979c86b3dfd7eca78d44616e2be5745269fd13f84def
|
3 |
+
size 9513159151
|
pytorch_model-00006-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1897444e5dc96776f98393fa608f3641d1386b20ad4910354e53e7406ad7cb9
|
3 |
+
size 9513159151
|
pytorch_model-00007-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c22e7bd5c9669c800e0f28866e7a16679b4b5a3024da51bd660c81e9a1809a25
|
3 |
+
size 9513159151
|
pytorch_model-00008-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a77d8b0d29c0d7b86adc64a624dd51ba873338e2c1ec77521461ff601315c15
|
3 |
+
size 9513159151
|
pytorch_model-00009-of-00009.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd228eaed363e85a0134f29147a579a4336b0572955e3c673ae4bef7196d81d2
|
3 |
+
size 7575236661
|
pytorch_model.bin.index.json
CHANGED
@@ -1,491 +1,491 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"lm_head.weight": "pytorch_model-
|
7 |
-
"transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-
|
8 |
-
"transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-
|
9 |
-
"transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-
|
10 |
-
"transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-
|
11 |
-
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
12 |
-
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
13 |
-
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-
|
14 |
-
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
15 |
-
"transformer.h.1.ln_attn.bias": "pytorch_model-00001-of-
|
16 |
-
"transformer.h.1.ln_attn.weight": "pytorch_model-00001-of-
|
17 |
-
"transformer.h.1.ln_mlp.bias": "pytorch_model-00001-of-
|
18 |
-
"transformer.h.1.ln_mlp.weight": "pytorch_model-00001-of-
|
19 |
-
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-
|
20 |
-
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
21 |
-
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-
|
22 |
-
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
23 |
-
"transformer.h.10.ln_attn.bias": "pytorch_model-
|
24 |
-
"transformer.h.10.ln_attn.weight": "pytorch_model-
|
25 |
-
"transformer.h.10.ln_mlp.bias": "pytorch_model-
|
26 |
-
"transformer.h.10.ln_mlp.weight": "pytorch_model-
|
27 |
-
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-
|
28 |
-
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-
|
29 |
-
"transformer.h.10.self_attention.dense.weight": "pytorch_model-
|
30 |
-
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-
|
31 |
-
"transformer.h.11.ln_attn.bias": "pytorch_model-
|
32 |
-
"transformer.h.11.ln_attn.weight": "pytorch_model-
|
33 |
-
"transformer.h.11.ln_mlp.bias": "pytorch_model-
|
34 |
-
"transformer.h.11.ln_mlp.weight": "pytorch_model-
|
35 |
-
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-
|
36 |
-
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-
|
37 |
-
"transformer.h.11.self_attention.dense.weight": "pytorch_model-
|
38 |
-
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-
|
39 |
-
"transformer.h.12.ln_attn.bias": "pytorch_model-
|
40 |
-
"transformer.h.12.ln_attn.weight": "pytorch_model-
|
41 |
-
"transformer.h.12.ln_mlp.bias": "pytorch_model-
|
42 |
-
"transformer.h.12.ln_mlp.weight": "pytorch_model-
|
43 |
-
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-
|
44 |
-
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-
|
45 |
-
"transformer.h.12.self_attention.dense.weight": "pytorch_model-
|
46 |
-
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-
|
47 |
-
"transformer.h.13.ln_attn.bias": "pytorch_model-
|
48 |
-
"transformer.h.13.ln_attn.weight": "pytorch_model-
|
49 |
-
"transformer.h.13.ln_mlp.bias": "pytorch_model-
|
50 |
-
"transformer.h.13.ln_mlp.weight": "pytorch_model-
|
51 |
-
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-
|
52 |
-
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-
|
53 |
-
"transformer.h.13.self_attention.dense.weight": "pytorch_model-
|
54 |
-
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-
|
55 |
-
"transformer.h.14.ln_attn.bias": "pytorch_model-
|
56 |
-
"transformer.h.14.ln_attn.weight": "pytorch_model-
|
57 |
-
"transformer.h.14.ln_mlp.bias": "pytorch_model-
|
58 |
-
"transformer.h.14.ln_mlp.weight": "pytorch_model-
|
59 |
-
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-
|
60 |
-
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-
|
61 |
-
"transformer.h.14.self_attention.dense.weight": "pytorch_model-
|
62 |
-
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-
|
63 |
-
"transformer.h.15.ln_attn.bias": "pytorch_model-
|
64 |
-
"transformer.h.15.ln_attn.weight": "pytorch_model-
|
65 |
-
"transformer.h.15.ln_mlp.bias": "pytorch_model-
|
66 |
-
"transformer.h.15.ln_mlp.weight": "pytorch_model-
|
67 |
-
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-
|
68 |
-
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-
|
69 |
-
"transformer.h.15.self_attention.dense.weight": "pytorch_model-
|
70 |
-
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-
|
71 |
-
"transformer.h.16.ln_attn.bias": "pytorch_model-
|
72 |
-
"transformer.h.16.ln_attn.weight": "pytorch_model-
|
73 |
-
"transformer.h.16.ln_mlp.bias": "pytorch_model-
|
74 |
-
"transformer.h.16.ln_mlp.weight": "pytorch_model-
|
75 |
-
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-
|
76 |
-
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-
|
77 |
-
"transformer.h.16.self_attention.dense.weight": "pytorch_model-
|
78 |
-
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-
|
79 |
-
"transformer.h.17.ln_attn.bias": "pytorch_model-
|
80 |
-
"transformer.h.17.ln_attn.weight": "pytorch_model-
|
81 |
-
"transformer.h.17.ln_mlp.bias": "pytorch_model-
|
82 |
-
"transformer.h.17.ln_mlp.weight": "pytorch_model-
|
83 |
-
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-
|
84 |
-
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-
|
85 |
-
"transformer.h.17.self_attention.dense.weight": "pytorch_model-
|
86 |
-
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-
|
87 |
-
"transformer.h.18.ln_attn.bias": "pytorch_model-
|
88 |
-
"transformer.h.18.ln_attn.weight": "pytorch_model-
|
89 |
-
"transformer.h.18.ln_mlp.bias": "pytorch_model-
|
90 |
-
"transformer.h.18.ln_mlp.weight": "pytorch_model-
|
91 |
-
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-
|
92 |
-
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-
|
93 |
-
"transformer.h.18.self_attention.dense.weight": "pytorch_model-
|
94 |
-
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-
|
95 |
-
"transformer.h.19.ln_attn.bias": "pytorch_model-
|
96 |
-
"transformer.h.19.ln_attn.weight": "pytorch_model-
|
97 |
-
"transformer.h.19.ln_mlp.bias": "pytorch_model-
|
98 |
-
"transformer.h.19.ln_mlp.weight": "pytorch_model-
|
99 |
-
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-
|
100 |
-
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-
|
101 |
-
"transformer.h.19.self_attention.dense.weight": "pytorch_model-
|
102 |
-
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-
|
103 |
-
"transformer.h.2.ln_attn.bias": "pytorch_model-00001-of-
|
104 |
-
"transformer.h.2.ln_attn.weight": "pytorch_model-00001-of-
|
105 |
-
"transformer.h.2.ln_mlp.bias": "pytorch_model-00001-of-
|
106 |
-
"transformer.h.2.ln_mlp.weight": "pytorch_model-00001-of-
|
107 |
-
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-
|
108 |
-
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-
|
109 |
-
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-
|
110 |
-
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-
|
111 |
-
"transformer.h.20.ln_attn.bias": "pytorch_model-
|
112 |
-
"transformer.h.20.ln_attn.weight": "pytorch_model-
|
113 |
-
"transformer.h.20.ln_mlp.bias": "pytorch_model-
|
114 |
-
"transformer.h.20.ln_mlp.weight": "pytorch_model-
|
115 |
-
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-
|
116 |
-
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-
|
117 |
-
"transformer.h.20.self_attention.dense.weight": "pytorch_model-
|
118 |
-
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-
|
119 |
-
"transformer.h.21.ln_attn.bias": "pytorch_model-
|
120 |
-
"transformer.h.21.ln_attn.weight": "pytorch_model-
|
121 |
-
"transformer.h.21.ln_mlp.bias": "pytorch_model-
|
122 |
-
"transformer.h.21.ln_mlp.weight": "pytorch_model-
|
123 |
-
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-
|
124 |
-
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-
|
125 |
-
"transformer.h.21.self_attention.dense.weight": "pytorch_model-
|
126 |
-
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-
|
127 |
-
"transformer.h.22.ln_attn.bias": "pytorch_model-
|
128 |
-
"transformer.h.22.ln_attn.weight": "pytorch_model-
|
129 |
-
"transformer.h.22.ln_mlp.bias": "pytorch_model-
|
130 |
-
"transformer.h.22.ln_mlp.weight": "pytorch_model-
|
131 |
-
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-
|
132 |
-
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-
|
133 |
-
"transformer.h.22.self_attention.dense.weight": "pytorch_model-
|
134 |
-
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-
|
135 |
-
"transformer.h.23.ln_attn.bias": "pytorch_model-
|
136 |
-
"transformer.h.23.ln_attn.weight": "pytorch_model-
|
137 |
-
"transformer.h.23.ln_mlp.bias": "pytorch_model-
|
138 |
-
"transformer.h.23.ln_mlp.weight": "pytorch_model-
|
139 |
-
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-
|
140 |
-
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-
|
141 |
-
"transformer.h.23.self_attention.dense.weight": "pytorch_model-
|
142 |
-
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-
|
143 |
-
"transformer.h.24.ln_attn.bias": "pytorch_model-
|
144 |
-
"transformer.h.24.ln_attn.weight": "pytorch_model-
|
145 |
-
"transformer.h.24.ln_mlp.bias": "pytorch_model-
|
146 |
-
"transformer.h.24.ln_mlp.weight": "pytorch_model-
|
147 |
-
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-
|
148 |
-
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-
|
149 |
-
"transformer.h.24.self_attention.dense.weight": "pytorch_model-
|
150 |
-
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-
|
151 |
-
"transformer.h.25.ln_attn.bias": "pytorch_model-
|
152 |
-
"transformer.h.25.ln_attn.weight": "pytorch_model-
|
153 |
-
"transformer.h.25.ln_mlp.bias": "pytorch_model-
|
154 |
-
"transformer.h.25.ln_mlp.weight": "pytorch_model-
|
155 |
-
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-
|
156 |
-
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-
|
157 |
-
"transformer.h.25.self_attention.dense.weight": "pytorch_model-
|
158 |
-
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-
|
159 |
-
"transformer.h.26.ln_attn.bias": "pytorch_model-
|
160 |
-
"transformer.h.26.ln_attn.weight": "pytorch_model-
|
161 |
-
"transformer.h.26.ln_mlp.bias": "pytorch_model-
|
162 |
-
"transformer.h.26.ln_mlp.weight": "pytorch_model-
|
163 |
-
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-
|
164 |
-
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-
|
165 |
-
"transformer.h.26.self_attention.dense.weight": "pytorch_model-
|
166 |
-
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-
|
167 |
-
"transformer.h.27.ln_attn.bias": "pytorch_model-
|
168 |
-
"transformer.h.27.ln_attn.weight": "pytorch_model-
|
169 |
-
"transformer.h.27.ln_mlp.bias": "pytorch_model-
|
170 |
-
"transformer.h.27.ln_mlp.weight": "pytorch_model-
|
171 |
-
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-
|
172 |
-
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-
|
173 |
-
"transformer.h.27.self_attention.dense.weight": "pytorch_model-
|
174 |
-
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-
|
175 |
-
"transformer.h.28.ln_attn.bias": "pytorch_model-
|
176 |
-
"transformer.h.28.ln_attn.weight": "pytorch_model-
|
177 |
-
"transformer.h.28.ln_mlp.bias": "pytorch_model-
|
178 |
-
"transformer.h.28.ln_mlp.weight": "pytorch_model-
|
179 |
-
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-
|
180 |
-
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-
|
181 |
-
"transformer.h.28.self_attention.dense.weight": "pytorch_model-
|
182 |
-
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-
|
183 |
-
"transformer.h.29.ln_attn.bias": "pytorch_model-
|
184 |
-
"transformer.h.29.ln_attn.weight": "pytorch_model-
|
185 |
-
"transformer.h.29.ln_mlp.bias": "pytorch_model-
|
186 |
-
"transformer.h.29.ln_mlp.weight": "pytorch_model-
|
187 |
-
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-
|
188 |
-
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-
|
189 |
-
"transformer.h.29.self_attention.dense.weight": "pytorch_model-
|
190 |
-
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-
|
191 |
-
"transformer.h.3.ln_attn.bias": "pytorch_model-
|
192 |
-
"transformer.h.3.ln_attn.weight": "pytorch_model-
|
193 |
-
"transformer.h.3.ln_mlp.bias": "pytorch_model-
|
194 |
-
"transformer.h.3.ln_mlp.weight": "pytorch_model-
|
195 |
-
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-
|
196 |
-
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-
|
197 |
-
"transformer.h.3.self_attention.dense.weight": "pytorch_model-
|
198 |
-
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-
|
199 |
-
"transformer.h.30.ln_attn.bias": "pytorch_model-
|
200 |
-
"transformer.h.30.ln_attn.weight": "pytorch_model-
|
201 |
-
"transformer.h.30.ln_mlp.bias": "pytorch_model-
|
202 |
-
"transformer.h.30.ln_mlp.weight": "pytorch_model-
|
203 |
-
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-
|
204 |
-
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-
|
205 |
-
"transformer.h.30.self_attention.dense.weight": "pytorch_model-
|
206 |
-
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-
|
207 |
-
"transformer.h.31.ln_attn.bias": "pytorch_model-
|
208 |
-
"transformer.h.31.ln_attn.weight": "pytorch_model-
|
209 |
-
"transformer.h.31.ln_mlp.bias": "pytorch_model-
|
210 |
-
"transformer.h.31.ln_mlp.weight": "pytorch_model-
|
211 |
-
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-
|
212 |
-
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-
|
213 |
-
"transformer.h.31.self_attention.dense.weight": "pytorch_model-
|
214 |
-
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-
|
215 |
-
"transformer.h.32.ln_attn.bias": "pytorch_model-
|
216 |
-
"transformer.h.32.ln_attn.weight": "pytorch_model-
|
217 |
-
"transformer.h.32.ln_mlp.bias": "pytorch_model-
|
218 |
-
"transformer.h.32.ln_mlp.weight": "pytorch_model-
|
219 |
-
"transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-
|
220 |
-
"transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-
|
221 |
-
"transformer.h.32.self_attention.dense.weight": "pytorch_model-
|
222 |
-
"transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-
|
223 |
-
"transformer.h.33.ln_attn.bias": "pytorch_model-
|
224 |
-
"transformer.h.33.ln_attn.weight": "pytorch_model-
|
225 |
-
"transformer.h.33.ln_mlp.bias": "pytorch_model-
|
226 |
-
"transformer.h.33.ln_mlp.weight": "pytorch_model-
|
227 |
-
"transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-
|
228 |
-
"transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-
|
229 |
-
"transformer.h.33.self_attention.dense.weight": "pytorch_model-
|
230 |
-
"transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-
|
231 |
-
"transformer.h.34.ln_attn.bias": "pytorch_model-
|
232 |
-
"transformer.h.34.ln_attn.weight": "pytorch_model-
|
233 |
-
"transformer.h.34.ln_mlp.bias": "pytorch_model-
|
234 |
-
"transformer.h.34.ln_mlp.weight": "pytorch_model-
|
235 |
-
"transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-
|
236 |
-
"transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-
|
237 |
-
"transformer.h.34.self_attention.dense.weight": "pytorch_model-
|
238 |
-
"transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-
|
239 |
-
"transformer.h.35.ln_attn.bias": "pytorch_model-
|
240 |
-
"transformer.h.35.ln_attn.weight": "pytorch_model-
|
241 |
-
"transformer.h.35.ln_mlp.bias": "pytorch_model-
|
242 |
-
"transformer.h.35.ln_mlp.weight": "pytorch_model-
|
243 |
-
"transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-
|
244 |
-
"transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-
|
245 |
-
"transformer.h.35.self_attention.dense.weight": "pytorch_model-
|
246 |
-
"transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-
|
247 |
-
"transformer.h.36.ln_attn.bias": "pytorch_model-
|
248 |
-
"transformer.h.36.ln_attn.weight": "pytorch_model-
|
249 |
-
"transformer.h.36.ln_mlp.bias": "pytorch_model-
|
250 |
-
"transformer.h.36.ln_mlp.weight": "pytorch_model-
|
251 |
-
"transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-
|
252 |
-
"transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-
|
253 |
-
"transformer.h.36.self_attention.dense.weight": "pytorch_model-
|
254 |
-
"transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-
|
255 |
-
"transformer.h.37.ln_attn.bias": "pytorch_model-
|
256 |
-
"transformer.h.37.ln_attn.weight": "pytorch_model-
|
257 |
-
"transformer.h.37.ln_mlp.bias": "pytorch_model-
|
258 |
-
"transformer.h.37.ln_mlp.weight": "pytorch_model-
|
259 |
-
"transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-
|
260 |
-
"transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-
|
261 |
-
"transformer.h.37.self_attention.dense.weight": "pytorch_model-
|
262 |
-
"transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-
|
263 |
-
"transformer.h.38.ln_attn.bias": "pytorch_model-
|
264 |
-
"transformer.h.38.ln_attn.weight": "pytorch_model-
|
265 |
-
"transformer.h.38.ln_mlp.bias": "pytorch_model-
|
266 |
-
"transformer.h.38.ln_mlp.weight": "pytorch_model-
|
267 |
-
"transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-
|
268 |
-
"transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-
|
269 |
-
"transformer.h.38.self_attention.dense.weight": "pytorch_model-
|
270 |
-
"transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-
|
271 |
-
"transformer.h.39.ln_attn.bias": "pytorch_model-
|
272 |
-
"transformer.h.39.ln_attn.weight": "pytorch_model-
|
273 |
-
"transformer.h.39.ln_mlp.bias": "pytorch_model-
|
274 |
-
"transformer.h.39.ln_mlp.weight": "pytorch_model-
|
275 |
-
"transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-
|
276 |
-
"transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-
|
277 |
-
"transformer.h.39.self_attention.dense.weight": "pytorch_model-
|
278 |
-
"transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-
|
279 |
-
"transformer.h.4.ln_attn.bias": "pytorch_model-
|
280 |
-
"transformer.h.4.ln_attn.weight": "pytorch_model-
|
281 |
-
"transformer.h.4.ln_mlp.bias": "pytorch_model-
|
282 |
-
"transformer.h.4.ln_mlp.weight": "pytorch_model-
|
283 |
-
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-
|
284 |
-
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-
|
285 |
-
"transformer.h.4.self_attention.dense.weight": "pytorch_model-
|
286 |
-
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-
|
287 |
-
"transformer.h.40.ln_attn.bias": "pytorch_model-
|
288 |
-
"transformer.h.40.ln_attn.weight": "pytorch_model-
|
289 |
-
"transformer.h.40.ln_mlp.bias": "pytorch_model-
|
290 |
-
"transformer.h.40.ln_mlp.weight": "pytorch_model-
|
291 |
-
"transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-
|
292 |
-
"transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-
|
293 |
-
"transformer.h.40.self_attention.dense.weight": "pytorch_model-
|
294 |
-
"transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-
|
295 |
-
"transformer.h.41.ln_attn.bias": "pytorch_model-
|
296 |
-
"transformer.h.41.ln_attn.weight": "pytorch_model-
|
297 |
-
"transformer.h.41.ln_mlp.bias": "pytorch_model-
|
298 |
-
"transformer.h.41.ln_mlp.weight": "pytorch_model-
|
299 |
-
"transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-
|
300 |
-
"transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-
|
301 |
-
"transformer.h.41.self_attention.dense.weight": "pytorch_model-
|
302 |
-
"transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-
|
303 |
-
"transformer.h.42.ln_attn.bias": "pytorch_model-
|
304 |
-
"transformer.h.42.ln_attn.weight": "pytorch_model-
|
305 |
-
"transformer.h.42.ln_mlp.bias": "pytorch_model-
|
306 |
-
"transformer.h.42.ln_mlp.weight": "pytorch_model-
|
307 |
-
"transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-
|
308 |
-
"transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-
|
309 |
-
"transformer.h.42.self_attention.dense.weight": "pytorch_model-
|
310 |
-
"transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-
|
311 |
-
"transformer.h.43.ln_attn.bias": "pytorch_model-
|
312 |
-
"transformer.h.43.ln_attn.weight": "pytorch_model-
|
313 |
-
"transformer.h.43.ln_mlp.bias": "pytorch_model-
|
314 |
-
"transformer.h.43.ln_mlp.weight": "pytorch_model-
|
315 |
-
"transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-
|
316 |
-
"transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-
|
317 |
-
"transformer.h.43.self_attention.dense.weight": "pytorch_model-
|
318 |
-
"transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-
|
319 |
-
"transformer.h.44.ln_attn.bias": "pytorch_model-
|
320 |
-
"transformer.h.44.ln_attn.weight": "pytorch_model-
|
321 |
-
"transformer.h.44.ln_mlp.bias": "pytorch_model-
|
322 |
-
"transformer.h.44.ln_mlp.weight": "pytorch_model-
|
323 |
-
"transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-
|
324 |
-
"transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-
|
325 |
-
"transformer.h.44.self_attention.dense.weight": "pytorch_model-
|
326 |
-
"transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-
|
327 |
-
"transformer.h.45.ln_attn.bias": "pytorch_model-
|
328 |
-
"transformer.h.45.ln_attn.weight": "pytorch_model-
|
329 |
-
"transformer.h.45.ln_mlp.bias": "pytorch_model-
|
330 |
-
"transformer.h.45.ln_mlp.weight": "pytorch_model-
|
331 |
-
"transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-
|
332 |
-
"transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-
|
333 |
-
"transformer.h.45.self_attention.dense.weight": "pytorch_model-
|
334 |
-
"transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-
|
335 |
-
"transformer.h.46.ln_attn.bias": "pytorch_model-
|
336 |
-
"transformer.h.46.ln_attn.weight": "pytorch_model-
|
337 |
-
"transformer.h.46.ln_mlp.bias": "pytorch_model-
|
338 |
-
"transformer.h.46.ln_mlp.weight": "pytorch_model-
|
339 |
-
"transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-
|
340 |
-
"transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-
|
341 |
-
"transformer.h.46.self_attention.dense.weight": "pytorch_model-
|
342 |
-
"transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-
|
343 |
-
"transformer.h.47.ln_attn.bias": "pytorch_model-
|
344 |
-
"transformer.h.47.ln_attn.weight": "pytorch_model-
|
345 |
-
"transformer.h.47.ln_mlp.bias": "pytorch_model-
|
346 |
-
"transformer.h.47.ln_mlp.weight": "pytorch_model-
|
347 |
-
"transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-
|
348 |
-
"transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-
|
349 |
-
"transformer.h.47.self_attention.dense.weight": "pytorch_model-
|
350 |
-
"transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-
|
351 |
-
"transformer.h.48.ln_attn.bias": "pytorch_model-
|
352 |
-
"transformer.h.48.ln_attn.weight": "pytorch_model-
|
353 |
-
"transformer.h.48.ln_mlp.bias": "pytorch_model-
|
354 |
-
"transformer.h.48.ln_mlp.weight": "pytorch_model-
|
355 |
-
"transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-
|
356 |
-
"transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-
|
357 |
-
"transformer.h.48.self_attention.dense.weight": "pytorch_model-
|
358 |
-
"transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-
|
359 |
-
"transformer.h.49.ln_attn.bias": "pytorch_model-
|
360 |
-
"transformer.h.49.ln_attn.weight": "pytorch_model-
|
361 |
-
"transformer.h.49.ln_mlp.bias": "pytorch_model-
|
362 |
-
"transformer.h.49.ln_mlp.weight": "pytorch_model-
|
363 |
-
"transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-
|
364 |
-
"transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-
|
365 |
-
"transformer.h.49.self_attention.dense.weight": "pytorch_model-
|
366 |
-
"transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-
|
367 |
-
"transformer.h.5.ln_attn.bias": "pytorch_model-
|
368 |
-
"transformer.h.5.ln_attn.weight": "pytorch_model-
|
369 |
-
"transformer.h.5.ln_mlp.bias": "pytorch_model-
|
370 |
-
"transformer.h.5.ln_mlp.weight": "pytorch_model-
|
371 |
-
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-
|
372 |
-
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-
|
373 |
-
"transformer.h.5.self_attention.dense.weight": "pytorch_model-
|
374 |
-
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-
|
375 |
-
"transformer.h.50.ln_attn.bias": "pytorch_model-
|
376 |
-
"transformer.h.50.ln_attn.weight": "pytorch_model-
|
377 |
-
"transformer.h.50.ln_mlp.bias": "pytorch_model-
|
378 |
-
"transformer.h.50.ln_mlp.weight": "pytorch_model-
|
379 |
-
"transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-
|
380 |
-
"transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-
|
381 |
-
"transformer.h.50.self_attention.dense.weight": "pytorch_model-
|
382 |
-
"transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-
|
383 |
-
"transformer.h.51.ln_attn.bias": "pytorch_model-
|
384 |
-
"transformer.h.51.ln_attn.weight": "pytorch_model-
|
385 |
-
"transformer.h.51.ln_mlp.bias": "pytorch_model-
|
386 |
-
"transformer.h.51.ln_mlp.weight": "pytorch_model-
|
387 |
-
"transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-
|
388 |
-
"transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-
|
389 |
-
"transformer.h.51.self_attention.dense.weight": "pytorch_model-
|
390 |
-
"transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-
|
391 |
-
"transformer.h.52.ln_attn.bias": "pytorch_model-
|
392 |
-
"transformer.h.52.ln_attn.weight": "pytorch_model-
|
393 |
-
"transformer.h.52.ln_mlp.bias": "pytorch_model-
|
394 |
-
"transformer.h.52.ln_mlp.weight": "pytorch_model-
|
395 |
-
"transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-
|
396 |
-
"transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-
|
397 |
-
"transformer.h.52.self_attention.dense.weight": "pytorch_model-
|
398 |
-
"transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-
|
399 |
-
"transformer.h.53.ln_attn.bias": "pytorch_model-
|
400 |
-
"transformer.h.53.ln_attn.weight": "pytorch_model-
|
401 |
-
"transformer.h.53.ln_mlp.bias": "pytorch_model-
|
402 |
-
"transformer.h.53.ln_mlp.weight": "pytorch_model-
|
403 |
-
"transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-
|
404 |
-
"transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-
|
405 |
-
"transformer.h.53.self_attention.dense.weight": "pytorch_model-
|
406 |
-
"transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-
|
407 |
-
"transformer.h.54.ln_attn.bias": "pytorch_model-
|
408 |
-
"transformer.h.54.ln_attn.weight": "pytorch_model-
|
409 |
-
"transformer.h.54.ln_mlp.bias": "pytorch_model-
|
410 |
-
"transformer.h.54.ln_mlp.weight": "pytorch_model-
|
411 |
-
"transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-
|
412 |
-
"transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-
|
413 |
-
"transformer.h.54.self_attention.dense.weight": "pytorch_model-
|
414 |
-
"transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-
|
415 |
-
"transformer.h.55.ln_attn.bias": "pytorch_model-
|
416 |
-
"transformer.h.55.ln_attn.weight": "pytorch_model-
|
417 |
-
"transformer.h.55.ln_mlp.bias": "pytorch_model-
|
418 |
-
"transformer.h.55.ln_mlp.weight": "pytorch_model-
|
419 |
-
"transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-
|
420 |
-
"transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-
|
421 |
-
"transformer.h.55.self_attention.dense.weight": "pytorch_model-
|
422 |
-
"transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-
|
423 |
-
"transformer.h.56.ln_attn.bias": "pytorch_model-
|
424 |
-
"transformer.h.56.ln_attn.weight": "pytorch_model-
|
425 |
-
"transformer.h.56.ln_mlp.bias": "pytorch_model-
|
426 |
-
"transformer.h.56.ln_mlp.weight": "pytorch_model-
|
427 |
-
"transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-
|
428 |
-
"transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-
|
429 |
-
"transformer.h.56.self_attention.dense.weight": "pytorch_model-
|
430 |
-
"transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-
|
431 |
-
"transformer.h.57.ln_attn.bias": "pytorch_model-
|
432 |
-
"transformer.h.57.ln_attn.weight": "pytorch_model-
|
433 |
-
"transformer.h.57.ln_mlp.bias": "pytorch_model-
|
434 |
-
"transformer.h.57.ln_mlp.weight": "pytorch_model-
|
435 |
-
"transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-
|
436 |
-
"transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-
|
437 |
-
"transformer.h.57.self_attention.dense.weight": "pytorch_model-
|
438 |
-
"transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-
|
439 |
-
"transformer.h.58.ln_attn.bias": "pytorch_model-
|
440 |
-
"transformer.h.58.ln_attn.weight": "pytorch_model-
|
441 |
-
"transformer.h.58.ln_mlp.bias": "pytorch_model-
|
442 |
-
"transformer.h.58.ln_mlp.weight": "pytorch_model-
|
443 |
-
"transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-
|
444 |
-
"transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-
|
445 |
-
"transformer.h.58.self_attention.dense.weight": "pytorch_model-
|
446 |
-
"transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-
|
447 |
-
"transformer.h.59.ln_attn.bias": "pytorch_model-
|
448 |
-
"transformer.h.59.ln_attn.weight": "pytorch_model-
|
449 |
-
"transformer.h.59.ln_mlp.bias": "pytorch_model-
|
450 |
-
"transformer.h.59.ln_mlp.weight": "pytorch_model-
|
451 |
-
"transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-
|
452 |
-
"transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-
|
453 |
-
"transformer.h.59.self_attention.dense.weight": "pytorch_model-
|
454 |
-
"transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-
|
455 |
-
"transformer.h.6.ln_attn.bias": "pytorch_model-
|
456 |
-
"transformer.h.6.ln_attn.weight": "pytorch_model-
|
457 |
-
"transformer.h.6.ln_mlp.bias": "pytorch_model-
|
458 |
-
"transformer.h.6.ln_mlp.weight": "pytorch_model-
|
459 |
-
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-
|
460 |
-
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-
|
461 |
-
"transformer.h.6.self_attention.dense.weight": "pytorch_model-
|
462 |
-
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-
|
463 |
-
"transformer.h.7.ln_attn.bias": "pytorch_model-
|
464 |
-
"transformer.h.7.ln_attn.weight": "pytorch_model-
|
465 |
-
"transformer.h.7.ln_mlp.bias": "pytorch_model-
|
466 |
-
"transformer.h.7.ln_mlp.weight": "pytorch_model-
|
467 |
-
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-
|
468 |
-
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-
|
469 |
-
"transformer.h.7.self_attention.dense.weight": "pytorch_model-
|
470 |
-
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-
|
471 |
-
"transformer.h.8.ln_attn.bias": "pytorch_model-
|
472 |
-
"transformer.h.8.ln_attn.weight": "pytorch_model-
|
473 |
-
"transformer.h.8.ln_mlp.bias": "pytorch_model-
|
474 |
-
"transformer.h.8.ln_mlp.weight": "pytorch_model-
|
475 |
-
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-
|
476 |
-
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-
|
477 |
-
"transformer.h.8.self_attention.dense.weight": "pytorch_model-
|
478 |
-
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-
|
479 |
-
"transformer.h.9.ln_attn.bias": "pytorch_model-
|
480 |
-
"transformer.h.9.ln_attn.weight": "pytorch_model-
|
481 |
-
"transformer.h.9.ln_mlp.bias": "pytorch_model-
|
482 |
-
"transformer.h.9.ln_mlp.weight": "pytorch_model-
|
483 |
-
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-
|
484 |
-
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-
|
485 |
-
"transformer.h.9.self_attention.dense.weight": "pytorch_model-
|
486 |
-
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-
|
487 |
-
"transformer.ln_f.bias": "pytorch_model-
|
488 |
-
"transformer.ln_f.weight": "pytorch_model-
|
489 |
-
"transformer.word_embeddings.weight": "pytorch_model-00001-of-
|
490 |
}
|
491 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 83671973888
|
4 |
},
|
5 |
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00009-of-00009.bin",
|
7 |
+
"transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
8 |
+
"transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
9 |
+
"transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
10 |
+
"transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
11 |
+
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
12 |
+
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
13 |
+
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
14 |
+
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
15 |
+
"transformer.h.1.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
16 |
+
"transformer.h.1.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
17 |
+
"transformer.h.1.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
18 |
+
"transformer.h.1.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
19 |
+
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
20 |
+
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
21 |
+
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
22 |
+
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
23 |
+
"transformer.h.10.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
24 |
+
"transformer.h.10.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
25 |
+
"transformer.h.10.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
26 |
+
"transformer.h.10.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
27 |
+
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
28 |
+
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
29 |
+
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
30 |
+
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
31 |
+
"transformer.h.11.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
32 |
+
"transformer.h.11.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
33 |
+
"transformer.h.11.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
34 |
+
"transformer.h.11.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
35 |
+
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
36 |
+
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
37 |
+
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
38 |
+
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
39 |
+
"transformer.h.12.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
40 |
+
"transformer.h.12.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
41 |
+
"transformer.h.12.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
42 |
+
"transformer.h.12.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
43 |
+
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
44 |
+
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
45 |
+
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
46 |
+
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
47 |
+
"transformer.h.13.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
48 |
+
"transformer.h.13.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
49 |
+
"transformer.h.13.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
50 |
+
"transformer.h.13.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
51 |
+
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
52 |
+
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
53 |
+
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
54 |
+
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
55 |
+
"transformer.h.14.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
56 |
+
"transformer.h.14.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
57 |
+
"transformer.h.14.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
58 |
+
"transformer.h.14.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
59 |
+
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
60 |
+
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
61 |
+
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
62 |
+
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
63 |
+
"transformer.h.15.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
64 |
+
"transformer.h.15.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
65 |
+
"transformer.h.15.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
66 |
+
"transformer.h.15.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
67 |
+
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
68 |
+
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
69 |
+
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
70 |
+
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
71 |
+
"transformer.h.16.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
72 |
+
"transformer.h.16.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
73 |
+
"transformer.h.16.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
74 |
+
"transformer.h.16.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
75 |
+
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
76 |
+
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
77 |
+
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
78 |
+
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
79 |
+
"transformer.h.17.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
80 |
+
"transformer.h.17.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
81 |
+
"transformer.h.17.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
82 |
+
"transformer.h.17.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
83 |
+
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
84 |
+
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
85 |
+
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
86 |
+
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
87 |
+
"transformer.h.18.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
88 |
+
"transformer.h.18.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
89 |
+
"transformer.h.18.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
90 |
+
"transformer.h.18.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
91 |
+
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
92 |
+
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
93 |
+
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
94 |
+
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
95 |
+
"transformer.h.19.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
96 |
+
"transformer.h.19.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
97 |
+
"transformer.h.19.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
98 |
+
"transformer.h.19.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
99 |
+
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
|
100 |
+
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
|
101 |
+
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
102 |
+
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
103 |
+
"transformer.h.2.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
104 |
+
"transformer.h.2.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
105 |
+
"transformer.h.2.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
106 |
+
"transformer.h.2.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
107 |
+
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
108 |
+
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
109 |
+
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
110 |
+
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
111 |
+
"transformer.h.20.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
|
112 |
+
"transformer.h.20.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
|
113 |
+
"transformer.h.20.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
|
114 |
+
"transformer.h.20.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
|
115 |
+
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
116 |
+
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
117 |
+
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
|
118 |
+
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
|
119 |
+
"transformer.h.21.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
120 |
+
"transformer.h.21.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
121 |
+
"transformer.h.21.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
122 |
+
"transformer.h.21.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
123 |
+
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
124 |
+
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
125 |
+
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
126 |
+
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
127 |
+
"transformer.h.22.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
128 |
+
"transformer.h.22.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
129 |
+
"transformer.h.22.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
130 |
+
"transformer.h.22.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
131 |
+
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
132 |
+
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
133 |
+
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
134 |
+
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
135 |
+
"transformer.h.23.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
136 |
+
"transformer.h.23.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
137 |
+
"transformer.h.23.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
138 |
+
"transformer.h.23.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
139 |
+
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
140 |
+
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
141 |
+
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
142 |
+
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
143 |
+
"transformer.h.24.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
144 |
+
"transformer.h.24.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
145 |
+
"transformer.h.24.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
146 |
+
"transformer.h.24.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
147 |
+
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
148 |
+
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
149 |
+
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
150 |
+
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
151 |
+
"transformer.h.25.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
152 |
+
"transformer.h.25.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
153 |
+
"transformer.h.25.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
154 |
+
"transformer.h.25.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
155 |
+
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
156 |
+
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
157 |
+
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
158 |
+
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
159 |
+
"transformer.h.26.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
160 |
+
"transformer.h.26.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
161 |
+
"transformer.h.26.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
162 |
+
"transformer.h.26.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
163 |
+
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
|
164 |
+
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
|
165 |
+
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
166 |
+
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
167 |
+
"transformer.h.27.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
|
168 |
+
"transformer.h.27.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
|
169 |
+
"transformer.h.27.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
|
170 |
+
"transformer.h.27.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
|
171 |
+
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
172 |
+
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
173 |
+
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
|
174 |
+
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
|
175 |
+
"transformer.h.28.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
176 |
+
"transformer.h.28.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
177 |
+
"transformer.h.28.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
178 |
+
"transformer.h.28.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
179 |
+
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
180 |
+
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
181 |
+
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
182 |
+
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
183 |
+
"transformer.h.29.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
184 |
+
"transformer.h.29.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
185 |
+
"transformer.h.29.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
186 |
+
"transformer.h.29.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
187 |
+
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
188 |
+
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
189 |
+
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
190 |
+
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
191 |
+
"transformer.h.3.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
192 |
+
"transformer.h.3.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
193 |
+
"transformer.h.3.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
194 |
+
"transformer.h.3.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
195 |
+
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
196 |
+
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
197 |
+
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
198 |
+
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
199 |
+
"transformer.h.30.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
200 |
+
"transformer.h.30.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
201 |
+
"transformer.h.30.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
202 |
+
"transformer.h.30.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
203 |
+
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
204 |
+
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
205 |
+
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
206 |
+
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
207 |
+
"transformer.h.31.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
208 |
+
"transformer.h.31.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
209 |
+
"transformer.h.31.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
210 |
+
"transformer.h.31.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
211 |
+
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
212 |
+
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
213 |
+
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
214 |
+
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
215 |
+
"transformer.h.32.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
216 |
+
"transformer.h.32.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
217 |
+
"transformer.h.32.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
218 |
+
"transformer.h.32.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
219 |
+
"transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
220 |
+
"transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
221 |
+
"transformer.h.32.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
222 |
+
"transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
223 |
+
"transformer.h.33.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
224 |
+
"transformer.h.33.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
225 |
+
"transformer.h.33.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
226 |
+
"transformer.h.33.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
227 |
+
"transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
|
228 |
+
"transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
|
229 |
+
"transformer.h.33.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
230 |
+
"transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
231 |
+
"transformer.h.34.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
|
232 |
+
"transformer.h.34.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
|
233 |
+
"transformer.h.34.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
|
234 |
+
"transformer.h.34.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
|
235 |
+
"transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
236 |
+
"transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
237 |
+
"transformer.h.34.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
|
238 |
+
"transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
|
239 |
+
"transformer.h.35.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
240 |
+
"transformer.h.35.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
241 |
+
"transformer.h.35.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
242 |
+
"transformer.h.35.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
243 |
+
"transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
244 |
+
"transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
245 |
+
"transformer.h.35.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
246 |
+
"transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
247 |
+
"transformer.h.36.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
248 |
+
"transformer.h.36.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
249 |
+
"transformer.h.36.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
250 |
+
"transformer.h.36.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
251 |
+
"transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
252 |
+
"transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
253 |
+
"transformer.h.36.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
254 |
+
"transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
255 |
+
"transformer.h.37.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
256 |
+
"transformer.h.37.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
257 |
+
"transformer.h.37.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
258 |
+
"transformer.h.37.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
259 |
+
"transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
260 |
+
"transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
261 |
+
"transformer.h.37.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
262 |
+
"transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
263 |
+
"transformer.h.38.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
264 |
+
"transformer.h.38.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
265 |
+
"transformer.h.38.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
266 |
+
"transformer.h.38.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
267 |
+
"transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
268 |
+
"transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
269 |
+
"transformer.h.38.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
270 |
+
"transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
271 |
+
"transformer.h.39.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
272 |
+
"transformer.h.39.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
273 |
+
"transformer.h.39.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
274 |
+
"transformer.h.39.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
275 |
+
"transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
276 |
+
"transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
277 |
+
"transformer.h.39.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
278 |
+
"transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
279 |
+
"transformer.h.4.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
280 |
+
"transformer.h.4.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
281 |
+
"transformer.h.4.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
282 |
+
"transformer.h.4.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
283 |
+
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
284 |
+
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
285 |
+
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
286 |
+
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
287 |
+
"transformer.h.40.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
288 |
+
"transformer.h.40.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
289 |
+
"transformer.h.40.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
290 |
+
"transformer.h.40.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
291 |
+
"transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
|
292 |
+
"transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
|
293 |
+
"transformer.h.40.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
294 |
+
"transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
295 |
+
"transformer.h.41.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
|
296 |
+
"transformer.h.41.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
|
297 |
+
"transformer.h.41.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
|
298 |
+
"transformer.h.41.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
|
299 |
+
"transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
300 |
+
"transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
301 |
+
"transformer.h.41.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
|
302 |
+
"transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
|
303 |
+
"transformer.h.42.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
304 |
+
"transformer.h.42.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
305 |
+
"transformer.h.42.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
306 |
+
"transformer.h.42.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
307 |
+
"transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
308 |
+
"transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
309 |
+
"transformer.h.42.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
310 |
+
"transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
311 |
+
"transformer.h.43.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
312 |
+
"transformer.h.43.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
313 |
+
"transformer.h.43.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
314 |
+
"transformer.h.43.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
315 |
+
"transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
316 |
+
"transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
317 |
+
"transformer.h.43.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
318 |
+
"transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
319 |
+
"transformer.h.44.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
320 |
+
"transformer.h.44.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
321 |
+
"transformer.h.44.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
322 |
+
"transformer.h.44.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
323 |
+
"transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
324 |
+
"transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
325 |
+
"transformer.h.44.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
326 |
+
"transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
327 |
+
"transformer.h.45.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
328 |
+
"transformer.h.45.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
329 |
+
"transformer.h.45.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
330 |
+
"transformer.h.45.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
331 |
+
"transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
332 |
+
"transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
333 |
+
"transformer.h.45.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
334 |
+
"transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
335 |
+
"transformer.h.46.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
336 |
+
"transformer.h.46.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
337 |
+
"transformer.h.46.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
338 |
+
"transformer.h.46.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
339 |
+
"transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
340 |
+
"transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
341 |
+
"transformer.h.46.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
342 |
+
"transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
343 |
+
"transformer.h.47.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
344 |
+
"transformer.h.47.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
345 |
+
"transformer.h.47.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
346 |
+
"transformer.h.47.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
347 |
+
"transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
|
348 |
+
"transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
|
349 |
+
"transformer.h.47.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
350 |
+
"transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
351 |
+
"transformer.h.48.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
|
352 |
+
"transformer.h.48.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
|
353 |
+
"transformer.h.48.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
|
354 |
+
"transformer.h.48.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
|
355 |
+
"transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
356 |
+
"transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
357 |
+
"transformer.h.48.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
|
358 |
+
"transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
|
359 |
+
"transformer.h.49.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
360 |
+
"transformer.h.49.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
361 |
+
"transformer.h.49.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
362 |
+
"transformer.h.49.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
363 |
+
"transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
364 |
+
"transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
365 |
+
"transformer.h.49.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
366 |
+
"transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
367 |
+
"transformer.h.5.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
368 |
+
"transformer.h.5.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
369 |
+
"transformer.h.5.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
370 |
+
"transformer.h.5.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
371 |
+
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
|
372 |
+
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
|
373 |
+
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
374 |
+
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
375 |
+
"transformer.h.50.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
376 |
+
"transformer.h.50.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
377 |
+
"transformer.h.50.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
378 |
+
"transformer.h.50.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
379 |
+
"transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
380 |
+
"transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
381 |
+
"transformer.h.50.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
382 |
+
"transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
383 |
+
"transformer.h.51.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
384 |
+
"transformer.h.51.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
385 |
+
"transformer.h.51.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
386 |
+
"transformer.h.51.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
387 |
+
"transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
388 |
+
"transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
389 |
+
"transformer.h.51.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
390 |
+
"transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
391 |
+
"transformer.h.52.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
392 |
+
"transformer.h.52.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
393 |
+
"transformer.h.52.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
394 |
+
"transformer.h.52.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
395 |
+
"transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
396 |
+
"transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
397 |
+
"transformer.h.52.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
398 |
+
"transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
399 |
+
"transformer.h.53.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
400 |
+
"transformer.h.53.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
401 |
+
"transformer.h.53.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
402 |
+
"transformer.h.53.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
403 |
+
"transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
404 |
+
"transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
405 |
+
"transformer.h.53.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
406 |
+
"transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
407 |
+
"transformer.h.54.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
408 |
+
"transformer.h.54.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
409 |
+
"transformer.h.54.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
410 |
+
"transformer.h.54.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
411 |
+
"transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
|
412 |
+
"transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
|
413 |
+
"transformer.h.54.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
414 |
+
"transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
415 |
+
"transformer.h.55.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
|
416 |
+
"transformer.h.55.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
|
417 |
+
"transformer.h.55.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
|
418 |
+
"transformer.h.55.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
|
419 |
+
"transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
|
420 |
+
"transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
|
421 |
+
"transformer.h.55.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
|
422 |
+
"transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
|
423 |
+
"transformer.h.56.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
|
424 |
+
"transformer.h.56.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
|
425 |
+
"transformer.h.56.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
|
426 |
+
"transformer.h.56.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
|
427 |
+
"transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
|
428 |
+
"transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
|
429 |
+
"transformer.h.56.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
|
430 |
+
"transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
|
431 |
+
"transformer.h.57.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
|
432 |
+
"transformer.h.57.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
|
433 |
+
"transformer.h.57.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
|
434 |
+
"transformer.h.57.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
|
435 |
+
"transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
|
436 |
+
"transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
|
437 |
+
"transformer.h.57.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
|
438 |
+
"transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
|
439 |
+
"transformer.h.58.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
|
440 |
+
"transformer.h.58.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
|
441 |
+
"transformer.h.58.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
|
442 |
+
"transformer.h.58.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
|
443 |
+
"transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
|
444 |
+
"transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
|
445 |
+
"transformer.h.58.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
|
446 |
+
"transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
|
447 |
+
"transformer.h.59.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
|
448 |
+
"transformer.h.59.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
|
449 |
+
"transformer.h.59.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
|
450 |
+
"transformer.h.59.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
|
451 |
+
"transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
|
452 |
+
"transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
|
453 |
+
"transformer.h.59.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
|
454 |
+
"transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
|
455 |
+
"transformer.h.6.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
|
456 |
+
"transformer.h.6.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
|
457 |
+
"transformer.h.6.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
|
458 |
+
"transformer.h.6.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
|
459 |
+
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
460 |
+
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
461 |
+
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
|
462 |
+
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
|
463 |
+
"transformer.h.7.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
464 |
+
"transformer.h.7.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
465 |
+
"transformer.h.7.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
466 |
+
"transformer.h.7.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
467 |
+
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
468 |
+
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
469 |
+
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
470 |
+
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
471 |
+
"transformer.h.8.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
472 |
+
"transformer.h.8.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
473 |
+
"transformer.h.8.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
474 |
+
"transformer.h.8.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
475 |
+
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
476 |
+
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
477 |
+
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
478 |
+
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
479 |
+
"transformer.h.9.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
|
480 |
+
"transformer.h.9.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
|
481 |
+
"transformer.h.9.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
|
482 |
+
"transformer.h.9.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
|
483 |
+
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
|
484 |
+
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
|
485 |
+
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
|
486 |
+
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
|
487 |
+
"transformer.ln_f.bias": "pytorch_model-00009-of-00009.bin",
|
488 |
+
"transformer.ln_f.weight": "pytorch_model-00009-of-00009.bin",
|
489 |
+
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00009.bin"
|
490 |
}
|
491 |
}
|