joanllop commited on
Commit
203f87a
1 Parent(s): f3d7c9c

Revert "2gb shards"

Browse files

This reverts commit 03a519c1d0d0e476a4a12af6d6a6d9bb802c0abc.

model-00001-of-00015.safetensors → model-00001-of-00002.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1e5b97f5ac8b84a16da79b0cd4d2ac660424f4a3f655dbb0cbbdb7784743ef7
3
- size 1909299216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2ee43ebc4b14760c2a94baa24213f0f37f2a5e9b07a6e6488f4376265830d7b
3
+ size 9981994344
model-00002-of-00015.safetensors → model-00002-of-00002.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13700ed44b712d0f762b1719a6ee2cfc8d2659c800abdf30e247f573d6ed210f
3
- size 1986929176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e85ec13d59bfc6c6f84bc0e7419ad03776a119d739dbe4f006c2dd87bbc71c
3
+ size 3727267912
model-00005-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4c46816a9da3f260fd7d64708fc87502c4449a0429f27b6dfee3aecebe469ba
3
- size 1986929168
 
 
 
 
model-00006-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4042f69ea71c4985063e70872fa99173cf4ec006d7c9a15fc6a8b8cc712a0c2a
3
- size 1986965768
 
 
 
 
model-00007-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:931719bbe3d98645fc70c8e22df68636cc2f504a14dd41354e544ce346bf36ac
3
- size 1824072368
 
 
 
 
model-00008-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:da1d16c2321080d8f71e6396a1a1d6adf8b5866629d2a5cb7f12fec73958ebe9
3
- size 1986929192
 
 
 
 
model-00009-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a760dcf799420983a7db9ebf49bb9c6bc004042d6a51cfdfd07c68abec0c6740
3
- size 1986965768
 
 
 
 
model-00010-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3e4da7be6ebf8c20057d8364c261126efeeceb56b2d190be3ccbf6f82b8f085
3
- size 1824072368
 
 
 
 
model-00011-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:590115bd785f5862835fbe023cb98ebc05d4c4f9310bc301a577283e0fb880b8
3
- size 1986929192
 
 
 
 
model-00012-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8957a361fa3558b14bfadb08e6e1c6611b2a8c70de914af861672fd614ae72bc
3
- size 1986965768
 
 
 
 
model-00013-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c7954b3c32e36900223d0725f7ec5e31951dc553aa7740dd8791a2c31cd584
3
- size 1824072368
 
 
 
 
model-00014-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:10dd2988a936abd107ee5c317e38ffa6f446acd781325440d890a0a28fb159a6
3
- size 1986929192
 
 
 
 
model-00015-of-00015.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93796669d72c8c5a962b346eaf158454f52531b7b7231683020f73760fb7d6a5
3
- size 330403664
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,202 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 27418477824
4
- },
5
- "weight_map": {
6
- "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
7
- "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
8
- "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00015.safetensors",
9
- "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
10
- "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
11
- "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
12
- "transformer.h.1.input_layernorm.bias": "model-00001-of-00015.safetensors",
13
- "transformer.h.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
14
- "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
15
- "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
16
- "transformer.h.1.self_attention.dense.weight": "model-00001-of-00015.safetensors",
17
- "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
18
- "transformer.h.10.input_layernorm.bias": "model-00005-of-00015.safetensors",
19
- "transformer.h.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
20
- "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
21
- "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
22
- "transformer.h.10.self_attention.dense.weight": "model-00005-of-00015.safetensors",
23
- "transformer.h.10.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
24
- "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
25
- "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
26
- "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
27
- "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
28
- "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
29
- "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
30
- "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
31
- "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
32
- "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
33
- "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
34
- "transformer.h.12.self_attention.dense.weight": "model-00006-of-00015.safetensors",
35
- "transformer.h.12.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
36
- "transformer.h.13.input_layernorm.bias": "model-00006-of-00015.safetensors",
37
- "transformer.h.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
38
- "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
39
- "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
40
- "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
41
- "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
42
- "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
43
- "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
44
- "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
45
- "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
46
- "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
47
- "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
48
- "transformer.h.15.input_layernorm.bias": "model-00007-of-00015.safetensors",
49
- "transformer.h.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
50
- "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
51
- "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
52
- "transformer.h.15.self_attention.dense.weight": "model-00007-of-00015.safetensors",
53
- "transformer.h.15.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
54
- "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
55
- "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
56
- "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
57
- "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
58
- "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
59
- "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
60
- "transformer.h.17.input_layernorm.bias": "model-00008-of-00015.safetensors",
61
- "transformer.h.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
62
- "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
63
- "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
64
- "transformer.h.17.self_attention.dense.weight": "model-00008-of-00015.safetensors",
65
- "transformer.h.17.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
66
- "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
67
- "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
68
- "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
69
- "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
70
- "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
71
- "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
72
- "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
73
- "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
74
- "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
75
- "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
76
- "transformer.h.19.self_attention.dense.weight": "model-00009-of-00015.safetensors",
77
- "transformer.h.19.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
78
- "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
79
- "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
80
- "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
81
- "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
82
- "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
83
- "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
84
- "transformer.h.20.input_layernorm.bias": "model-00009-of-00015.safetensors",
85
- "transformer.h.20.input_layernorm.weight": "model-00009-of-00015.safetensors",
86
- "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
87
- "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
88
- "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
89
- "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
90
- "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
91
- "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
92
- "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
93
- "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
94
- "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
95
- "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
96
- "transformer.h.22.input_layernorm.bias": "model-00010-of-00015.safetensors",
97
- "transformer.h.22.input_layernorm.weight": "model-00010-of-00015.safetensors",
98
- "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
99
- "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
100
- "transformer.h.22.self_attention.dense.weight": "model-00010-of-00015.safetensors",
101
- "transformer.h.22.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
102
- "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
103
- "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
104
- "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
105
- "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
106
- "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
107
- "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
108
- "transformer.h.24.input_layernorm.bias": "model-00011-of-00015.safetensors",
109
- "transformer.h.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
110
- "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
111
- "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
112
- "transformer.h.24.self_attention.dense.weight": "model-00011-of-00015.safetensors",
113
- "transformer.h.24.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
114
- "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
115
- "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
116
- "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
117
- "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
118
- "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
119
- "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
120
- "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
121
- "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
122
- "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
123
- "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
124
- "transformer.h.26.self_attention.dense.weight": "model-00012-of-00015.safetensors",
125
- "transformer.h.26.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
126
- "transformer.h.27.input_layernorm.bias": "model-00012-of-00015.safetensors",
127
- "transformer.h.27.input_layernorm.weight": "model-00012-of-00015.safetensors",
128
- "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
129
- "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
130
- "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
131
- "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
132
- "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
133
- "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
134
- "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
135
- "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
136
- "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
137
- "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
138
- "transformer.h.29.input_layernorm.bias": "model-00013-of-00015.safetensors",
139
- "transformer.h.29.input_layernorm.weight": "model-00013-of-00015.safetensors",
140
- "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
141
- "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
142
- "transformer.h.29.self_attention.dense.weight": "model-00013-of-00015.safetensors",
143
- "transformer.h.29.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
144
- "transformer.h.3.input_layernorm.bias": "model-00002-of-00015.safetensors",
145
- "transformer.h.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
146
- "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
147
- "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
148
- "transformer.h.3.self_attention.dense.weight": "model-00002-of-00015.safetensors",
149
- "transformer.h.3.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
150
- "transformer.h.30.input_layernorm.bias": "model-00014-of-00015.safetensors",
151
- "transformer.h.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
152
- "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
153
- "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
154
- "transformer.h.30.self_attention.dense.weight": "model-00014-of-00015.safetensors",
155
- "transformer.h.30.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
156
- "transformer.h.31.input_layernorm.bias": "model-00014-of-00015.safetensors",
157
- "transformer.h.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
158
- "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
159
- "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
160
- "transformer.h.31.self_attention.dense.weight": "model-00014-of-00015.safetensors",
161
- "transformer.h.31.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
162
- "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
163
- "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
164
- "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
165
- "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
166
- "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
167
- "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
168
- "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
169
- "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
170
- "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
171
- "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
172
- "transformer.h.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
173
- "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
174
- "transformer.h.6.input_layernorm.bias": "model-00003-of-00015.safetensors",
175
- "transformer.h.6.input_layernorm.weight": "model-00003-of-00015.safetensors",
176
- "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
177
- "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
178
- "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
179
- "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
180
- "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
181
- "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
182
- "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
183
- "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
184
- "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
185
- "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
186
- "transformer.h.8.input_layernorm.bias": "model-00004-of-00015.safetensors",
187
- "transformer.h.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
188
- "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
189
- "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
190
- "transformer.h.8.self_attention.dense.weight": "model-00004-of-00015.safetensors",
191
- "transformer.h.8.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
192
- "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
193
- "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
194
- "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
195
- "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
196
- "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
197
- "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
198
- "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
199
- "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
200
- "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors"
201
- }
202
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00003-of-00015.safetensors → pytorch_model-00001-of-00002.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b84ab4f3c73bacb562641c4fe426f757fb51615efd14ca1ca3663071dc8008e
3
- size 1986965752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71df7f76b33ae5afd2d6185422944e5063cd69d065cb73421ffdaae1bca4ef9e
3
+ size 9982026522
pytorch_model-00001-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcc6b4251e53efbde51d4267520049b5fd6290d5b4d3a7ad95f180e5f47c4dcf
3
- size 1909302101
 
 
 
 
model-00004-of-00015.safetensors → pytorch_model-00002-of-00002.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec939c0bca9ed24a14b89afb4bfc6d4e23f0ce232197d84a17f13ed3d5aba0f8
3
- size 1824072352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ad1f3e7abd726291a34fb5e8d80c3e5c2025bc3f137bbd6fa8a9cb081057eb
3
+ size 3727279707
pytorch_model-00002-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:91505af0d02b77bcc1e2f41c2acb1ef60625dd688abc6c50bad493a37b8c5408
3
- size 1986932345
 
 
 
 
pytorch_model-00003-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:35ccc21d95528dfa6be25e5b439f53f17cb9a044a7e9dfd4e61f5a58cde9d355
3
- size 1986969309
 
 
 
 
pytorch_model-00004-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:662025b98bc27ccc6edddc04b1d1c8528da36ed0efb538499494b25e981a9b64
3
- size 1824075723
 
 
 
 
pytorch_model-00005-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b55c63a3646bf82d9df1b16cd0c0fd1b13686f8d0c3f65ac96c0b631a452e4f
3
- size 1986932345
 
 
 
 
pytorch_model-00006-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:82e27b55247afe45d8f1ad66e869953b3bc2aeded98f5839d5a78249c72f7efc
3
- size 1986969309
 
 
 
 
pytorch_model-00007-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b1b676120ed79ae2b1f2b1bb49501af70cfee5b4716c7540f28bbe6e61c71ff
3
- size 1824075723
 
 
 
 
pytorch_model-00008-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ca67f101145e22551ce485d9a9d75d4cbaf0f27e3ad3902accfba3749e3901d
3
- size 1986932345
 
 
 
 
pytorch_model-00009-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:df972d9c60693ff21ae7ff3f5411b7e53d82dda5035a8dad4d1e67c17a3e8b5d
3
- size 1986969309
 
 
 
 
pytorch_model-00010-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d4f8abc1d6e1b4e42918572fcf6b52f930040846d043ad28a2c95eff7f84f22
3
- size 1824075723
 
 
 
 
pytorch_model-00011-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c050c86969b75eabd38cfc686f1ab8603b8e345ae495051aa044f6402f131a17
3
- size 1986932345
 
 
 
 
pytorch_model-00012-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:357d43e96875c27decf9c84d1b0ad8a8b00af6377602014f3da41b1466ef3502
3
- size 1986969309
 
 
 
 
pytorch_model-00013-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a593fe4635ae63eec96f3a3aa1d43d3ca62e615fad5658e63661494fd17f1279
3
- size 1824075723
 
 
 
 
pytorch_model-00014-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0544c157fb6fee6627ed6d9ddd2dd13d3b69200de20d2e0a72877531cc2215cf
3
- size 1986932345
 
 
 
 
pytorch_model-00015-of-00015.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3805702dea4614f05988ed0eada9b1e087cb12ccc34080642756b986daadb8bd
3
- size 330404876
 
 
 
 
pytorch_model.bin.index.json CHANGED
@@ -1,203 +1,203 @@
1
  {
2
  "metadata": {
3
- "total_size": 27418477824
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "pytorch_model-00001-of-00015.bin",
7
- "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00015.bin",
8
- "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
9
- "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00015.bin",
10
- "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00015.bin",
11
- "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
12
- "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
13
- "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00015.bin",
14
- "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
15
- "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
16
- "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
17
- "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
18
- "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
19
- "transformer.h.10.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
20
- "transformer.h.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
21
- "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
22
- "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
23
- "transformer.h.10.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
24
- "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
25
- "transformer.h.11.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
26
- "transformer.h.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
27
- "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
28
- "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
29
- "transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
30
- "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
31
- "transformer.h.12.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
32
- "transformer.h.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
33
- "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
34
- "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
35
- "transformer.h.12.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
36
- "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
37
- "transformer.h.13.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
38
- "transformer.h.13.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
39
- "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
40
- "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
41
- "transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
42
- "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
43
- "transformer.h.14.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
44
- "transformer.h.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
45
- "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
46
- "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
47
- "transformer.h.14.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
48
- "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
49
- "transformer.h.15.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
50
- "transformer.h.15.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
51
- "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
52
- "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
53
- "transformer.h.15.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
54
- "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
55
- "transformer.h.16.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
56
- "transformer.h.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
57
- "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
58
- "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
59
- "transformer.h.16.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
60
- "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
61
- "transformer.h.17.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
62
- "transformer.h.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
63
- "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
64
- "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
65
- "transformer.h.17.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
66
- "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
67
- "transformer.h.18.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
68
- "transformer.h.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
69
- "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
70
- "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
71
- "transformer.h.18.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
72
- "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
73
- "transformer.h.19.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
74
- "transformer.h.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
75
- "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
76
- "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
77
- "transformer.h.19.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
78
- "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
79
- "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
80
- "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
81
- "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
82
- "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
83
- "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
84
- "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
85
- "transformer.h.20.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
86
- "transformer.h.20.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
87
- "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
88
- "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
89
- "transformer.h.20.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
90
- "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
91
- "transformer.h.21.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
92
- "transformer.h.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
93
- "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
94
- "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
95
- "transformer.h.21.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
96
- "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
97
- "transformer.h.22.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
98
- "transformer.h.22.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
99
- "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
100
- "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
101
- "transformer.h.22.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
102
- "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
103
- "transformer.h.23.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
104
- "transformer.h.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
105
- "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
106
- "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
107
- "transformer.h.23.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
108
- "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
109
- "transformer.h.24.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
110
- "transformer.h.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
111
- "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
112
- "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
113
- "transformer.h.24.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
114
- "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
115
- "transformer.h.25.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
116
- "transformer.h.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
117
- "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
118
- "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
119
- "transformer.h.25.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
120
- "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
121
- "transformer.h.26.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
122
- "transformer.h.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
123
- "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
124
- "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
125
- "transformer.h.26.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
126
- "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
127
- "transformer.h.27.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
128
- "transformer.h.27.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
129
- "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
130
- "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
131
- "transformer.h.27.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
132
- "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
133
- "transformer.h.28.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
134
- "transformer.h.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
135
- "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
136
- "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
137
- "transformer.h.28.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
138
- "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
139
- "transformer.h.29.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
140
- "transformer.h.29.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
141
- "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
142
- "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
143
- "transformer.h.29.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
144
- "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
145
- "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
146
- "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
147
- "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
148
- "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
149
- "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
150
- "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
151
- "transformer.h.30.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
152
- "transformer.h.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
153
- "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
154
- "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
155
- "transformer.h.30.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
156
- "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
157
- "transformer.h.31.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
158
- "transformer.h.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
159
- "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00015.bin",
160
- "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
161
- "transformer.h.31.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
162
- "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
163
- "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
164
- "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
165
- "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
166
- "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
167
- "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
168
- "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
169
- "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
170
- "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
171
- "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
172
- "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
173
- "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
174
- "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
175
- "transformer.h.6.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
176
- "transformer.h.6.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
177
- "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
178
- "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
179
- "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
180
- "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
181
- "transformer.h.7.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
182
- "transformer.h.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
183
- "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
184
- "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
185
- "transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
186
- "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
187
- "transformer.h.8.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
188
- "transformer.h.8.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
189
- "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
190
- "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
191
- "transformer.h.8.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
192
- "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
193
- "transformer.h.9.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
194
- "transformer.h.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
195
- "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
196
- "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
197
- "transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
198
- "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
199
- "transformer.ln_f.bias": "pytorch_model-00015-of-00015.bin",
200
- "transformer.ln_f.weight": "pytorch_model-00015-of-00015.bin",
201
- "transformer.word_embeddings.weight": "pytorch_model-00001-of-00015.bin"
202
  }
203
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 13709238912
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-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.weight": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
106
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
107
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
108
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
109
+ "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
110
+ "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
111
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
112
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
113
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
114
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
115
+ "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
116
+ "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
118
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
119
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
120
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
121
+ "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
122
+ "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
123
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
124
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
125
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
126
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
127
+ "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
128
+ "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
130
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
131
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
132
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
133
+ "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
134
+ "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
136
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
137
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
138
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
139
+ "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
140
+ "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
142
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
143
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
144
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
145
+ "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
152
+ "transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
154
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
155
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
156
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
157
+ "transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
158
+ "transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
160
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
161
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
162
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
163
+ "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
200
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
201
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
202
  }
203
  }