SFconvertbot commited on
Commit
e4651b3
1 Parent(s): 7fabe56

Adding `safetensors` variant of this model

Browse files

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b252a9d518fdcd2e6ddbac42fca81ace7e2dc6b302f1b0241977d21ba79ff8
3
+ size 1827774184
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0256bcdc72a6274e572f17b0286aa57afca4f8a6fb5e539d55db17bdd461c0
3
+ size 1968291920
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2094df5c2234f4859de915aba9fd1d12a976e392d9e0eb51d7e514e90a88c0cc
3
+ size 1927406968
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059b389231148bac107fee793a033c5d475afc67e95214fd96337e45efba067a
3
+ size 1815217672
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc32862c70547336d4bd329a6e3fa800b52637ebcfa88be5f19613776d18d121
3
+ size 1968291952
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cf956b25c3f726829512eb46ae62dfe4ca8a46f6b0f1b626d5fb3f51e9ff97
3
+ size 1927406992
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58786658e9657ddda307f913760ef5de23d02f432128b2378bbee4998daa3048
3
+ size 1052805416
model.safetensors.index.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12487168064
4
+ },
5
+ "weight_map": {
6
+ "transformer.embedding.word_embeddings.weight": "model-00001-of-00007.safetensors",
7
+ "transformer.encoder.final_layernorm.weight": "model-00007-of-00007.safetensors",
8
+ "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
10
+ "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
11
+ "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
12
+ "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00007.safetensors",
13
+ "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
14
+ "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
15
+ "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
16
+ "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
17
+ "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
18
+ "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
19
+ "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00007.safetensors",
20
+ "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
21
+ "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
22
+ "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
23
+ "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
24
+ "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
25
+ "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
26
+ "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00007.safetensors",
27
+ "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
28
+ "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
29
+ "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
30
+ "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
31
+ "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
32
+ "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
33
+ "transformer.encoder.layers.11.self_attention.dense.weight": "model-00003-of-00007.safetensors",
34
+ "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
35
+ "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
36
+ "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
37
+ "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
38
+ "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
39
+ "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
40
+ "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00007.safetensors",
41
+ "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
42
+ "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
43
+ "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
44
+ "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
45
+ "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
46
+ "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
47
+ "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00007.safetensors",
48
+ "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
49
+ "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
50
+ "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
51
+ "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
52
+ "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
53
+ "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
54
+ "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00007.safetensors",
55
+ "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
56
+ "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
57
+ "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
58
+ "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
59
+ "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
60
+ "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
61
+ "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00007.safetensors",
62
+ "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
63
+ "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
64
+ "transformer.encoder.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
65
+ "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
66
+ "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
67
+ "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
68
+ "transformer.encoder.layers.16.self_attention.dense.weight": "model-00004-of-00007.safetensors",
69
+ "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
70
+ "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
71
+ "transformer.encoder.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
72
+ "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
73
+ "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
74
+ "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
75
+ "transformer.encoder.layers.17.self_attention.dense.weight": "model-00004-of-00007.safetensors",
76
+ "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
77
+ "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
78
+ "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
79
+ "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
80
+ "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
81
+ "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
82
+ "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00007.safetensors",
83
+ "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
84
+ "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
85
+ "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
86
+ "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
87
+ "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
88
+ "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
89
+ "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00007.safetensors",
90
+ "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
91
+ "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
92
+ "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
93
+ "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
94
+ "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
95
+ "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
96
+ "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00007.safetensors",
97
+ "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
98
+ "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
99
+ "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
100
+ "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
101
+ "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
102
+ "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
103
+ "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00007.safetensors",
104
+ "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
105
+ "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
106
+ "transformer.encoder.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
107
+ "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
108
+ "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
109
+ "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
110
+ "transformer.encoder.layers.21.self_attention.dense.weight": "model-00005-of-00007.safetensors",
111
+ "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
112
+ "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
113
+ "transformer.encoder.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
114
+ "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
115
+ "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
116
+ "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
117
+ "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00007.safetensors",
118
+ "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
119
+ "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
120
+ "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
121
+ "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
122
+ "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
123
+ "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
124
+ "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00007.safetensors",
125
+ "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
126
+ "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
127
+ "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
128
+ "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
129
+ "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
130
+ "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
131
+ "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00007.safetensors",
132
+ "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
133
+ "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
134
+ "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
135
+ "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
136
+ "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
137
+ "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
138
+ "transformer.encoder.layers.25.self_attention.dense.weight": "model-00006-of-00007.safetensors",
139
+ "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
140
+ "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
141
+ "transformer.encoder.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
142
+ "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
143
+ "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
144
+ "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
145
+ "transformer.encoder.layers.26.self_attention.dense.weight": "model-00006-of-00007.safetensors",
146
+ "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
147
+ "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
148
+ "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
149
+ "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
150
+ "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors",
151
+ "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
152
+ "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00007.safetensors",
153
+ "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00007.safetensors",
154
+ "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00007.safetensors",
155
+ "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
156
+ "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
157
+ "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
158
+ "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
159
+ "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00007.safetensors",
160
+ "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
161
+ "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
162
+ "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
163
+ "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
164
+ "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
165
+ "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
166
+ "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00007.safetensors",
167
+ "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
168
+ "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
169
+ "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
170
+ "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
171
+ "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
172
+ "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
173
+ "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00007.safetensors",
174
+ "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
175
+ "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
176
+ "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
177
+ "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
178
+ "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
179
+ "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
180
+ "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00007.safetensors",
181
+ "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
182
+ "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
183
+ "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
184
+ "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
185
+ "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
186
+ "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
187
+ "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00007.safetensors",
188
+ "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
189
+ "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
190
+ "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
191
+ "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
192
+ "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
193
+ "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
194
+ "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00007.safetensors",
195
+ "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
196
+ "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
197
+ "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
198
+ "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
199
+ "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
200
+ "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
201
+ "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00007.safetensors",
202
+ "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
203
+ "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
204
+ "transformer.output_layer.weight": "model-00007-of-00007.safetensors",
205
+ "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00007.safetensors"
206
+ }
207
+ }