SFconvertbot commited on
Commit
5c9e6a4
1 Parent(s): 1ffcec2

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-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2209fe278c9739e972ef421f22083072a059d555f16a49a4e65fe48d02312b5
3
+ size 1974522792
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7b16c7fdda0127752095596df8281aebe28c61b11ab0f40b9b5d47fb04dbea
3
+ size 1912663824
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea70638dfd0c8bf6384c0ac71303ad7255419a897a4741567ed7b46db88e626
3
+ size 1879117936
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2162ccdaca85e949d38f58128bbd0154db30c70110dc590058615119a3b2bd4b
3
+ size 1879100992
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c59a90e9d5638ee441f92bb52c5625b48e08ab376ec1c39e751338ede109b76
3
+ size 1879117976
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55836e7056080b72616c1189bdb22a9e8db15a7a54b4c82ded9b739c7e561a7
3
+ size 1879100992
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322ba58ab5293e0d26631174c0018bde034c093657479977ea3bc18bd280692d
3
+ size 1879117976
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:585c0eeac0b8b45b12c5bd1805f493fe5caaf1da4628468e0a2be33499d4d9af
3
+ size 1879100992
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9d00116ac05fbbd8e287e25415f5256e816c789e350b59c2a5b6ba0532b9fa
3
+ size 1879117976
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bb3c7372775edb158534a4ae3b75f05851cb571aa85af698bd5fad546b2cd9
3
+ size 402670208
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17443595264
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00010.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
160
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
161
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
162
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
163
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
164
+ "encoder.block.24.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
165
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
166
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
167
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
168
+ "encoder.block.24.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
169
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
170
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
171
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
172
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
173
+ "encoder.block.25.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
174
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
175
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
176
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
177
+ "encoder.block.25.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
178
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
179
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
180
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
181
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
182
+ "encoder.block.26.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
183
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
184
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
185
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
186
+ "encoder.block.26.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
187
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
188
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
189
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
190
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
191
+ "encoder.block.27.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
192
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
193
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
194
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
195
+ "encoder.block.27.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
196
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
197
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
198
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
199
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
200
+ "encoder.block.28.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
201
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
202
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
203
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
204
+ "encoder.block.28.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
205
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
206
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
207
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
208
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
209
+ "encoder.block.29.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
210
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
211
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
212
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
213
+ "encoder.block.29.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
214
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
215
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
216
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
217
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
218
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
219
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
220
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
221
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
222
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
223
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
224
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
225
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
226
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
227
+ "encoder.block.30.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
228
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
229
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
230
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
231
+ "encoder.block.30.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
232
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
233
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
234
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
235
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
236
+ "encoder.block.31.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
237
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00010-of-00010.safetensors",
238
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00010-of-00010.safetensors",
239
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00010-of-00010.safetensors",
240
+ "encoder.block.31.layer.1.layer_norm.weight": "model-00010-of-00010.safetensors",
241
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
242
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
243
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
244
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
245
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
246
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
247
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
248
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
249
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
250
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
251
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
252
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
253
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
254
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
255
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
256
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
257
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
258
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
259
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
260
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
261
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
262
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
263
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
264
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
265
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
266
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
267
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
268
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
269
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
270
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
271
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
272
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
273
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
274
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
275
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
276
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
277
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
278
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
279
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
280
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
281
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
282
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
283
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
284
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
285
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
286
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
287
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
288
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
289
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
290
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
291
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
292
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
293
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
294
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
295
+ "encoder.embed_tokens.weight": "model-00001-of-00010.safetensors",
296
+ "encoder.final_layer_norm.weight": "model-00010-of-00010.safetensors",
297
+ "shared.weight": "model-00001-of-00010.safetensors"
298
+ }
299
+ }