Hugging Face's logo

warshakhan
/
pix2struct-large-docvqa-ISynHMP

Image-Text-to-Text
Transformers
PyTorch
pix2struct
Model card Files
xet
Community
1

Adding `safetensors` variant of this model

#1
by SFconvertbot - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+436
-0
Files changed (3) hide show
  1. model-00001-of-00002.safetensors +3 -0
  2. model-00002-of-00002.safetensors +3 -0
  3. model.safetensors.index.json +430 -0
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baba513859ab8c63ea793a1269905f3d8cb1b072a9167f55645890cb37c3d082
3
+ size 4987650872
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1047064e38349d57e2b6d294961586009d50011781274e6f35c4d49b0a8cfd9e
3
+ size 358109760
model.safetensors.index.json ADDED
@@ -0,0 +1,430 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5345707008
4
+ },
5
+ "weight_map": {
6
+ "decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
8
+ "decoder.layer.0.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
9
+ "decoder.layer.0.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
10
+ "decoder.layer.0.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
11
+ "decoder.layer.0.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
12
+ "decoder.layer.0.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
13
+ "decoder.layer.0.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
14
+ "decoder.layer.0.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
15
+ "decoder.layer.0.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
16
+ "decoder.layer.0.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
17
+ "decoder.layer.0.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
18
+ "decoder.layer.0.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
19
+ "decoder.layer.0.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
20
+ "decoder.layer.0.self_attention.attention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
21
+ "decoder.layer.0.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
22
+ "decoder.layer.0.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
23
+ "decoder.layer.1.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
24
+ "decoder.layer.1.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
25
+ "decoder.layer.1.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
26
+ "decoder.layer.1.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
27
+ "decoder.layer.1.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
28
+ "decoder.layer.1.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
29
+ "decoder.layer.1.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
30
+ "decoder.layer.1.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
31
+ "decoder.layer.1.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
32
+ "decoder.layer.1.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
33
+ "decoder.layer.1.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
34
+ "decoder.layer.1.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
35
+ "decoder.layer.1.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
36
+ "decoder.layer.1.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
37
+ "decoder.layer.10.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
38
+ "decoder.layer.10.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
39
+ "decoder.layer.10.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
40
+ "decoder.layer.10.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
41
+ "decoder.layer.10.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
42
+ "decoder.layer.10.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
43
+ "decoder.layer.10.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
44
+ "decoder.layer.10.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
45
+ "decoder.layer.10.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
46
+ "decoder.layer.10.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
47
+ "decoder.layer.10.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
48
+ "decoder.layer.10.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
49
+ "decoder.layer.10.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
50
+ "decoder.layer.10.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
51
+ "decoder.layer.11.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
52
+ "decoder.layer.11.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
53
+ "decoder.layer.11.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
54
+ "decoder.layer.11.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
55
+ "decoder.layer.11.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
56
+ "decoder.layer.11.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
57
+ "decoder.layer.11.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
58
+ "decoder.layer.11.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
59
+ "decoder.layer.11.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
60
+ "decoder.layer.11.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
61
+ "decoder.layer.11.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
62
+ "decoder.layer.11.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
63
+ "decoder.layer.11.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
64
+ "decoder.layer.11.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
65
+ "decoder.layer.12.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
66
+ "decoder.layer.12.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
67
+ "decoder.layer.12.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
68
+ "decoder.layer.12.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
69
+ "decoder.layer.12.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
70
+ "decoder.layer.12.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
71
+ "decoder.layer.12.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
72
+ "decoder.layer.12.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
73
+ "decoder.layer.12.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
74
+ "decoder.layer.12.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
75
+ "decoder.layer.12.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
76
+ "decoder.layer.12.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
77
+ "decoder.layer.12.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
78
+ "decoder.layer.12.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
79
+ "decoder.layer.13.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
80
+ "decoder.layer.13.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
81
+ "decoder.layer.13.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
82
+ "decoder.layer.13.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
83
+ "decoder.layer.13.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
84
+ "decoder.layer.13.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
85
+ "decoder.layer.13.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
86
+ "decoder.layer.13.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
87
+ "decoder.layer.13.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
88
+ "decoder.layer.13.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
89
+ "decoder.layer.13.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
90
+ "decoder.layer.13.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
91
+ "decoder.layer.13.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
92
+ "decoder.layer.13.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
93
+ "decoder.layer.14.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
94
+ "decoder.layer.14.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
95
+ "decoder.layer.14.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
96
+ "decoder.layer.14.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
97
+ "decoder.layer.14.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
98
+ "decoder.layer.14.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
99
+ "decoder.layer.14.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
100
+ "decoder.layer.14.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
101
+ "decoder.layer.14.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
102
+ "decoder.layer.14.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
103
+ "decoder.layer.14.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
104
+ "decoder.layer.14.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
105
+ "decoder.layer.14.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
106
+ "decoder.layer.14.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
107
+ "decoder.layer.15.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
108
+ "decoder.layer.15.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
109
+ "decoder.layer.15.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
110
+ "decoder.layer.15.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
111
+ "decoder.layer.15.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
112
+ "decoder.layer.15.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
113
+ "decoder.layer.15.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
114
+ "decoder.layer.15.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
115
+ "decoder.layer.15.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
116
+ "decoder.layer.15.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
117
+ "decoder.layer.15.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
118
+ "decoder.layer.15.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
119
+ "decoder.layer.15.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
120
+ "decoder.layer.15.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
121
+ "decoder.layer.16.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
122
+ "decoder.layer.16.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
123
+ "decoder.layer.16.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
124
+ "decoder.layer.16.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
125
+ "decoder.layer.16.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
126
+ "decoder.layer.16.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
127
+ "decoder.layer.16.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
128
+ "decoder.layer.16.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
129
+ "decoder.layer.16.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
130
+ "decoder.layer.16.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
131
+ "decoder.layer.16.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
132
+ "decoder.layer.16.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
133
+ "decoder.layer.16.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
134
+ "decoder.layer.16.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
135
+ "decoder.layer.17.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
136
+ "decoder.layer.17.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
137
+ "decoder.layer.17.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
138
+ "decoder.layer.17.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
139
+ "decoder.layer.17.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
140
+ "decoder.layer.17.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
141
+ "decoder.layer.17.mlp.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
142
+ "decoder.layer.17.mlp.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
143
+ "decoder.layer.17.mlp.layer_norm.weight": "model-00002-of-00002.safetensors",
144
+ "decoder.layer.17.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
145
+ "decoder.layer.17.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
146
+ "decoder.layer.17.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
147
+ "decoder.layer.17.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
148
+ "decoder.layer.17.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
149
+ "decoder.layer.2.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
150
+ "decoder.layer.2.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
151
+ "decoder.layer.2.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
152
+ "decoder.layer.2.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
153
+ "decoder.layer.2.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
154
+ "decoder.layer.2.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
155
+ "decoder.layer.2.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
156
+ "decoder.layer.2.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
157
+ "decoder.layer.2.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
158
+ "decoder.layer.2.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
159
+ "decoder.layer.2.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
160
+ "decoder.layer.2.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
161
+ "decoder.layer.2.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
162
+ "decoder.layer.2.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
163
+ "decoder.layer.3.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
164
+ "decoder.layer.3.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
165
+ "decoder.layer.3.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
166
+ "decoder.layer.3.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
167
+ "decoder.layer.3.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
168
+ "decoder.layer.3.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
169
+ "decoder.layer.3.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
170
+ "decoder.layer.3.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
171
+ "decoder.layer.3.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
172
+ "decoder.layer.3.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
173
+ "decoder.layer.3.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
174
+ "decoder.layer.3.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
175
+ "decoder.layer.3.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
176
+ "decoder.layer.3.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
177
+ "decoder.layer.4.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
178
+ "decoder.layer.4.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
179
+ "decoder.layer.4.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
180
+ "decoder.layer.4.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
181
+ "decoder.layer.4.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
182
+ "decoder.layer.4.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
183
+ "decoder.layer.4.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
184
+ "decoder.layer.4.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
185
+ "decoder.layer.4.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
186
+ "decoder.layer.4.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
187
+ "decoder.layer.4.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
188
+ "decoder.layer.4.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
189
+ "decoder.layer.4.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
190
+ "decoder.layer.4.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
191
+ "decoder.layer.5.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
192
+ "decoder.layer.5.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
193
+ "decoder.layer.5.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
194
+ "decoder.layer.5.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
195
+ "decoder.layer.5.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
196
+ "decoder.layer.5.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
197
+ "decoder.layer.5.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
198
+ "decoder.layer.5.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
199
+ "decoder.layer.5.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
200
+ "decoder.layer.5.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
201
+ "decoder.layer.5.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
202
+ "decoder.layer.5.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
203
+ "decoder.layer.5.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
204
+ "decoder.layer.5.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
205
+ "decoder.layer.6.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
206
+ "decoder.layer.6.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
207
+ "decoder.layer.6.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
208
+ "decoder.layer.6.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
209
+ "decoder.layer.6.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
210
+ "decoder.layer.6.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
211
+ "decoder.layer.6.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
212
+ "decoder.layer.6.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
213
+ "decoder.layer.6.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
214
+ "decoder.layer.6.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
215
+ "decoder.layer.6.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
216
+ "decoder.layer.6.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
217
+ "decoder.layer.6.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
218
+ "decoder.layer.6.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
219
+ "decoder.layer.7.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
220
+ "decoder.layer.7.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
221
+ "decoder.layer.7.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
222
+ "decoder.layer.7.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
223
+ "decoder.layer.7.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
224
+ "decoder.layer.7.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
225
+ "decoder.layer.7.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
226
+ "decoder.layer.7.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
227
+ "decoder.layer.7.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
228
+ "decoder.layer.7.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
229
+ "decoder.layer.7.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
230
+ "decoder.layer.7.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
231
+ "decoder.layer.7.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
232
+ "decoder.layer.7.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
233
+ "decoder.layer.8.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
234
+ "decoder.layer.8.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
235
+ "decoder.layer.8.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
236
+ "decoder.layer.8.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
237
+ "decoder.layer.8.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
238
+ "decoder.layer.8.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
239
+ "decoder.layer.8.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
240
+ "decoder.layer.8.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
241
+ "decoder.layer.8.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
242
+ "decoder.layer.8.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
243
+ "decoder.layer.8.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
244
+ "decoder.layer.8.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
245
+ "decoder.layer.8.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
246
+ "decoder.layer.8.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
247
+ "decoder.layer.9.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors",
248
+ "decoder.layer.9.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors",
249
+ "decoder.layer.9.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors",
250
+ "decoder.layer.9.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors",
251
+ "decoder.layer.9.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
252
+ "decoder.layer.9.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
253
+ "decoder.layer.9.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
254
+ "decoder.layer.9.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
255
+ "decoder.layer.9.mlp.layer_norm.weight": "model-00001-of-00002.safetensors",
256
+ "decoder.layer.9.self_attention.attention.key.weight": "model-00001-of-00002.safetensors",
257
+ "decoder.layer.9.self_attention.attention.output.weight": "model-00001-of-00002.safetensors",
258
+ "decoder.layer.9.self_attention.attention.query.weight": "model-00001-of-00002.safetensors",
259
+ "decoder.layer.9.self_attention.attention.value.weight": "model-00001-of-00002.safetensors",
260
+ "decoder.layer.9.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors",
261
+ "decoder.lm_head.weight": "model-00002-of-00002.safetensors",
262
+ "encoder.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors",
263
+ "encoder.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors",
264
+ "encoder.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors",
265
+ "encoder.embeddings.row_embedder.weight": "model-00001-of-00002.safetensors",
266
+ "encoder.encoder.layer.0.attention.key.weight": "model-00001-of-00002.safetensors",
267
+ "encoder.encoder.layer.0.attention.output.weight": "model-00001-of-00002.safetensors",
268
+ "encoder.encoder.layer.0.attention.query.weight": "model-00001-of-00002.safetensors",
269
+ "encoder.encoder.layer.0.attention.value.weight": "model-00001-of-00002.safetensors",
270
+ "encoder.encoder.layer.0.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
271
+ "encoder.encoder.layer.0.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
272
+ "encoder.encoder.layer.0.mlp.wo.weight": "model-00001-of-00002.safetensors",
273
+ "encoder.encoder.layer.0.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
274
+ "encoder.encoder.layer.0.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
275
+ "encoder.encoder.layer.1.attention.key.weight": "model-00001-of-00002.safetensors",
276
+ "encoder.encoder.layer.1.attention.output.weight": "model-00001-of-00002.safetensors",
277
+ "encoder.encoder.layer.1.attention.query.weight": "model-00001-of-00002.safetensors",
278
+ "encoder.encoder.layer.1.attention.value.weight": "model-00001-of-00002.safetensors",
279
+ "encoder.encoder.layer.1.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
280
+ "encoder.encoder.layer.1.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
281
+ "encoder.encoder.layer.1.mlp.wo.weight": "model-00001-of-00002.safetensors",
282
+ "encoder.encoder.layer.1.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
283
+ "encoder.encoder.layer.1.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
284
+ "encoder.encoder.layer.10.attention.key.weight": "model-00001-of-00002.safetensors",
285
+ "encoder.encoder.layer.10.attention.output.weight": "model-00001-of-00002.safetensors",
286
+ "encoder.encoder.layer.10.attention.query.weight": "model-00001-of-00002.safetensors",
287
+ "encoder.encoder.layer.10.attention.value.weight": "model-00001-of-00002.safetensors",
288
+ "encoder.encoder.layer.10.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
289
+ "encoder.encoder.layer.10.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
290
+ "encoder.encoder.layer.10.mlp.wo.weight": "model-00001-of-00002.safetensors",
291
+ "encoder.encoder.layer.10.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
292
+ "encoder.encoder.layer.10.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
293
+ "encoder.encoder.layer.11.attention.key.weight": "model-00001-of-00002.safetensors",
294
+ "encoder.encoder.layer.11.attention.output.weight": "model-00001-of-00002.safetensors",
295
+ "encoder.encoder.layer.11.attention.query.weight": "model-00001-of-00002.safetensors",
296
+ "encoder.encoder.layer.11.attention.value.weight": "model-00001-of-00002.safetensors",
297
+ "encoder.encoder.layer.11.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
298
+ "encoder.encoder.layer.11.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
299
+ "encoder.encoder.layer.11.mlp.wo.weight": "model-00001-of-00002.safetensors",
300
+ "encoder.encoder.layer.11.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
301
+ "encoder.encoder.layer.11.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
302
+ "encoder.encoder.layer.12.attention.key.weight": "model-00001-of-00002.safetensors",
303
+ "encoder.encoder.layer.12.attention.output.weight": "model-00001-of-00002.safetensors",
304
+ "encoder.encoder.layer.12.attention.query.weight": "model-00001-of-00002.safetensors",
305
+ "encoder.encoder.layer.12.attention.value.weight": "model-00001-of-00002.safetensors",
306
+ "encoder.encoder.layer.12.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
307
+ "encoder.encoder.layer.12.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
308
+ "encoder.encoder.layer.12.mlp.wo.weight": "model-00001-of-00002.safetensors",
309
+ "encoder.encoder.layer.12.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
310
+ "encoder.encoder.layer.12.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
311
+ "encoder.encoder.layer.13.attention.key.weight": "model-00001-of-00002.safetensors",
312
+ "encoder.encoder.layer.13.attention.output.weight": "model-00001-of-00002.safetensors",
313
+ "encoder.encoder.layer.13.attention.query.weight": "model-00001-of-00002.safetensors",
314
+ "encoder.encoder.layer.13.attention.value.weight": "model-00001-of-00002.safetensors",
315
+ "encoder.encoder.layer.13.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
316
+ "encoder.encoder.layer.13.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
317
+ "encoder.encoder.layer.13.mlp.wo.weight": "model-00001-of-00002.safetensors",
318
+ "encoder.encoder.layer.13.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
319
+ "encoder.encoder.layer.13.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
320
+ "encoder.encoder.layer.14.attention.key.weight": "model-00001-of-00002.safetensors",
321
+ "encoder.encoder.layer.14.attention.output.weight": "model-00001-of-00002.safetensors",
322
+ "encoder.encoder.layer.14.attention.query.weight": "model-00001-of-00002.safetensors",
323
+ "encoder.encoder.layer.14.attention.value.weight": "model-00001-of-00002.safetensors",
324
+ "encoder.encoder.layer.14.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
325
+ "encoder.encoder.layer.14.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
326
+ "encoder.encoder.layer.14.mlp.wo.weight": "model-00001-of-00002.safetensors",
327
+ "encoder.encoder.layer.14.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
328
+ "encoder.encoder.layer.14.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
329
+ "encoder.encoder.layer.15.attention.key.weight": "model-00001-of-00002.safetensors",
330
+ "encoder.encoder.layer.15.attention.output.weight": "model-00001-of-00002.safetensors",
331
+ "encoder.encoder.layer.15.attention.query.weight": "model-00001-of-00002.safetensors",
332
+ "encoder.encoder.layer.15.attention.value.weight": "model-00001-of-00002.safetensors",
333
+ "encoder.encoder.layer.15.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
334
+ "encoder.encoder.layer.15.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
335
+ "encoder.encoder.layer.15.mlp.wo.weight": "model-00001-of-00002.safetensors",
336
+ "encoder.encoder.layer.15.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
337
+ "encoder.encoder.layer.15.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
338
+ "encoder.encoder.layer.16.attention.key.weight": "model-00001-of-00002.safetensors",
339
+ "encoder.encoder.layer.16.attention.output.weight": "model-00001-of-00002.safetensors",
340
+ "encoder.encoder.layer.16.attention.query.weight": "model-00001-of-00002.safetensors",
341
+ "encoder.encoder.layer.16.attention.value.weight": "model-00001-of-00002.safetensors",
342
+ "encoder.encoder.layer.16.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
343
+ "encoder.encoder.layer.16.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
344
+ "encoder.encoder.layer.16.mlp.wo.weight": "model-00001-of-00002.safetensors",
345
+ "encoder.encoder.layer.16.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
346
+ "encoder.encoder.layer.16.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
347
+ "encoder.encoder.layer.17.attention.key.weight": "model-00001-of-00002.safetensors",
348
+ "encoder.encoder.layer.17.attention.output.weight": "model-00001-of-00002.safetensors",
349
+ "encoder.encoder.layer.17.attention.query.weight": "model-00001-of-00002.safetensors",
350
+ "encoder.encoder.layer.17.attention.value.weight": "model-00001-of-00002.safetensors",
351
+ "encoder.encoder.layer.17.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
352
+ "encoder.encoder.layer.17.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
353
+ "encoder.encoder.layer.17.mlp.wo.weight": "model-00001-of-00002.safetensors",
354
+ "encoder.encoder.layer.17.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
355
+ "encoder.encoder.layer.17.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
356
+ "encoder.encoder.layer.2.attention.key.weight": "model-00001-of-00002.safetensors",
357
+ "encoder.encoder.layer.2.attention.output.weight": "model-00001-of-00002.safetensors",
358
+ "encoder.encoder.layer.2.attention.query.weight": "model-00001-of-00002.safetensors",
359
+ "encoder.encoder.layer.2.attention.value.weight": "model-00001-of-00002.safetensors",
360
+ "encoder.encoder.layer.2.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
361
+ "encoder.encoder.layer.2.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
362
+ "encoder.encoder.layer.2.mlp.wo.weight": "model-00001-of-00002.safetensors",
363
+ "encoder.encoder.layer.2.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
364
+ "encoder.encoder.layer.2.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
365
+ "encoder.encoder.layer.3.attention.key.weight": "model-00001-of-00002.safetensors",
366
+ "encoder.encoder.layer.3.attention.output.weight": "model-00001-of-00002.safetensors",
367
+ "encoder.encoder.layer.3.attention.query.weight": "model-00001-of-00002.safetensors",
368
+ "encoder.encoder.layer.3.attention.value.weight": "model-00001-of-00002.safetensors",
369
+ "encoder.encoder.layer.3.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
370
+ "encoder.encoder.layer.3.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
371
+ "encoder.encoder.layer.3.mlp.wo.weight": "model-00001-of-00002.safetensors",
372
+ "encoder.encoder.layer.3.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
373
+ "encoder.encoder.layer.3.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
374
+ "encoder.encoder.layer.4.attention.key.weight": "model-00001-of-00002.safetensors",
375
+ "encoder.encoder.layer.4.attention.output.weight": "model-00001-of-00002.safetensors",
376
+ "encoder.encoder.layer.4.attention.query.weight": "model-00001-of-00002.safetensors",
377
+ "encoder.encoder.layer.4.attention.value.weight": "model-00001-of-00002.safetensors",
378
+ "encoder.encoder.layer.4.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
379
+ "encoder.encoder.layer.4.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
380
+ "encoder.encoder.layer.4.mlp.wo.weight": "model-00001-of-00002.safetensors",
381
+ "encoder.encoder.layer.4.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
382
+ "encoder.encoder.layer.4.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
383
+ "encoder.encoder.layer.5.attention.key.weight": "model-00001-of-00002.safetensors",
384
+ "encoder.encoder.layer.5.attention.output.weight": "model-00001-of-00002.safetensors",
385
+ "encoder.encoder.layer.5.attention.query.weight": "model-00001-of-00002.safetensors",
386
+ "encoder.encoder.layer.5.attention.value.weight": "model-00001-of-00002.safetensors",
387
+ "encoder.encoder.layer.5.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
388
+ "encoder.encoder.layer.5.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
389
+ "encoder.encoder.layer.5.mlp.wo.weight": "model-00001-of-00002.safetensors",
390
+ "encoder.encoder.layer.5.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
391
+ "encoder.encoder.layer.5.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
392
+ "encoder.encoder.layer.6.attention.key.weight": "model-00001-of-00002.safetensors",
393
+ "encoder.encoder.layer.6.attention.output.weight": "model-00001-of-00002.safetensors",
394
+ "encoder.encoder.layer.6.attention.query.weight": "model-00001-of-00002.safetensors",
395
+ "encoder.encoder.layer.6.attention.value.weight": "model-00001-of-00002.safetensors",
396
+ "encoder.encoder.layer.6.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
397
+ "encoder.encoder.layer.6.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
398
+ "encoder.encoder.layer.6.mlp.wo.weight": "model-00001-of-00002.safetensors",
399
+ "encoder.encoder.layer.6.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
400
+ "encoder.encoder.layer.6.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
401
+ "encoder.encoder.layer.7.attention.key.weight": "model-00001-of-00002.safetensors",
402
+ "encoder.encoder.layer.7.attention.output.weight": "model-00001-of-00002.safetensors",
403
+ "encoder.encoder.layer.7.attention.query.weight": "model-00001-of-00002.safetensors",
404
+ "encoder.encoder.layer.7.attention.value.weight": "model-00001-of-00002.safetensors",
405
+ "encoder.encoder.layer.7.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
406
+ "encoder.encoder.layer.7.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
407
+ "encoder.encoder.layer.7.mlp.wo.weight": "model-00001-of-00002.safetensors",
408
+ "encoder.encoder.layer.7.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
409
+ "encoder.encoder.layer.7.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
410
+ "encoder.encoder.layer.8.attention.key.weight": "model-00001-of-00002.safetensors",
411
+ "encoder.encoder.layer.8.attention.output.weight": "model-00001-of-00002.safetensors",
412
+ "encoder.encoder.layer.8.attention.query.weight": "model-00001-of-00002.safetensors",
413
+ "encoder.encoder.layer.8.attention.value.weight": "model-00001-of-00002.safetensors",
414
+ "encoder.encoder.layer.8.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
415
+ "encoder.encoder.layer.8.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
416
+ "encoder.encoder.layer.8.mlp.wo.weight": "model-00001-of-00002.safetensors",
417
+ "encoder.encoder.layer.8.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
418
+ "encoder.encoder.layer.8.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
419
+ "encoder.encoder.layer.9.attention.key.weight": "model-00001-of-00002.safetensors",
420
+ "encoder.encoder.layer.9.attention.output.weight": "model-00001-of-00002.safetensors",
421
+ "encoder.encoder.layer.9.attention.query.weight": "model-00001-of-00002.safetensors",
422
+ "encoder.encoder.layer.9.attention.value.weight": "model-00001-of-00002.safetensors",
423
+ "encoder.encoder.layer.9.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
424
+ "encoder.encoder.layer.9.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
425
+ "encoder.encoder.layer.9.mlp.wo.weight": "model-00001-of-00002.safetensors",
426
+ "encoder.encoder.layer.9.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
427
+ "encoder.encoder.layer.9.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
428
+ "encoder.layernorm.weight": "model-00001-of-00002.safetensors"
429
+ }
430
+ }