Hugging Face's logo

LewisThorpe
/
results

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
LewisThorpe commited on
Commit
1e223c6
·
verified ·
1 Parent(s): 9849547

Delete model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +0 -565
model.safetensors.index.json DELETED
@@ -1,565 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 5699514368
4
- },
5
- "weight_map": {
6
- "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
- "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
- "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
- "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
- "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
- "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
- "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
13
- "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
14
- "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
15
- "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
16
- "decoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
17
- "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
18
- "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
19
- "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
20
- "decoder.block.0.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
21
- "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
22
- "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
23
- "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
24
- "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
25
- "decoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
26
- "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
27
- "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
28
- "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
29
- "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
30
- "decoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
31
- "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
32
- "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
33
- "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
34
- "decoder.block.1.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
35
- "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
36
- "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
37
- "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
38
- "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
39
- "decoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
40
- "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
41
- "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
42
- "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
43
- "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
44
- "decoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
45
- "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
46
- "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
47
- "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
48
- "decoder.block.10.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
49
- "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
50
- "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
51
- "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
52
- "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
53
- "decoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
54
- "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
55
- "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
56
- "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
57
- "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
58
- "decoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
59
- "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
60
- "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
61
- "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
62
- "decoder.block.11.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
63
- "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
64
- "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
65
- "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
66
- "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
67
- "decoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
68
- "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
69
- "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
70
- "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
71
- "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
72
- "decoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
73
- "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
74
- "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
75
- "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
76
- "decoder.block.12.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
77
- "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
78
- "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
79
- "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
80
- "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
81
- "decoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
82
- "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
83
- "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
84
- "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
85
- "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
86
- "decoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
87
- "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
88
- "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
89
- "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
90
- "decoder.block.13.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
91
- "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
92
- "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
93
- "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
94
- "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
95
- "decoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
96
- "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
97
- "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
98
- "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
99
- "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
100
- "decoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
101
- "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
102
- "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
103
- "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
104
- "decoder.block.14.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
105
- "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
106
- "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
107
- "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
108
- "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
109
- "decoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
110
- "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
111
- "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
112
- "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
113
- "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
114
- "decoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
115
- "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
116
- "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
117
- "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
118
- "decoder.block.15.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
119
- "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
120
- "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
121
- "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
122
- "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
123
- "decoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
124
- "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
125
- "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
126
- "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
127
- "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
128
- "decoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
129
- "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
130
- "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
131
- "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
132
- "decoder.block.16.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
133
- "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
134
- "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
135
- "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
136
- "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
137
- "decoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
138
- "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
139
- "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
140
- "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
141
- "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
142
- "decoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
143
- "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
144
- "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
145
- "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
146
- "decoder.block.17.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
147
- "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
148
- "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
149
- "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
150
- "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
151
- "decoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
152
- "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
153
- "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
154
- "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
155
- "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
156
- "decoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
157
- "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
158
- "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
159
- "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
160
- "decoder.block.18.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
161
- "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
162
- "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
163
- "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
164
- "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
165
- "decoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
166
- "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
167
- "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
168
- "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
169
- "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
170
- "decoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
171
- "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
172
- "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
173
- "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
174
- "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
175
- "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
176
- "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
177
- "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
178
- "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
179
- "decoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
180
- "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
181
- "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
182
- "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
183
- "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
184
- "decoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
185
- "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
186
- "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
187
- "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
188
- "decoder.block.2.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
189
- "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
190
- "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
191
- "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
192
- "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
193
- "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
194
- "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
195
- "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
196
- "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
197
- "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
198
- "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
199
- "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
200
- "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
201
- "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
202
- "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
203
- "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
204
- "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
205
- "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
206
- "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
207
- "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
208
- "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
209
- "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
210
- "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
211
- "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
212
- "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
213
- "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
214
- "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
215
- "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
216
- "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
217
- "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
218
- "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
219
- "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
220
- "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
221
- "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
222
- "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
223
- "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
224
- "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
225
- "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
226
- "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
227
- "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
228
- "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
229
- "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
230
- "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
231
- "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
232
- "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
233
- "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
234
- "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
235
- "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
236
- "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
237
- "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
238
- "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
239
- "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
240
- "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
241
- "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
242
- "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
243
- "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
244
- "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
245
- "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
246
- "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
247
- "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
248
- "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
249
- "decoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
250
- "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
251
- "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
252
- "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
253
- "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
254
- "decoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
255
- "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
256
- "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
257
- "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
258
- "decoder.block.3.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
259
- "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
260
- "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
261
- "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
262
- "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
263
- "decoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
264
- "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
265
- "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
266
- "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
267
- "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
268
- "decoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
269
- "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
270
- "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
271
- "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
272
- "decoder.block.4.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
273
- "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
274
- "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
275
- "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
276
- "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
277
- "decoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
278
- "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
279
- "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
280
- "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
281
- "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
282
- "decoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
283
- "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
284
- "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
285
- "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
286
- "decoder.block.5.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
287
- "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
288
- "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
289
- "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
290
- "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
291
- "decoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
292
- "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
293
- "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
294
- "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
295
- "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
296
- "decoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
297
- "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
298
- "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
299
- "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
300
- "decoder.block.6.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
301
- "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
302
- "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
303
- "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
304
- "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
305
- "decoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
306
- "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
307
- "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
308
- "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
309
- "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
310
- "decoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
311
- "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
312
- "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
313
- "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
314
- "decoder.block.7.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
315
- "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
316
- "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
317
- "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
318
- "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
319
- "decoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
320
- "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
321
- "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
322
- "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
323
- "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
324
- "decoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
325
- "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
326
- "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
327
- "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
328
- "decoder.block.8.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
329
- "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
330
- "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
331
- "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
332
- "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
333
- "decoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
334
- "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
335
- "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
336
- "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
337
- "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
338
- "decoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
339
- "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
340
- "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
341
- "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
342
- "decoder.block.9.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
343
- "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
344
- "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
345
- "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
346
- "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
347
- "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
348
- "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
349
- "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
350
- "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
351
- "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
352
- "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
353
- "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
354
- "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
355
- "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
356
- "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
357
- "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
358
- "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
359
- "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
360
- "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
361
- "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
362
- "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
363
- "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
364
- "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
365
- "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
366
- "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
367
- "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
368
- "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
369
- "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
370
- "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
371
- "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
372
- "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
373
- "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
374
- "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
375
- "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
376
- "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
377
- "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
378
- "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
379
- "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
380
- "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
381
- "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
382
- "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
383
- "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
384
- "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
385
- "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
386
- "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
387
- "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
388
- "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
389
- "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
390
- "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
391
- "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
392
- "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
393
- "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
394
- "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
395
- "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
396
- "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
397
- "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
398
- "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
399
- "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
400
- "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
401
- "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
402
- "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
403
- "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
404
- "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
405
- "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
406
- "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
407
- "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
408
- "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
409
- "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
410
- "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
411
- "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
412
- "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
413
- "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
414
- "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
415
- "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
416
- "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
417
- "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
418
- "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
419
- "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
420
- "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
421
- "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
422
- "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
423
- "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
424
- "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
425
- "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
426
- "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
427
- "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
428
- "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
429
- "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
430
- "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
431
- "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
432
- "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
433
- "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
434
- "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
435
- "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
436
- "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
437
- "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
438
- "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
439
- "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
440
- "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
441
- "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
442
- "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
443
- "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
444
- "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
445
- "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
446
- "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
447
- "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
448
- "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
449
- "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
450
- "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
451
- "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
452
- "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
453
- "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
454
- "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
455
- "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
456
- "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
457
- "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
458
- "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
459
- "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
460
- "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
461
- "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
462
- "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
463
- "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
464
- "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
465
- "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
466
- "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
467
- "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
468
- "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
469
- "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
470
- "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
471
- "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
472
- "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
473
- "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
474
- "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
475
- "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
476
- "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
477
- "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
478
- "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
479
- "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
480
- "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
481
- "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
482
- "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
483
- "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
484
- "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
485
- "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
486
- "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
487
- "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
488
- "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
489
- "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
490
- "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
491
- "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
492
- "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
493
- "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
494
- "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
495
- "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
496
- "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
497
- "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
498
- "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
499
- "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
500
- "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
501
- "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
502
- "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
503
- "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
504
- "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
505
- "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
506
- "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
507
- "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
508
- "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
509
- "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
510
- "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
511
- "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
512
- "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
513
- "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
514
- "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
515
- "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
516
- "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
517
- "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
518
- "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
519
- "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
520
- "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
521
- "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
522
- "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
523
- "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
524
- "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
525
- "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
526
- "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
527
- "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
528
- "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
529
- "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
530
- "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
531
- "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
532
- "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
533
- "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
534
- "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
535
- "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
536
- "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
537
- "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
538
- "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
539
- "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
540
- "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
541
- "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
542
- "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
543
- "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
544
- "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
545
- "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
546
- "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
547
- "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
548
- "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
549
- "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
550
- "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
551
- "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
552
- "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
553
- "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
554
- "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
555
- "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
556
- "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
557
- "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
558
- "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
559
- "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
560
- "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
561
- "encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
562
- "lm_head.weight": "model-00002-of-00002.safetensors",
563
- "shared.weight": "model-00001-of-00002.safetensors"
564
- }
565
- }