Hugging Face's logo

Synthyra
/
ANKH3_xl

Fill-Mask
Transformers
Safetensors
fast_ankh
protein language model
biology
custom_code
Model card Files
xet
 Community
lhallee commited on
Commit
ba57c45
·
verified ·
1 Parent(s): 528b869

Upload FastAnkhForMaskedLM

Browse files
Files changed (5) hide show
  1. config.json +4 -0
  2. model-00001-of-00003.safetensors +2 -2
  3. model-00002-of-00003.safetensors +2 -2
  4. model-00003-of-00003.safetensors +2 -2
  5. model.safetensors.index.json +439 -438
config.json CHANGED
@@ -1,4 +1,7 @@
1
  {
 
 
 
2
  "attn_backend": "sdpa",
3
  "auto_map": {
4
  "AutoConfig": "modeling_ankh.FastAnkhConfig",
@@ -11,6 +14,7 @@
11
  "d_kv": 64,
12
  "d_model": 2560,
13
  "dense_act_fn": "silu",
 
14
  "eos_token_id": 1,
15
  "initializer_factor": 1.0,
16
  "layer_norm_epsilon": 1e-06,
 
1
  {
2
+ "architectures": [
3
+ "FastAnkhForMaskedLM"
4
+ ],
5
  "attn_backend": "sdpa",
6
  "auto_map": {
7
  "AutoConfig": "modeling_ankh.FastAnkhConfig",
 
14
  "d_kv": 64,
15
  "d_model": 2560,
16
  "dense_act_fn": "silu",
17
+ "dtype": "float32",
18
  "eos_token_id": 1,
19
  "initializer_factor": 1.0,
20
  "layer_norm_epsilon": 1e-06,
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e1fdaed6f5c0f349a044a8e6d63281a2b0c80e5a4c8e503477d1d1930adaad
3
- size 4980455024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39bd8f75cf98a67cf04055399f9fc401198f6fc2896b112aba9fd9ec9df52ab9
3
+ size 4983077840
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad4004aecbeb5fdaa304ecaf01ec1db9e2d05f3f008fd767fdd0eb96483f0f25
3
- size 4977835616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff73233b39d2c200abb78e66b320c014ec61431bd6e1af36fb188a3cfa24c34
3
+ size 4977836888
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8c5904212d0184746e0a39ec5c7a22180dffb58d98385eba2fef4fca2fdbf0
3
- size 3983578952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13125c02dbcd7f07bd412e9e085f2bca6624d2f1f45fedc95fb777f53161cbe
3
+ size 3983579968
model.safetensors.index.json CHANGED
@@ -1,444 +1,445 @@
1
  {
2
  "metadata": {
3
- "total_parameters": 3485454848,
4
- "total_size": 13941819392
5
  },
6
  "weight_map": {
7
- "ankh.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "ankh.encoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
9
- "ankh.encoder.layer.0.attention.k.weight": "model-00001-of-00003.safetensors",
10
- "ankh.encoder.layer.0.attention.o.weight": "model-00001-of-00003.safetensors",
11
- "ankh.encoder.layer.0.attention.q.weight": "model-00001-of-00003.safetensors",
12
- "ankh.encoder.layer.0.attention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
13
- "ankh.encoder.layer.0.attention.v.weight": "model-00001-of-00003.safetensors",
14
- "ankh.encoder.layer.0.attention_norm.weight": "model-00001-of-00003.safetensors",
15
- "ankh.encoder.layer.0.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
16
- "ankh.encoder.layer.0.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
17
- "ankh.encoder.layer.0.ffn.wo.weight": "model-00001-of-00003.safetensors",
18
- "ankh.encoder.layer.0.ffn_norm.weight": "model-00001-of-00003.safetensors",
19
- "ankh.encoder.layer.1.attention.k.weight": "model-00001-of-00003.safetensors",
20
- "ankh.encoder.layer.1.attention.o.weight": "model-00001-of-00003.safetensors",
21
- "ankh.encoder.layer.1.attention.q.weight": "model-00001-of-00003.safetensors",
22
- "ankh.encoder.layer.1.attention.v.weight": "model-00001-of-00003.safetensors",
23
- "ankh.encoder.layer.1.attention_norm.weight": "model-00001-of-00003.safetensors",
24
- "ankh.encoder.layer.1.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
25
- "ankh.encoder.layer.1.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
26
- "ankh.encoder.layer.1.ffn.wo.weight": "model-00001-of-00003.safetensors",
27
- "ankh.encoder.layer.1.ffn_norm.weight": "model-00001-of-00003.safetensors",
28
- "ankh.encoder.layer.10.attention.k.weight": "model-00001-of-00003.safetensors",
29
- "ankh.encoder.layer.10.attention.o.weight": "model-00001-of-00003.safetensors",
30
- "ankh.encoder.layer.10.attention.q.weight": "model-00001-of-00003.safetensors",
31
- "ankh.encoder.layer.10.attention.v.weight": "model-00001-of-00003.safetensors",
32
- "ankh.encoder.layer.10.attention_norm.weight": "model-00001-of-00003.safetensors",
33
- "ankh.encoder.layer.10.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
34
- "ankh.encoder.layer.10.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
35
- "ankh.encoder.layer.10.ffn.wo.weight": "model-00001-of-00003.safetensors",
36
- "ankh.encoder.layer.10.ffn_norm.weight": "model-00001-of-00003.safetensors",
37
- "ankh.encoder.layer.11.attention.k.weight": "model-00001-of-00003.safetensors",
38
- "ankh.encoder.layer.11.attention.o.weight": "model-00001-of-00003.safetensors",
39
- "ankh.encoder.layer.11.attention.q.weight": "model-00001-of-00003.safetensors",
40
- "ankh.encoder.layer.11.attention.v.weight": "model-00001-of-00003.safetensors",
41
- "ankh.encoder.layer.11.attention_norm.weight": "model-00001-of-00003.safetensors",
42
- "ankh.encoder.layer.11.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
43
- "ankh.encoder.layer.11.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
44
- "ankh.encoder.layer.11.ffn.wo.weight": "model-00001-of-00003.safetensors",
45
- "ankh.encoder.layer.11.ffn_norm.weight": "model-00001-of-00003.safetensors",
46
- "ankh.encoder.layer.12.attention.k.weight": "model-00001-of-00003.safetensors",
47
- "ankh.encoder.layer.12.attention.o.weight": "model-00001-of-00003.safetensors",
48
- "ankh.encoder.layer.12.attention.q.weight": "model-00001-of-00003.safetensors",
49
- "ankh.encoder.layer.12.attention.v.weight": "model-00001-of-00003.safetensors",
50
- "ankh.encoder.layer.12.attention_norm.weight": "model-00001-of-00003.safetensors",
51
- "ankh.encoder.layer.12.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
52
- "ankh.encoder.layer.12.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
53
- "ankh.encoder.layer.12.ffn.wo.weight": "model-00001-of-00003.safetensors",
54
- "ankh.encoder.layer.12.ffn_norm.weight": "model-00001-of-00003.safetensors",
55
- "ankh.encoder.layer.13.attention.k.weight": "model-00001-of-00003.safetensors",
56
- "ankh.encoder.layer.13.attention.o.weight": "model-00001-of-00003.safetensors",
57
- "ankh.encoder.layer.13.attention.q.weight": "model-00001-of-00003.safetensors",
58
- "ankh.encoder.layer.13.attention.v.weight": "model-00001-of-00003.safetensors",
59
- "ankh.encoder.layer.13.attention_norm.weight": "model-00001-of-00003.safetensors",
60
- "ankh.encoder.layer.13.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
61
- "ankh.encoder.layer.13.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
62
- "ankh.encoder.layer.13.ffn.wo.weight": "model-00001-of-00003.safetensors",
63
- "ankh.encoder.layer.13.ffn_norm.weight": "model-00001-of-00003.safetensors",
64
- "ankh.encoder.layer.14.attention.k.weight": "model-00001-of-00003.safetensors",
65
- "ankh.encoder.layer.14.attention.o.weight": "model-00001-of-00003.safetensors",
66
- "ankh.encoder.layer.14.attention.q.weight": "model-00001-of-00003.safetensors",
67
- "ankh.encoder.layer.14.attention.v.weight": "model-00001-of-00003.safetensors",
68
- "ankh.encoder.layer.14.attention_norm.weight": "model-00001-of-00003.safetensors",
69
- "ankh.encoder.layer.14.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
70
- "ankh.encoder.layer.14.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
71
- "ankh.encoder.layer.14.ffn.wo.weight": "model-00001-of-00003.safetensors",
72
- "ankh.encoder.layer.14.ffn_norm.weight": "model-00001-of-00003.safetensors",
73
- "ankh.encoder.layer.15.attention.k.weight": "model-00001-of-00003.safetensors",
74
- "ankh.encoder.layer.15.attention.o.weight": "model-00001-of-00003.safetensors",
75
- "ankh.encoder.layer.15.attention.q.weight": "model-00001-of-00003.safetensors",
76
- "ankh.encoder.layer.15.attention.v.weight": "model-00001-of-00003.safetensors",
77
- "ankh.encoder.layer.15.attention_norm.weight": "model-00001-of-00003.safetensors",
78
- "ankh.encoder.layer.15.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
79
- "ankh.encoder.layer.15.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
80
- "ankh.encoder.layer.15.ffn.wo.weight": "model-00001-of-00003.safetensors",
81
- "ankh.encoder.layer.15.ffn_norm.weight": "model-00001-of-00003.safetensors",
82
- "ankh.encoder.layer.16.attention.k.weight": "model-00001-of-00003.safetensors",
83
- "ankh.encoder.layer.16.attention.o.weight": "model-00001-of-00003.safetensors",
84
- "ankh.encoder.layer.16.attention.q.weight": "model-00001-of-00003.safetensors",
85
- "ankh.encoder.layer.16.attention.v.weight": "model-00001-of-00003.safetensors",
86
- "ankh.encoder.layer.16.attention_norm.weight": "model-00001-of-00003.safetensors",
87
- "ankh.encoder.layer.16.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
88
- "ankh.encoder.layer.16.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
89
- "ankh.encoder.layer.16.ffn.wo.weight": "model-00001-of-00003.safetensors",
90
- "ankh.encoder.layer.16.ffn_norm.weight": "model-00001-of-00003.safetensors",
91
- "ankh.encoder.layer.17.attention.k.weight": "model-00001-of-00003.safetensors",
92
- "ankh.encoder.layer.17.attention.o.weight": "model-00002-of-00003.safetensors",
93
- "ankh.encoder.layer.17.attention.q.weight": "model-00001-of-00003.safetensors",
94
- "ankh.encoder.layer.17.attention.v.weight": "model-00002-of-00003.safetensors",
95
- "ankh.encoder.layer.17.attention_norm.weight": "model-00002-of-00003.safetensors",
96
- "ankh.encoder.layer.17.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
97
- "ankh.encoder.layer.17.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
98
- "ankh.encoder.layer.17.ffn.wo.weight": "model-00002-of-00003.safetensors",
99
- "ankh.encoder.layer.17.ffn_norm.weight": "model-00002-of-00003.safetensors",
100
- "ankh.encoder.layer.18.attention.k.weight": "model-00002-of-00003.safetensors",
101
- "ankh.encoder.layer.18.attention.o.weight": "model-00002-of-00003.safetensors",
102
- "ankh.encoder.layer.18.attention.q.weight": "model-00002-of-00003.safetensors",
103
- "ankh.encoder.layer.18.attention.v.weight": "model-00002-of-00003.safetensors",
104
- "ankh.encoder.layer.18.attention_norm.weight": "model-00002-of-00003.safetensors",
105
- "ankh.encoder.layer.18.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
106
- "ankh.encoder.layer.18.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
107
- "ankh.encoder.layer.18.ffn.wo.weight": "model-00002-of-00003.safetensors",
108
- "ankh.encoder.layer.18.ffn_norm.weight": "model-00002-of-00003.safetensors",
109
- "ankh.encoder.layer.19.attention.k.weight": "model-00002-of-00003.safetensors",
110
- "ankh.encoder.layer.19.attention.o.weight": "model-00002-of-00003.safetensors",
111
- "ankh.encoder.layer.19.attention.q.weight": "model-00002-of-00003.safetensors",
112
- "ankh.encoder.layer.19.attention.v.weight": "model-00002-of-00003.safetensors",
113
- "ankh.encoder.layer.19.attention_norm.weight": "model-00002-of-00003.safetensors",
114
- "ankh.encoder.layer.19.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
115
- "ankh.encoder.layer.19.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
116
- "ankh.encoder.layer.19.ffn.wo.weight": "model-00002-of-00003.safetensors",
117
- "ankh.encoder.layer.19.ffn_norm.weight": "model-00002-of-00003.safetensors",
118
- "ankh.encoder.layer.2.attention.k.weight": "model-00001-of-00003.safetensors",
119
- "ankh.encoder.layer.2.attention.o.weight": "model-00001-of-00003.safetensors",
120
- "ankh.encoder.layer.2.attention.q.weight": "model-00001-of-00003.safetensors",
121
- "ankh.encoder.layer.2.attention.v.weight": "model-00001-of-00003.safetensors",
122
- "ankh.encoder.layer.2.attention_norm.weight": "model-00001-of-00003.safetensors",
123
- "ankh.encoder.layer.2.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
124
- "ankh.encoder.layer.2.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
125
- "ankh.encoder.layer.2.ffn.wo.weight": "model-00001-of-00003.safetensors",
126
- "ankh.encoder.layer.2.ffn_norm.weight": "model-00001-of-00003.safetensors",
127
- "ankh.encoder.layer.20.attention.k.weight": "model-00002-of-00003.safetensors",
128
- "ankh.encoder.layer.20.attention.o.weight": "model-00002-of-00003.safetensors",
129
- "ankh.encoder.layer.20.attention.q.weight": "model-00002-of-00003.safetensors",
130
- "ankh.encoder.layer.20.attention.v.weight": "model-00002-of-00003.safetensors",
131
- "ankh.encoder.layer.20.attention_norm.weight": "model-00002-of-00003.safetensors",
132
- "ankh.encoder.layer.20.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
133
- "ankh.encoder.layer.20.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
134
- "ankh.encoder.layer.20.ffn.wo.weight": "model-00002-of-00003.safetensors",
135
- "ankh.encoder.layer.20.ffn_norm.weight": "model-00002-of-00003.safetensors",
136
- "ankh.encoder.layer.21.attention.k.weight": "model-00002-of-00003.safetensors",
137
- "ankh.encoder.layer.21.attention.o.weight": "model-00002-of-00003.safetensors",
138
- "ankh.encoder.layer.21.attention.q.weight": "model-00002-of-00003.safetensors",
139
- "ankh.encoder.layer.21.attention.v.weight": "model-00002-of-00003.safetensors",
140
- "ankh.encoder.layer.21.attention_norm.weight": "model-00002-of-00003.safetensors",
141
- "ankh.encoder.layer.21.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
142
- "ankh.encoder.layer.21.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
143
- "ankh.encoder.layer.21.ffn.wo.weight": "model-00002-of-00003.safetensors",
144
- "ankh.encoder.layer.21.ffn_norm.weight": "model-00002-of-00003.safetensors",
145
- "ankh.encoder.layer.22.attention.k.weight": "model-00002-of-00003.safetensors",
146
- "ankh.encoder.layer.22.attention.o.weight": "model-00002-of-00003.safetensors",
147
- "ankh.encoder.layer.22.attention.q.weight": "model-00002-of-00003.safetensors",
148
- "ankh.encoder.layer.22.attention.v.weight": "model-00002-of-00003.safetensors",
149
- "ankh.encoder.layer.22.attention_norm.weight": "model-00002-of-00003.safetensors",
150
- "ankh.encoder.layer.22.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
151
- "ankh.encoder.layer.22.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
152
- "ankh.encoder.layer.22.ffn.wo.weight": "model-00002-of-00003.safetensors",
153
- "ankh.encoder.layer.22.ffn_norm.weight": "model-00002-of-00003.safetensors",
154
- "ankh.encoder.layer.23.attention.k.weight": "model-00002-of-00003.safetensors",
155
- "ankh.encoder.layer.23.attention.o.weight": "model-00002-of-00003.safetensors",
156
- "ankh.encoder.layer.23.attention.q.weight": "model-00002-of-00003.safetensors",
157
- "ankh.encoder.layer.23.attention.v.weight": "model-00002-of-00003.safetensors",
158
- "ankh.encoder.layer.23.attention_norm.weight": "model-00002-of-00003.safetensors",
159
- "ankh.encoder.layer.23.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
160
- "ankh.encoder.layer.23.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
161
- "ankh.encoder.layer.23.ffn.wo.weight": "model-00002-of-00003.safetensors",
162
- "ankh.encoder.layer.23.ffn_norm.weight": "model-00002-of-00003.safetensors",
163
- "ankh.encoder.layer.24.attention.k.weight": "model-00002-of-00003.safetensors",
164
- "ankh.encoder.layer.24.attention.o.weight": "model-00002-of-00003.safetensors",
165
- "ankh.encoder.layer.24.attention.q.weight": "model-00002-of-00003.safetensors",
166
- "ankh.encoder.layer.24.attention.v.weight": "model-00002-of-00003.safetensors",
167
- "ankh.encoder.layer.24.attention_norm.weight": "model-00002-of-00003.safetensors",
168
- "ankh.encoder.layer.24.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
169
- "ankh.encoder.layer.24.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
170
- "ankh.encoder.layer.24.ffn.wo.weight": "model-00002-of-00003.safetensors",
171
- "ankh.encoder.layer.24.ffn_norm.weight": "model-00002-of-00003.safetensors",
172
- "ankh.encoder.layer.25.attention.k.weight": "model-00002-of-00003.safetensors",
173
- "ankh.encoder.layer.25.attention.o.weight": "model-00002-of-00003.safetensors",
174
- "ankh.encoder.layer.25.attention.q.weight": "model-00002-of-00003.safetensors",
175
- "ankh.encoder.layer.25.attention.v.weight": "model-00002-of-00003.safetensors",
176
- "ankh.encoder.layer.25.attention_norm.weight": "model-00002-of-00003.safetensors",
177
- "ankh.encoder.layer.25.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
178
- "ankh.encoder.layer.25.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
179
- "ankh.encoder.layer.25.ffn.wo.weight": "model-00002-of-00003.safetensors",
180
- "ankh.encoder.layer.25.ffn_norm.weight": "model-00002-of-00003.safetensors",
181
- "ankh.encoder.layer.26.attention.k.weight": "model-00002-of-00003.safetensors",
182
- "ankh.encoder.layer.26.attention.o.weight": "model-00002-of-00003.safetensors",
183
- "ankh.encoder.layer.26.attention.q.weight": "model-00002-of-00003.safetensors",
184
- "ankh.encoder.layer.26.attention.v.weight": "model-00002-of-00003.safetensors",
185
- "ankh.encoder.layer.26.attention_norm.weight": "model-00002-of-00003.safetensors",
186
- "ankh.encoder.layer.26.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
187
- "ankh.encoder.layer.26.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
188
- "ankh.encoder.layer.26.ffn.wo.weight": "model-00002-of-00003.safetensors",
189
- "ankh.encoder.layer.26.ffn_norm.weight": "model-00002-of-00003.safetensors",
190
- "ankh.encoder.layer.27.attention.k.weight": "model-00002-of-00003.safetensors",
191
- "ankh.encoder.layer.27.attention.o.weight": "model-00002-of-00003.safetensors",
192
- "ankh.encoder.layer.27.attention.q.weight": "model-00002-of-00003.safetensors",
193
- "ankh.encoder.layer.27.attention.v.weight": "model-00002-of-00003.safetensors",
194
- "ankh.encoder.layer.27.attention_norm.weight": "model-00002-of-00003.safetensors",
195
- "ankh.encoder.layer.27.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
196
- "ankh.encoder.layer.27.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
197
- "ankh.encoder.layer.27.ffn.wo.weight": "model-00002-of-00003.safetensors",
198
- "ankh.encoder.layer.27.ffn_norm.weight": "model-00002-of-00003.safetensors",
199
- "ankh.encoder.layer.28.attention.k.weight": "model-00002-of-00003.safetensors",
200
- "ankh.encoder.layer.28.attention.o.weight": "model-00002-of-00003.safetensors",
201
- "ankh.encoder.layer.28.attention.q.weight": "model-00002-of-00003.safetensors",
202
- "ankh.encoder.layer.28.attention.v.weight": "model-00002-of-00003.safetensors",
203
- "ankh.encoder.layer.28.attention_norm.weight": "model-00002-of-00003.safetensors",
204
- "ankh.encoder.layer.28.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
205
- "ankh.encoder.layer.28.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
206
- "ankh.encoder.layer.28.ffn.wo.weight": "model-00002-of-00003.safetensors",
207
- "ankh.encoder.layer.28.ffn_norm.weight": "model-00002-of-00003.safetensors",
208
- "ankh.encoder.layer.29.attention.k.weight": "model-00002-of-00003.safetensors",
209
- "ankh.encoder.layer.29.attention.o.weight": "model-00002-of-00003.safetensors",
210
- "ankh.encoder.layer.29.attention.q.weight": "model-00002-of-00003.safetensors",
211
- "ankh.encoder.layer.29.attention.v.weight": "model-00002-of-00003.safetensors",
212
- "ankh.encoder.layer.29.attention_norm.weight": "model-00002-of-00003.safetensors",
213
- "ankh.encoder.layer.29.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
214
- "ankh.encoder.layer.29.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
215
- "ankh.encoder.layer.29.ffn.wo.weight": "model-00002-of-00003.safetensors",
216
- "ankh.encoder.layer.29.ffn_norm.weight": "model-00002-of-00003.safetensors",
217
- "ankh.encoder.layer.3.attention.k.weight": "model-00001-of-00003.safetensors",
218
- "ankh.encoder.layer.3.attention.o.weight": "model-00001-of-00003.safetensors",
219
- "ankh.encoder.layer.3.attention.q.weight": "model-00001-of-00003.safetensors",
220
- "ankh.encoder.layer.3.attention.v.weight": "model-00001-of-00003.safetensors",
221
- "ankh.encoder.layer.3.attention_norm.weight": "model-00001-of-00003.safetensors",
222
- "ankh.encoder.layer.3.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
223
- "ankh.encoder.layer.3.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
224
- "ankh.encoder.layer.3.ffn.wo.weight": "model-00001-of-00003.safetensors",
225
- "ankh.encoder.layer.3.ffn_norm.weight": "model-00001-of-00003.safetensors",
226
- "ankh.encoder.layer.30.attention.k.weight": "model-00002-of-00003.safetensors",
227
- "ankh.encoder.layer.30.attention.o.weight": "model-00002-of-00003.safetensors",
228
- "ankh.encoder.layer.30.attention.q.weight": "model-00002-of-00003.safetensors",
229
- "ankh.encoder.layer.30.attention.v.weight": "model-00002-of-00003.safetensors",
230
- "ankh.encoder.layer.30.attention_norm.weight": "model-00002-of-00003.safetensors",
231
- "ankh.encoder.layer.30.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
232
- "ankh.encoder.layer.30.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
233
- "ankh.encoder.layer.30.ffn.wo.weight": "model-00002-of-00003.safetensors",
234
- "ankh.encoder.layer.30.ffn_norm.weight": "model-00002-of-00003.safetensors",
235
- "ankh.encoder.layer.31.attention.k.weight": "model-00002-of-00003.safetensors",
236
- "ankh.encoder.layer.31.attention.o.weight": "model-00002-of-00003.safetensors",
237
- "ankh.encoder.layer.31.attention.q.weight": "model-00002-of-00003.safetensors",
238
- "ankh.encoder.layer.31.attention.v.weight": "model-00002-of-00003.safetensors",
239
- "ankh.encoder.layer.31.attention_norm.weight": "model-00002-of-00003.safetensors",
240
- "ankh.encoder.layer.31.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
241
- "ankh.encoder.layer.31.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
242
- "ankh.encoder.layer.31.ffn.wo.weight": "model-00002-of-00003.safetensors",
243
- "ankh.encoder.layer.31.ffn_norm.weight": "model-00002-of-00003.safetensors",
244
- "ankh.encoder.layer.32.attention.k.weight": "model-00002-of-00003.safetensors",
245
- "ankh.encoder.layer.32.attention.o.weight": "model-00002-of-00003.safetensors",
246
- "ankh.encoder.layer.32.attention.q.weight": "model-00002-of-00003.safetensors",
247
- "ankh.encoder.layer.32.attention.v.weight": "model-00002-of-00003.safetensors",
248
- "ankh.encoder.layer.32.attention_norm.weight": "model-00002-of-00003.safetensors",
249
- "ankh.encoder.layer.32.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
250
- "ankh.encoder.layer.32.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
251
- "ankh.encoder.layer.32.ffn.wo.weight": "model-00002-of-00003.safetensors",
252
- "ankh.encoder.layer.32.ffn_norm.weight": "model-00002-of-00003.safetensors",
253
- "ankh.encoder.layer.33.attention.k.weight": "model-00002-of-00003.safetensors",
254
- "ankh.encoder.layer.33.attention.o.weight": "model-00002-of-00003.safetensors",
255
- "ankh.encoder.layer.33.attention.q.weight": "model-00002-of-00003.safetensors",
256
- "ankh.encoder.layer.33.attention.v.weight": "model-00002-of-00003.safetensors",
257
- "ankh.encoder.layer.33.attention_norm.weight": "model-00002-of-00003.safetensors",
258
- "ankh.encoder.layer.33.ffn.wi_0.weight": "model-00002-of-00003.safetensors",
259
- "ankh.encoder.layer.33.ffn.wi_1.weight": "model-00002-of-00003.safetensors",
260
- "ankh.encoder.layer.33.ffn.wo.weight": "model-00002-of-00003.safetensors",
261
- "ankh.encoder.layer.33.ffn_norm.weight": "model-00002-of-00003.safetensors",
262
- "ankh.encoder.layer.34.attention.k.weight": "model-00002-of-00003.safetensors",
263
- "ankh.encoder.layer.34.attention.o.weight": "model-00002-of-00003.safetensors",
264
- "ankh.encoder.layer.34.attention.q.weight": "model-00002-of-00003.safetensors",
265
- "ankh.encoder.layer.34.attention.v.weight": "model-00002-of-00003.safetensors",
266
- "ankh.encoder.layer.34.attention_norm.weight": "model-00002-of-00003.safetensors",
267
- "ankh.encoder.layer.34.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
268
- "ankh.encoder.layer.34.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
269
- "ankh.encoder.layer.34.ffn.wo.weight": "model-00003-of-00003.safetensors",
270
- "ankh.encoder.layer.34.ffn_norm.weight": "model-00003-of-00003.safetensors",
271
- "ankh.encoder.layer.35.attention.k.weight": "model-00003-of-00003.safetensors",
272
- "ankh.encoder.layer.35.attention.o.weight": "model-00003-of-00003.safetensors",
273
- "ankh.encoder.layer.35.attention.q.weight": "model-00003-of-00003.safetensors",
274
- "ankh.encoder.layer.35.attention.v.weight": "model-00003-of-00003.safetensors",
275
- "ankh.encoder.layer.35.attention_norm.weight": "model-00003-of-00003.safetensors",
276
- "ankh.encoder.layer.35.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
277
- "ankh.encoder.layer.35.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
278
- "ankh.encoder.layer.35.ffn.wo.weight": "model-00003-of-00003.safetensors",
279
- "ankh.encoder.layer.35.ffn_norm.weight": "model-00003-of-00003.safetensors",
280
- "ankh.encoder.layer.36.attention.k.weight": "model-00003-of-00003.safetensors",
281
- "ankh.encoder.layer.36.attention.o.weight": "model-00003-of-00003.safetensors",
282
- "ankh.encoder.layer.36.attention.q.weight": "model-00003-of-00003.safetensors",
283
- "ankh.encoder.layer.36.attention.v.weight": "model-00003-of-00003.safetensors",
284
- "ankh.encoder.layer.36.attention_norm.weight": "model-00003-of-00003.safetensors",
285
- "ankh.encoder.layer.36.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
286
- "ankh.encoder.layer.36.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
287
- "ankh.encoder.layer.36.ffn.wo.weight": "model-00003-of-00003.safetensors",
288
- "ankh.encoder.layer.36.ffn_norm.weight": "model-00003-of-00003.safetensors",
289
- "ankh.encoder.layer.37.attention.k.weight": "model-00003-of-00003.safetensors",
290
- "ankh.encoder.layer.37.attention.o.weight": "model-00003-of-00003.safetensors",
291
- "ankh.encoder.layer.37.attention.q.weight": "model-00003-of-00003.safetensors",
292
- "ankh.encoder.layer.37.attention.v.weight": "model-00003-of-00003.safetensors",
293
- "ankh.encoder.layer.37.attention_norm.weight": "model-00003-of-00003.safetensors",
294
- "ankh.encoder.layer.37.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
295
- "ankh.encoder.layer.37.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
296
- "ankh.encoder.layer.37.ffn.wo.weight": "model-00003-of-00003.safetensors",
297
- "ankh.encoder.layer.37.ffn_norm.weight": "model-00003-of-00003.safetensors",
298
- "ankh.encoder.layer.38.attention.k.weight": "model-00003-of-00003.safetensors",
299
- "ankh.encoder.layer.38.attention.o.weight": "model-00003-of-00003.safetensors",
300
- "ankh.encoder.layer.38.attention.q.weight": "model-00003-of-00003.safetensors",
301
- "ankh.encoder.layer.38.attention.v.weight": "model-00003-of-00003.safetensors",
302
- "ankh.encoder.layer.38.attention_norm.weight": "model-00003-of-00003.safetensors",
303
- "ankh.encoder.layer.38.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
304
- "ankh.encoder.layer.38.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
305
- "ankh.encoder.layer.38.ffn.wo.weight": "model-00003-of-00003.safetensors",
306
- "ankh.encoder.layer.38.ffn_norm.weight": "model-00003-of-00003.safetensors",
307
- "ankh.encoder.layer.39.attention.k.weight": "model-00003-of-00003.safetensors",
308
- "ankh.encoder.layer.39.attention.o.weight": "model-00003-of-00003.safetensors",
309
- "ankh.encoder.layer.39.attention.q.weight": "model-00003-of-00003.safetensors",
310
- "ankh.encoder.layer.39.attention.v.weight": "model-00003-of-00003.safetensors",
311
- "ankh.encoder.layer.39.attention_norm.weight": "model-00003-of-00003.safetensors",
312
- "ankh.encoder.layer.39.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
313
- "ankh.encoder.layer.39.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
314
- "ankh.encoder.layer.39.ffn.wo.weight": "model-00003-of-00003.safetensors",
315
- "ankh.encoder.layer.39.ffn_norm.weight": "model-00003-of-00003.safetensors",
316
- "ankh.encoder.layer.4.attention.k.weight": "model-00001-of-00003.safetensors",
317
- "ankh.encoder.layer.4.attention.o.weight": "model-00001-of-00003.safetensors",
318
- "ankh.encoder.layer.4.attention.q.weight": "model-00001-of-00003.safetensors",
319
- "ankh.encoder.layer.4.attention.v.weight": "model-00001-of-00003.safetensors",
320
- "ankh.encoder.layer.4.attention_norm.weight": "model-00001-of-00003.safetensors",
321
- "ankh.encoder.layer.4.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
322
- "ankh.encoder.layer.4.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
323
- "ankh.encoder.layer.4.ffn.wo.weight": "model-00001-of-00003.safetensors",
324
- "ankh.encoder.layer.4.ffn_norm.weight": "model-00001-of-00003.safetensors",
325
- "ankh.encoder.layer.40.attention.k.weight": "model-00003-of-00003.safetensors",
326
- "ankh.encoder.layer.40.attention.o.weight": "model-00003-of-00003.safetensors",
327
- "ankh.encoder.layer.40.attention.q.weight": "model-00003-of-00003.safetensors",
328
- "ankh.encoder.layer.40.attention.v.weight": "model-00003-of-00003.safetensors",
329
- "ankh.encoder.layer.40.attention_norm.weight": "model-00003-of-00003.safetensors",
330
- "ankh.encoder.layer.40.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
331
- "ankh.encoder.layer.40.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
332
- "ankh.encoder.layer.40.ffn.wo.weight": "model-00003-of-00003.safetensors",
333
- "ankh.encoder.layer.40.ffn_norm.weight": "model-00003-of-00003.safetensors",
334
- "ankh.encoder.layer.41.attention.k.weight": "model-00003-of-00003.safetensors",
335
- "ankh.encoder.layer.41.attention.o.weight": "model-00003-of-00003.safetensors",
336
- "ankh.encoder.layer.41.attention.q.weight": "model-00003-of-00003.safetensors",
337
- "ankh.encoder.layer.41.attention.v.weight": "model-00003-of-00003.safetensors",
338
- "ankh.encoder.layer.41.attention_norm.weight": "model-00003-of-00003.safetensors",
339
- "ankh.encoder.layer.41.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
340
- "ankh.encoder.layer.41.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
341
- "ankh.encoder.layer.41.ffn.wo.weight": "model-00003-of-00003.safetensors",
342
- "ankh.encoder.layer.41.ffn_norm.weight": "model-00003-of-00003.safetensors",
343
- "ankh.encoder.layer.42.attention.k.weight": "model-00003-of-00003.safetensors",
344
- "ankh.encoder.layer.42.attention.o.weight": "model-00003-of-00003.safetensors",
345
- "ankh.encoder.layer.42.attention.q.weight": "model-00003-of-00003.safetensors",
346
- "ankh.encoder.layer.42.attention.v.weight": "model-00003-of-00003.safetensors",
347
- "ankh.encoder.layer.42.attention_norm.weight": "model-00003-of-00003.safetensors",
348
- "ankh.encoder.layer.42.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
349
- "ankh.encoder.layer.42.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
350
- "ankh.encoder.layer.42.ffn.wo.weight": "model-00003-of-00003.safetensors",
351
- "ankh.encoder.layer.42.ffn_norm.weight": "model-00003-of-00003.safetensors",
352
- "ankh.encoder.layer.43.attention.k.weight": "model-00003-of-00003.safetensors",
353
- "ankh.encoder.layer.43.attention.o.weight": "model-00003-of-00003.safetensors",
354
- "ankh.encoder.layer.43.attention.q.weight": "model-00003-of-00003.safetensors",
355
- "ankh.encoder.layer.43.attention.v.weight": "model-00003-of-00003.safetensors",
356
- "ankh.encoder.layer.43.attention_norm.weight": "model-00003-of-00003.safetensors",
357
- "ankh.encoder.layer.43.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
358
- "ankh.encoder.layer.43.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
359
- "ankh.encoder.layer.43.ffn.wo.weight": "model-00003-of-00003.safetensors",
360
- "ankh.encoder.layer.43.ffn_norm.weight": "model-00003-of-00003.safetensors",
361
- "ankh.encoder.layer.44.attention.k.weight": "model-00003-of-00003.safetensors",
362
- "ankh.encoder.layer.44.attention.o.weight": "model-00003-of-00003.safetensors",
363
- "ankh.encoder.layer.44.attention.q.weight": "model-00003-of-00003.safetensors",
364
- "ankh.encoder.layer.44.attention.v.weight": "model-00003-of-00003.safetensors",
365
- "ankh.encoder.layer.44.attention_norm.weight": "model-00003-of-00003.safetensors",
366
- "ankh.encoder.layer.44.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
367
- "ankh.encoder.layer.44.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
368
- "ankh.encoder.layer.44.ffn.wo.weight": "model-00003-of-00003.safetensors",
369
- "ankh.encoder.layer.44.ffn_norm.weight": "model-00003-of-00003.safetensors",
370
- "ankh.encoder.layer.45.attention.k.weight": "model-00003-of-00003.safetensors",
371
- "ankh.encoder.layer.45.attention.o.weight": "model-00003-of-00003.safetensors",
372
- "ankh.encoder.layer.45.attention.q.weight": "model-00003-of-00003.safetensors",
373
- "ankh.encoder.layer.45.attention.v.weight": "model-00003-of-00003.safetensors",
374
- "ankh.encoder.layer.45.attention_norm.weight": "model-00003-of-00003.safetensors",
375
- "ankh.encoder.layer.45.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
376
- "ankh.encoder.layer.45.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
377
- "ankh.encoder.layer.45.ffn.wo.weight": "model-00003-of-00003.safetensors",
378
- "ankh.encoder.layer.45.ffn_norm.weight": "model-00003-of-00003.safetensors",
379
- "ankh.encoder.layer.46.attention.k.weight": "model-00003-of-00003.safetensors",
380
- "ankh.encoder.layer.46.attention.o.weight": "model-00003-of-00003.safetensors",
381
- "ankh.encoder.layer.46.attention.q.weight": "model-00003-of-00003.safetensors",
382
- "ankh.encoder.layer.46.attention.v.weight": "model-00003-of-00003.safetensors",
383
- "ankh.encoder.layer.46.attention_norm.weight": "model-00003-of-00003.safetensors",
384
- "ankh.encoder.layer.46.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
385
- "ankh.encoder.layer.46.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
386
- "ankh.encoder.layer.46.ffn.wo.weight": "model-00003-of-00003.safetensors",
387
- "ankh.encoder.layer.46.ffn_norm.weight": "model-00003-of-00003.safetensors",
388
- "ankh.encoder.layer.47.attention.k.weight": "model-00003-of-00003.safetensors",
389
- "ankh.encoder.layer.47.attention.o.weight": "model-00003-of-00003.safetensors",
390
- "ankh.encoder.layer.47.attention.q.weight": "model-00003-of-00003.safetensors",
391
- "ankh.encoder.layer.47.attention.v.weight": "model-00003-of-00003.safetensors",
392
- "ankh.encoder.layer.47.attention_norm.weight": "model-00003-of-00003.safetensors",
393
- "ankh.encoder.layer.47.ffn.wi_0.weight": "model-00003-of-00003.safetensors",
394
- "ankh.encoder.layer.47.ffn.wi_1.weight": "model-00003-of-00003.safetensors",
395
- "ankh.encoder.layer.47.ffn.wo.weight": "model-00003-of-00003.safetensors",
396
- "ankh.encoder.layer.47.ffn_norm.weight": "model-00003-of-00003.safetensors",
397
- "ankh.encoder.layer.5.attention.k.weight": "model-00001-of-00003.safetensors",
398
- "ankh.encoder.layer.5.attention.o.weight": "model-00001-of-00003.safetensors",
399
- "ankh.encoder.layer.5.attention.q.weight": "model-00001-of-00003.safetensors",
400
- "ankh.encoder.layer.5.attention.v.weight": "model-00001-of-00003.safetensors",
401
- "ankh.encoder.layer.5.attention_norm.weight": "model-00001-of-00003.safetensors",
402
- "ankh.encoder.layer.5.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
403
- "ankh.encoder.layer.5.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
404
- "ankh.encoder.layer.5.ffn.wo.weight": "model-00001-of-00003.safetensors",
405
- "ankh.encoder.layer.5.ffn_norm.weight": "model-00001-of-00003.safetensors",
406
- "ankh.encoder.layer.6.attention.k.weight": "model-00001-of-00003.safetensors",
407
- "ankh.encoder.layer.6.attention.o.weight": "model-00001-of-00003.safetensors",
408
- "ankh.encoder.layer.6.attention.q.weight": "model-00001-of-00003.safetensors",
409
- "ankh.encoder.layer.6.attention.v.weight": "model-00001-of-00003.safetensors",
410
- "ankh.encoder.layer.6.attention_norm.weight": "model-00001-of-00003.safetensors",
411
- "ankh.encoder.layer.6.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
412
- "ankh.encoder.layer.6.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
413
- "ankh.encoder.layer.6.ffn.wo.weight": "model-00001-of-00003.safetensors",
414
- "ankh.encoder.layer.6.ffn_norm.weight": "model-00001-of-00003.safetensors",
415
- "ankh.encoder.layer.7.attention.k.weight": "model-00001-of-00003.safetensors",
416
- "ankh.encoder.layer.7.attention.o.weight": "model-00001-of-00003.safetensors",
417
- "ankh.encoder.layer.7.attention.q.weight": "model-00001-of-00003.safetensors",
418
- "ankh.encoder.layer.7.attention.v.weight": "model-00001-of-00003.safetensors",
419
- "ankh.encoder.layer.7.attention_norm.weight": "model-00001-of-00003.safetensors",
420
- "ankh.encoder.layer.7.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
421
- "ankh.encoder.layer.7.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
422
- "ankh.encoder.layer.7.ffn.wo.weight": "model-00001-of-00003.safetensors",
423
- "ankh.encoder.layer.7.ffn_norm.weight": "model-00001-of-00003.safetensors",
424
- "ankh.encoder.layer.8.attention.k.weight": "model-00001-of-00003.safetensors",
425
- "ankh.encoder.layer.8.attention.o.weight": "model-00001-of-00003.safetensors",
426
- "ankh.encoder.layer.8.attention.q.weight": "model-00001-of-00003.safetensors",
427
- "ankh.encoder.layer.8.attention.v.weight": "model-00001-of-00003.safetensors",
428
- "ankh.encoder.layer.8.attention_norm.weight": "model-00001-of-00003.safetensors",
429
- "ankh.encoder.layer.8.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
430
- "ankh.encoder.layer.8.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
431
- "ankh.encoder.layer.8.ffn.wo.weight": "model-00001-of-00003.safetensors",
432
- "ankh.encoder.layer.8.ffn_norm.weight": "model-00001-of-00003.safetensors",
433
- "ankh.encoder.layer.9.attention.k.weight": "model-00001-of-00003.safetensors",
434
- "ankh.encoder.layer.9.attention.o.weight": "model-00001-of-00003.safetensors",
435
- "ankh.encoder.layer.9.attention.q.weight": "model-00001-of-00003.safetensors",
436
- "ankh.encoder.layer.9.attention.v.weight": "model-00001-of-00003.safetensors",
437
- "ankh.encoder.layer.9.attention_norm.weight": "model-00001-of-00003.safetensors",
438
- "ankh.encoder.layer.9.ffn.wi_0.weight": "model-00001-of-00003.safetensors",
439
- "ankh.encoder.layer.9.ffn.wi_1.weight": "model-00001-of-00003.safetensors",
440
- "ankh.encoder.layer.9.ffn.wo.weight": "model-00001-of-00003.safetensors",
441
- "ankh.encoder.layer.9.ffn_norm.weight": "model-00001-of-00003.safetensors",
442
- "lm_head.weight": "model-00003-of-00003.safetensors"
 
443
  }
444
  }
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 3486110208,
4
+ "total_size": 13944440832
5
  },
6
  "weight_map": {
7
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
11
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
12
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
15
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
16
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
20
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
21
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
24
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
25
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
29
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
30
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
33
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
34
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
38
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
39
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
42
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
43
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
47
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
48
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
51
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
52
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
56
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
57
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
60
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
61
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
65
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
66
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
69
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
70
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
74
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
75
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
78
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
79
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
83
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
84
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
87
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
88
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
92
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
93
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
96
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
97
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
101
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
102
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
105
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
106
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
110
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
111
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
114
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
115
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
119
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
120
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
123
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
124
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
128
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
129
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
132
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
133
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
137
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
138
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
141
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
142
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
146
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
147
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
150
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
151
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
155
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
156
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
159
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
160
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
161
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
162
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
163
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
164
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
165
+ "encoder.block.24.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
166
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
167
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
168
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
169
+ "encoder.block.24.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
170
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
171
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
172
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
173
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
174
+ "encoder.block.25.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
175
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
176
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
177
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
178
+ "encoder.block.25.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
179
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
180
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
181
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
182
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
183
+ "encoder.block.26.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
184
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
185
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
186
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
187
+ "encoder.block.26.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
188
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
189
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
190
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
191
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
192
+ "encoder.block.27.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
193
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
194
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
195
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
196
+ "encoder.block.27.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
197
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
198
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
199
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
200
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
201
+ "encoder.block.28.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
202
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
203
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
204
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
205
+ "encoder.block.28.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
206
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
207
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
208
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
209
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
210
+ "encoder.block.29.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
211
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
212
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
213
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
214
+ "encoder.block.29.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
215
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
216
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
217
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
218
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
219
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
220
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
221
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
222
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
223
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
224
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
225
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
226
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
227
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
228
+ "encoder.block.30.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
229
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
230
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
231
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
232
+ "encoder.block.30.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
233
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
234
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
235
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
236
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
237
+ "encoder.block.31.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
238
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
239
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
240
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
241
+ "encoder.block.31.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
242
+ "encoder.block.32.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
243
+ "encoder.block.32.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
244
+ "encoder.block.32.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
245
+ "encoder.block.32.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
246
+ "encoder.block.32.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
247
+ "encoder.block.32.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
248
+ "encoder.block.32.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
249
+ "encoder.block.32.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
250
+ "encoder.block.32.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
251
+ "encoder.block.33.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
252
+ "encoder.block.33.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
253
+ "encoder.block.33.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
254
+ "encoder.block.33.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
255
+ "encoder.block.33.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
256
+ "encoder.block.33.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
257
+ "encoder.block.33.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
258
+ "encoder.block.33.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
259
+ "encoder.block.33.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
260
+ "encoder.block.34.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
261
+ "encoder.block.34.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
262
+ "encoder.block.34.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
263
+ "encoder.block.34.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
264
+ "encoder.block.34.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
265
+ "encoder.block.34.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
266
+ "encoder.block.34.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
267
+ "encoder.block.34.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
268
+ "encoder.block.34.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
269
+ "encoder.block.35.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
270
+ "encoder.block.35.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
271
+ "encoder.block.35.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
272
+ "encoder.block.35.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
273
+ "encoder.block.35.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
274
+ "encoder.block.35.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
275
+ "encoder.block.35.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
276
+ "encoder.block.35.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
277
+ "encoder.block.35.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
278
+ "encoder.block.36.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
279
+ "encoder.block.36.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
280
+ "encoder.block.36.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
281
+ "encoder.block.36.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
282
+ "encoder.block.36.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
283
+ "encoder.block.36.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
284
+ "encoder.block.36.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
285
+ "encoder.block.36.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
286
+ "encoder.block.36.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
287
+ "encoder.block.37.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
288
+ "encoder.block.37.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
289
+ "encoder.block.37.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
290
+ "encoder.block.37.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
291
+ "encoder.block.37.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
292
+ "encoder.block.37.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
293
+ "encoder.block.37.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
294
+ "encoder.block.37.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
295
+ "encoder.block.37.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
296
+ "encoder.block.38.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
297
+ "encoder.block.38.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
298
+ "encoder.block.38.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
299
+ "encoder.block.38.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
300
+ "encoder.block.38.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
301
+ "encoder.block.38.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
302
+ "encoder.block.38.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
303
+ "encoder.block.38.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
304
+ "encoder.block.38.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
305
+ "encoder.block.39.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
306
+ "encoder.block.39.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
307
+ "encoder.block.39.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
308
+ "encoder.block.39.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
309
+ "encoder.block.39.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
310
+ "encoder.block.39.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
311
+ "encoder.block.39.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
312
+ "encoder.block.39.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
313
+ "encoder.block.39.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
314
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
315
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
316
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
317
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
318
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
319
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
320
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
321
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
322
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
323
+ "encoder.block.40.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
324
+ "encoder.block.40.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
325
+ "encoder.block.40.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
326
+ "encoder.block.40.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
327
+ "encoder.block.40.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
328
+ "encoder.block.40.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
329
+ "encoder.block.40.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
330
+ "encoder.block.40.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
331
+ "encoder.block.40.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
332
+ "encoder.block.41.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
333
+ "encoder.block.41.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
334
+ "encoder.block.41.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
335
+ "encoder.block.41.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
336
+ "encoder.block.41.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
337
+ "encoder.block.41.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
338
+ "encoder.block.41.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
339
+ "encoder.block.41.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
340
+ "encoder.block.41.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
341
+ "encoder.block.42.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
342
+ "encoder.block.42.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
343
+ "encoder.block.42.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
344
+ "encoder.block.42.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
345
+ "encoder.block.42.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
346
+ "encoder.block.42.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
347
+ "encoder.block.42.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
348
+ "encoder.block.42.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
349
+ "encoder.block.42.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
350
+ "encoder.block.43.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
351
+ "encoder.block.43.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
352
+ "encoder.block.43.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
353
+ "encoder.block.43.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
354
+ "encoder.block.43.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
355
+ "encoder.block.43.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
356
+ "encoder.block.43.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
357
+ "encoder.block.43.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
358
+ "encoder.block.43.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
359
+ "encoder.block.44.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
360
+ "encoder.block.44.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
361
+ "encoder.block.44.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
362
+ "encoder.block.44.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
363
+ "encoder.block.44.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
364
+ "encoder.block.44.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
365
+ "encoder.block.44.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
366
+ "encoder.block.44.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
367
+ "encoder.block.44.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
368
+ "encoder.block.45.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
369
+ "encoder.block.45.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
370
+ "encoder.block.45.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
371
+ "encoder.block.45.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
372
+ "encoder.block.45.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
373
+ "encoder.block.45.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
374
+ "encoder.block.45.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
375
+ "encoder.block.45.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
376
+ "encoder.block.45.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
377
+ "encoder.block.46.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
378
+ "encoder.block.46.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
379
+ "encoder.block.46.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
380
+ "encoder.block.46.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
381
+ "encoder.block.46.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
382
+ "encoder.block.46.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
383
+ "encoder.block.46.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
384
+ "encoder.block.46.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
385
+ "encoder.block.46.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
386
+ "encoder.block.47.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
387
+ "encoder.block.47.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
388
+ "encoder.block.47.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
389
+ "encoder.block.47.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
390
+ "encoder.block.47.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
391
+ "encoder.block.47.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
392
+ "encoder.block.47.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
393
+ "encoder.block.47.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
394
+ "encoder.block.47.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
395
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
396
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
397
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
398
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
399
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
400
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
401
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
402
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
403
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
404
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
405
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
406
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
407
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
408
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
409
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
410
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
411
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
412
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
413
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
414
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
415
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
416
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
417
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
418
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
419
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
420
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
421
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
422
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
423
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
424
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
425
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
426
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
427
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
428
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
429
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
430
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
431
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
432
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
433
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
434
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
435
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
436
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
437
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
438
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
439
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
440
+ "encoder.embed_tokens.weight": "model-00001-of-00003.safetensors",
441
+ "encoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
442
+ "lm_head.weight": "model-00003-of-00003.safetensors",
443
+ "shared.weight": "model-00001-of-00003.safetensors"
444
  }
445
  }