Hugging Face's logo

izhx
/
udever-bloom-7b1

Feature Extraction
Transformers
PyTorch
bloom
mteb
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
3

Adding `safetensors` variant of this model

#3
by SFconvertbot - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+381
-0
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +3 -0
  2. model-00002-of-00003.safetensors +3 -0
  3. model-00003-of-00003.safetensors +3 -0
  4. model.safetensors.index.json +372 -0
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f349e36868e003ecb3cc25230714a1291586bea5183b73f71f34e5e757feb74
3
+ size 9950504312
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654be39834de337033e4580a3dca01a430796a38ee6985350179737a74778460
3
+ size 9733406064
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d735135f3935f1659eaed05b900c5597e9c2563e4c8c6764df3421f953858d
3
+ size 8592192584
model.safetensors.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28276064256
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
7
+ "h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
9
+ "h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
10
+ "h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
11
+ "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
12
+ "h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
13
+ "h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
15
+ "h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
16
+ "h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
17
+ "h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
18
+ "h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
19
+ "h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
20
+ "h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
21
+ "h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
22
+ "h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
23
+ "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
24
+ "h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
25
+ "h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
26
+ "h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
27
+ "h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
28
+ "h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
29
+ "h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
30
+ "h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
31
+ "h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
33
+ "h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
34
+ "h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
35
+ "h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
36
+ "h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
37
+ "h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
39
+ "h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
40
+ "h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
41
+ "h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
42
+ "h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
43
+ "h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
45
+ "h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
46
+ "h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
47
+ "h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
48
+ "h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
49
+ "h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
51
+ "h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
52
+ "h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
53
+ "h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
54
+ "h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
55
+ "h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
57
+ "h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
58
+ "h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
59
+ "h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
60
+ "h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
61
+ "h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
63
+ "h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
64
+ "h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
65
+ "h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
66
+ "h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
67
+ "h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
69
+ "h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
70
+ "h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
71
+ "h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
72
+ "h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
73
+ "h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
75
+ "h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
76
+ "h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
77
+ "h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
78
+ "h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
79
+ "h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
81
+ "h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
82
+ "h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
83
+ "h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
84
+ "h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
85
+ "h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
87
+ "h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
88
+ "h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
89
+ "h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
90
+ "h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
91
+ "h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
93
+ "h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
94
+ "h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
95
+ "h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
96
+ "h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
97
+ "h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
99
+ "h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
100
+ "h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
101
+ "h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
102
+ "h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
103
+ "h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
105
+ "h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
106
+ "h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
107
+ "h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
108
+ "h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
109
+ "h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
111
+ "h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
112
+ "h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
113
+ "h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
114
+ "h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
115
+ "h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
116
+ "h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
117
+ "h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
118
+ "h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
119
+ "h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
120
+ "h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
121
+ "h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
122
+ "h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
123
+ "h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
124
+ "h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
125
+ "h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
126
+ "h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
127
+ "h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
129
+ "h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
130
+ "h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
131
+ "h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
132
+ "h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
133
+ "h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
135
+ "h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
136
+ "h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
137
+ "h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
138
+ "h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
139
+ "h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
140
+ "h.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
141
+ "h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
142
+ "h.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
143
+ "h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
144
+ "h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
145
+ "h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
146
+ "h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
147
+ "h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
148
+ "h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
149
+ "h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
150
+ "h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
151
+ "h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
152
+ "h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
153
+ "h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
154
+ "h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
155
+ "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
156
+ "h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
157
+ "h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
158
+ "h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
159
+ "h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
160
+ "h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
161
+ "h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
162
+ "h.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
163
+ "h.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
164
+ "h.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
165
+ "h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
166
+ "h.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
167
+ "h.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
168
+ "h.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
169
+ "h.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "h.20.self_attention.dense.bias": "model-00003-of-00003.safetensors",
171
+ "h.20.self_attention.dense.weight": "model-00003-of-00003.safetensors",
172
+ "h.20.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
173
+ "h.20.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
174
+ "h.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
175
+ "h.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
176
+ "h.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
177
+ "h.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
178
+ "h.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
179
+ "h.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
180
+ "h.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
181
+ "h.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
182
+ "h.21.self_attention.dense.bias": "model-00003-of-00003.safetensors",
183
+ "h.21.self_attention.dense.weight": "model-00003-of-00003.safetensors",
184
+ "h.21.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
185
+ "h.21.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
186
+ "h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
187
+ "h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "h.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
189
+ "h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
190
+ "h.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
191
+ "h.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
192
+ "h.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
193
+ "h.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
194
+ "h.22.self_attention.dense.bias": "model-00003-of-00003.safetensors",
195
+ "h.22.self_attention.dense.weight": "model-00003-of-00003.safetensors",
196
+ "h.22.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
197
+ "h.22.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
198
+ "h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
199
+ "h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
200
+ "h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
201
+ "h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
202
+ "h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
203
+ "h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
204
+ "h.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
205
+ "h.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
206
+ "h.23.self_attention.dense.bias": "model-00003-of-00003.safetensors",
207
+ "h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
208
+ "h.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
209
+ "h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
210
+ "h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
211
+ "h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
212
+ "h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
213
+ "h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
214
+ "h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
215
+ "h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
216
+ "h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
217
+ "h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
218
+ "h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
219
+ "h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
220
+ "h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
221
+ "h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
222
+ "h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
223
+ "h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
224
+ "h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
225
+ "h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
226
+ "h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
227
+ "h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
228
+ "h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
229
+ "h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
230
+ "h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
231
+ "h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
232
+ "h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
233
+ "h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
234
+ "h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
235
+ "h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
236
+ "h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
237
+ "h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
238
+ "h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
239
+ "h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
240
+ "h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
241
+ "h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
242
+ "h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
243
+ "h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
244
+ "h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
245
+ "h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
246
+ "h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
247
+ "h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
248
+ "h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
249
+ "h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
250
+ "h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
251
+ "h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
252
+ "h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
253
+ "h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
254
+ "h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
255
+ "h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
256
+ "h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
257
+ "h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
258
+ "h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
259
+ "h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
260
+ "h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
261
+ "h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
262
+ "h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
263
+ "h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
264
+ "h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
265
+ "h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
266
+ "h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
267
+ "h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
268
+ "h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
269
+ "h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
270
+ "h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
271
+ "h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
272
+ "h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
273
+ "h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
274
+ "h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
275
+ "h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
276
+ "h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
277
+ "h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
278
+ "h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
279
+ "h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
280
+ "h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
281
+ "h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
282
+ "h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
283
+ "h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
284
+ "h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
285
+ "h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
286
+ "h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
287
+ "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
288
+ "h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
289
+ "h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
290
+ "h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
291
+ "h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
292
+ "h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
293
+ "h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
294
+ "h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
295
+ "h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
296
+ "h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
297
+ "h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
298
+ "h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
299
+ "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
300
+ "h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
301
+ "h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
302
+ "h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
303
+ "h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
304
+ "h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
305
+ "h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
306
+ "h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
307
+ "h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
308
+ "h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
309
+ "h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
310
+ "h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
311
+ "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
312
+ "h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
313
+ "h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
314
+ "h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
315
+ "h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
316
+ "h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
317
+ "h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
318
+ "h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
319
+ "h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
320
+ "h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
321
+ "h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
322
+ "h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
323
+ "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
324
+ "h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
325
+ "h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
326
+ "h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
327
+ "h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
328
+ "h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
329
+ "h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
330
+ "h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
331
+ "h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
332
+ "h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
333
+ "h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
334
+ "h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
335
+ "h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
336
+ "h.7.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
337
+ "h.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
338
+ "h.7.self_attention.dense.bias": "model-00002-of-00003.safetensors",
339
+ "h.7.self_attention.dense.weight": "model-00002-of-00003.safetensors",
340
+ "h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
341
+ "h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
342
+ "h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
343
+ "h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
344
+ "h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
345
+ "h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
346
+ "h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
347
+ "h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
348
+ "h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
349
+ "h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
350
+ "h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
351
+ "h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
352
+ "h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
353
+ "h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
354
+ "h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
355
+ "h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
356
+ "h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
357
+ "h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
358
+ "h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
359
+ "h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
360
+ "h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
361
+ "h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
362
+ "h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
363
+ "h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
364
+ "h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
365
+ "h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
366
+ "ln_f.bias": "model-00003-of-00003.safetensors",
367
+ "ln_f.weight": "model-00003-of-00003.safetensors",
368
+ "word_embeddings.weight": "model-00001-of-00003.safetensors",
369
+ "word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
370
+ "word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
371
+ }
372
+ }