Hugging Face's logo

AIFunOver
/
glm-4-9b-chat-openvino-fp16

Safetensors
OpenVINO
Chinese
English
chatglm
glm
thudm
nncf
fp16
custom_code
Model card Files Community
AIFunOver commited on
Commit
bf403f9
•
1 Parent(s): f5d3213

Upload model.safetensors.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +291 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,291 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18799902784
4
+ },
5
+ "weight_map": {
6
+ "transformer.embedding.word_embeddings.weight": "model-00001-of-00010.safetensors",
7
+ "transformer.encoder.final_layernorm.weight": "model-00010-of-00010.safetensors",
8
+ "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
9
+ "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00010.safetensors",
10
+ "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
11
+ "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
12
+ "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00010.safetensors",
13
+ "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
14
+ "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
15
+ "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
16
+ "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
17
+ "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
18
+ "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
19
+ "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00010.safetensors",
20
+ "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
21
+ "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
22
+ "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
23
+ "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
24
+ "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
25
+ "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
26
+ "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00010.safetensors",
27
+ "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
28
+ "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
29
+ "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
30
+ "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
31
+ "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
32
+ "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
33
+ "transformer.encoder.layers.11.self_attention.dense.weight": "model-00004-of-00010.safetensors",
34
+ "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
35
+ "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
36
+ "transformer.encoder.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
37
+ "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
38
+ "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
39
+ "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
40
+ "transformer.encoder.layers.12.self_attention.dense.weight": "model-00004-of-00010.safetensors",
41
+ "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
42
+ "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
43
+ "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
44
+ "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
45
+ "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
46
+ "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
47
+ "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00010.safetensors",
48
+ "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
49
+ "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
50
+ "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
51
+ "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
52
+ "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
53
+ "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
54
+ "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00010.safetensors",
55
+ "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
56
+ "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
57
+ "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
58
+ "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
59
+ "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
60
+ "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
61
+ "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00010.safetensors",
62
+ "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
63
+ "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
64
+ "transformer.encoder.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
65
+ "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
66
+ "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
67
+ "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
68
+ "transformer.encoder.layers.16.self_attention.dense.weight": "model-00005-of-00010.safetensors",
69
+ "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
70
+ "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
71
+ "transformer.encoder.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
72
+ "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
73
+ "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
74
+ "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
75
+ "transformer.encoder.layers.17.self_attention.dense.weight": "model-00005-of-00010.safetensors",
76
+ "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
77
+ "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
78
+ "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
79
+ "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
80
+ "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
81
+ "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
82
+ "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00010.safetensors",
83
+ "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
84
+ "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
85
+ "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
86
+ "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
87
+ "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
88
+ "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
89
+ "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00010.safetensors",
90
+ "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
91
+ "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
92
+ "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
93
+ "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
94
+ "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
95
+ "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
96
+ "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00010.safetensors",
97
+ "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
98
+ "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
99
+ "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
100
+ "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
101
+ "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
102
+ "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
103
+ "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00010.safetensors",
104
+ "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
105
+ "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
106
+ "transformer.encoder.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
107
+ "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
108
+ "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
109
+ "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
110
+ "transformer.encoder.layers.21.self_attention.dense.weight": "model-00006-of-00010.safetensors",
111
+ "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
112
+ "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
113
+ "transformer.encoder.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
114
+ "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
115
+ "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
116
+ "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
117
+ "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00010.safetensors",
118
+ "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
119
+ "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
120
+ "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
121
+ "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
122
+ "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
123
+ "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
124
+ "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00010.safetensors",
125
+ "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
126
+ "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
127
+ "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
128
+ "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
129
+ "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
130
+ "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
131
+ "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00010.safetensors",
132
+ "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
133
+ "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
134
+ "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors",
135
+ "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
136
+ "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
137
+ "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
138
+ "transformer.encoder.layers.25.self_attention.dense.weight": "model-00007-of-00010.safetensors",
139
+ "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
140
+ "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
141
+ "transformer.encoder.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
142
+ "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
143
+ "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
144
+ "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
145
+ "transformer.encoder.layers.26.self_attention.dense.weight": "model-00007-of-00010.safetensors",
146
+ "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
147
+ "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
148
+ "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
149
+ "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
150
+ "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
151
+ "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
152
+ "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00010.safetensors",
153
+ "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
154
+ "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
155
+ "transformer.encoder.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
156
+ "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
157
+ "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
158
+ "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
159
+ "transformer.encoder.layers.28.self_attention.dense.weight": "model-00007-of-00010.safetensors",
160
+ "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
161
+ "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
162
+ "transformer.encoder.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
163
+ "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
164
+ "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
165
+ "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
166
+ "transformer.encoder.layers.29.self_attention.dense.weight": "model-00007-of-00010.safetensors",
167
+ "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
168
+ "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
169
+ "transformer.encoder.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
170
+ "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
171
+ "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
172
+ "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
173
+ "transformer.encoder.layers.3.self_attention.dense.weight": "model-00002-of-00010.safetensors",
174
+ "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
175
+ "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
176
+ "transformer.encoder.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
177
+ "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
178
+ "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
179
+ "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
180
+ "transformer.encoder.layers.30.self_attention.dense.weight": "model-00008-of-00010.safetensors",
181
+ "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
182
+ "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
183
+ "transformer.encoder.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
184
+ "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
185
+ "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
186
+ "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
187
+ "transformer.encoder.layers.31.self_attention.dense.weight": "model-00008-of-00010.safetensors",
188
+ "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
189
+ "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
190
+ "transformer.encoder.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
191
+ "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
192
+ "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
193
+ "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
194
+ "transformer.encoder.layers.32.self_attention.dense.weight": "model-00008-of-00010.safetensors",
195
+ "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
196
+ "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
197
+ "transformer.encoder.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
198
+ "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
199
+ "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
200
+ "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
201
+ "transformer.encoder.layers.33.self_attention.dense.weight": "model-00008-of-00010.safetensors",
202
+ "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
203
+ "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
204
+ "transformer.encoder.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
205
+ "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
206
+ "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
207
+ "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
208
+ "transformer.encoder.layers.34.self_attention.dense.weight": "model-00008-of-00010.safetensors",
209
+ "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
210
+ "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
211
+ "transformer.encoder.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
212
+ "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
213
+ "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
214
+ "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
215
+ "transformer.encoder.layers.35.self_attention.dense.weight": "model-00009-of-00010.safetensors",
216
+ "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
217
+ "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
218
+ "transformer.encoder.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
219
+ "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
220
+ "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
221
+ "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
222
+ "transformer.encoder.layers.36.self_attention.dense.weight": "model-00009-of-00010.safetensors",
223
+ "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
224
+ "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
225
+ "transformer.encoder.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
226
+ "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
227
+ "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
228
+ "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
229
+ "transformer.encoder.layers.37.self_attention.dense.weight": "model-00009-of-00010.safetensors",
230
+ "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
231
+ "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
232
+ "transformer.encoder.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
233
+ "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
234
+ "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
235
+ "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
236
+ "transformer.encoder.layers.38.self_attention.dense.weight": "model-00009-of-00010.safetensors",
237
+ "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
238
+ "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
239
+ "transformer.encoder.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
240
+ "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00010-of-00010.safetensors",
241
+ "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00010-of-00010.safetensors",
242
+ "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
243
+ "transformer.encoder.layers.39.self_attention.dense.weight": "model-00010-of-00010.safetensors",
244
+ "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00010-of-00010.safetensors",
245
+ "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00010-of-00010.safetensors",
246
+ "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
247
+ "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
248
+ "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
249
+ "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
250
+ "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00010.safetensors",
251
+ "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
252
+ "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
253
+ "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
254
+ "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
255
+ "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
256
+ "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
257
+ "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00010.safetensors",
258
+ "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
259
+ "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
260
+ "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
261
+ "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
262
+ "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
263
+ "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
264
+ "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00010.safetensors",
265
+ "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
266
+ "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
267
+ "transformer.encoder.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
268
+ "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
269
+ "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
270
+ "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
271
+ "transformer.encoder.layers.7.self_attention.dense.weight": "model-00003-of-00010.safetensors",
272
+ "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
273
+ "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
274
+ "transformer.encoder.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
275
+ "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
276
+ "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
277
+ "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
278
+ "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00010.safetensors",
279
+ "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
280
+ "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
281
+ "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
282
+ "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
283
+ "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
284
+ "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
285
+ "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00010.safetensors",
286
+ "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
287
+ "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
288
+ "transformer.output_layer.weight": "model-00010-of-00010.safetensors",
289
+ "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00010.safetensors"
290
+ }
291
+ }