Hugging Face's logo

OpenNLPLab
/
TransNormerLLM-7B

Text Generation
Transformers
PyTorch
English
Chinese
TransNormerLLM
custom_code
Model card Files Community
1
OpenNLPLab commited on
Commit
fbc1a5e
•
1 Parent(s): 9f7d0a7

Upload model.bin

Browse files
Files changed (1) hide show
  1. pytorch_model.bin.index.json +160 -0
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27346878464
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.token_mixer.lrpe.theta": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.1.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.1.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.1.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.10.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
20
+ "model.layers.10.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
21
+ "model.layers.10.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
22
+ "model.layers.10.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.10.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
24
+ "model.layers.11.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
25
+ "model.layers.11.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
26
+ "model.layers.11.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
27
+ "model.layers.11.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
28
+ "model.layers.11.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
29
+ "model.layers.12.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
30
+ "model.layers.12.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
31
+ "model.layers.12.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
32
+ "model.layers.12.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
33
+ "model.layers.12.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
34
+ "model.layers.13.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
35
+ "model.layers.13.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
36
+ "model.layers.13.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
37
+ "model.layers.13.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
38
+ "model.layers.13.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.14.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.14.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
41
+ "model.layers.14.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.14.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.14.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
44
+ "model.layers.15.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
45
+ "model.layers.15.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
46
+ "model.layers.15.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
47
+ "model.layers.15.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
48
+ "model.layers.15.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.16.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.16.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.16.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.16.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.16.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.17.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.17.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.17.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.17.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.17.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.18.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.18.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.18.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.18.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.18.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.19.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.19.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.19.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.19.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.19.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.2.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.2.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.2.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.2.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.2.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.20.channel_mixer.l1.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.20.channel_mixer.l2.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.20.channel_mixer.l3.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.20.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.20.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.21.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
80
+ "model.layers.21.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
81
+ "model.layers.21.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
82
+ "model.layers.21.token_mixer.out_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.21.token_mixer.qkvu_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.22.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
85
+ "model.layers.22.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
86
+ "model.layers.22.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
87
+ "model.layers.22.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
88
+ "model.layers.22.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
89
+ "model.layers.23.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
90
+ "model.layers.23.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
91
+ "model.layers.23.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
92
+ "model.layers.23.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
93
+ "model.layers.23.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
94
+ "model.layers.24.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
95
+ "model.layers.24.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
96
+ "model.layers.24.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
97
+ "model.layers.24.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
98
+ "model.layers.24.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
99
+ "model.layers.25.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
100
+ "model.layers.25.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
101
+ "model.layers.25.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
102
+ "model.layers.25.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
103
+ "model.layers.25.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
104
+ "model.layers.26.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
105
+ "model.layers.26.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
106
+ "model.layers.26.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
107
+ "model.layers.26.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
108
+ "model.layers.26.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
109
+ "model.layers.27.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
110
+ "model.layers.27.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
111
+ "model.layers.27.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
112
+ "model.layers.27.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
113
+ "model.layers.27.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
114
+ "model.layers.28.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
115
+ "model.layers.28.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
116
+ "model.layers.28.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
117
+ "model.layers.28.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
118
+ "model.layers.28.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
119
+ "model.layers.29.channel_mixer.l1.weight": "pytorch_model-00003-of-00003.bin",
120
+ "model.layers.29.channel_mixer.l2.weight": "pytorch_model-00003-of-00003.bin",
121
+ "model.layers.29.channel_mixer.l3.weight": "pytorch_model-00003-of-00003.bin",
122
+ "model.layers.29.token_mixer.out_proj.weight": "pytorch_model-00003-of-00003.bin",
123
+ "model.layers.29.token_mixer.qkvu_proj.weight": "pytorch_model-00003-of-00003.bin",
124
+ "model.layers.3.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.3.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
126
+ "model.layers.3.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
127
+ "model.layers.3.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
128
+ "model.layers.3.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.4.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.4.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.4.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.4.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.4.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.5.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.5.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.5.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.5.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.5.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
139
+ "model.layers.6.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
140
+ "model.layers.6.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
141
+ "model.layers.6.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
142
+ "model.layers.6.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
143
+ "model.layers.6.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
144
+ "model.layers.7.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
145
+ "model.layers.7.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
146
+ "model.layers.7.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
147
+ "model.layers.7.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
148
+ "model.layers.7.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
149
+ "model.layers.8.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
150
+ "model.layers.8.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
151
+ "model.layers.8.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
152
+ "model.layers.8.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
153
+ "model.layers.8.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin",
154
+ "model.layers.9.channel_mixer.l1.weight": "pytorch_model-00001-of-00003.bin",
155
+ "model.layers.9.channel_mixer.l2.weight": "pytorch_model-00001-of-00003.bin",
156
+ "model.layers.9.channel_mixer.l3.weight": "pytorch_model-00001-of-00003.bin",
157
+ "model.layers.9.token_mixer.out_proj.weight": "pytorch_model-00001-of-00003.bin",
158
+ "model.layers.9.token_mixer.qkvu_proj.weight": "pytorch_model-00001-of-00003.bin"
159
+ }
160
+ }