flozi00 commited on
Commit
0070f30
1 Parent(s): d14ad33

Upload RWForCausalLM

Browse files
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab0333898847880e61ef817c53afde2ceffe3b79f1c64bd984e14683d4b771c
3
+ size 9951171745
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7bd4fb89360ee3d0f4acff5d9eeaa6b6d07de7c0b56e2f2690ea4a4a3299ca
3
+ size 3892482321
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13843586816
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
8
+ "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
100
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
104
+ "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
106
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
107
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
108
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
109
+ "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
110
+ "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
111
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
112
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
113
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
114
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
115
+ "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
116
+ "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
118
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
119
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
120
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
121
+ "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
122
+ "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
123
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
124
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
125
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
126
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
127
+ "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
128
+ "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
130
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
131
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
132
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
133
+ "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
134
+ "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
136
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
137
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
138
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
139
+ "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
140
+ "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
142
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
143
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
144
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
145
+ "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
152
+ "transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
154
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
155
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
156
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
157
+ "transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
158
+ "transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
160
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
161
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
162
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
163
+ "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
200
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
201
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
202
+ }
203
+ }