Hugging Face's logo

Sweson
/
Bora

Model card Files Community
Sweson commited on
Commit
dbc3d0a
•
1 Parent(s): 8ce5c03

Upload 5 files

Browse files
Files changed (5) hide show
  1. ema.pt +3 -0
  2. model/pytorch_model-00001.bin +3 -0
  3. model/pytorch_model-00002.bin +3 -0
  4. model/pytorch_model.bin.index.json +557 -0
  5. model_ckpt.pt +3 -0
ema.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace42ae8fd5cacbe9d87bd409c92faabebad940253e0dcb60ee775758c082240
3
+ size 3041991550
model/pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606e51d60df2fbf3448d2ab0d36ae5bd8560f261b065475cfaa25a9e75738d28
3
+ size 1063982720
model/pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428b5d3f7e31a8d2633747c955c6a068b3b2370a8c2e16a7810df98d949720df
3
+ size 457098752
model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,557 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1450.4495239257812
4
+ },
5
+ "weight_map": {
6
+ "pos_embed": "pytorch_model-00001.bin",
7
+ "pos_embed_temporal": "pytorch_model-00001.bin",
8
+ "x_embedder.proj.weight": "pytorch_model-00001.bin",
9
+ "x_embedder.proj.bias": "pytorch_model-00001.bin",
10
+ "t_embedder.mlp.0.weight": "pytorch_model-00001.bin",
11
+ "t_embedder.mlp.0.bias": "pytorch_model-00001.bin",
12
+ "t_embedder.mlp.2.weight": "pytorch_model-00001.bin",
13
+ "t_embedder.mlp.2.bias": "pytorch_model-00001.bin",
14
+ "t_block.1.weight": "pytorch_model-00001.bin",
15
+ "t_block.1.bias": "pytorch_model-00001.bin",
16
+ "y_embedder.y_embedding": "pytorch_model-00001.bin",
17
+ "y_embedder.y_proj.fc1.weight": "pytorch_model-00001.bin",
18
+ "y_embedder.y_proj.fc1.bias": "pytorch_model-00001.bin",
19
+ "y_embedder.y_proj.fc2.weight": "pytorch_model-00001.bin",
20
+ "y_embedder.y_proj.fc2.bias": "pytorch_model-00001.bin",
21
+ "blocks.0.scale_shift_table": "pytorch_model-00001.bin",
22
+ "blocks.0.attn.qkv.weight": "pytorch_model-00001.bin",
23
+ "blocks.0.attn.qkv.bias": "pytorch_model-00001.bin",
24
+ "blocks.0.attn.proj.weight": "pytorch_model-00001.bin",
25
+ "blocks.0.attn.proj.bias": "pytorch_model-00001.bin",
26
+ "blocks.0.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
27
+ "blocks.0.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
28
+ "blocks.0.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
29
+ "blocks.0.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
30
+ "blocks.0.cross_attn.proj.weight": "pytorch_model-00001.bin",
31
+ "blocks.0.cross_attn.proj.bias": "pytorch_model-00001.bin",
32
+ "blocks.0.mlp.fc1.weight": "pytorch_model-00001.bin",
33
+ "blocks.0.mlp.fc1.bias": "pytorch_model-00001.bin",
34
+ "blocks.0.mlp.fc2.weight": "pytorch_model-00001.bin",
35
+ "blocks.0.mlp.fc2.bias": "pytorch_model-00001.bin",
36
+ "blocks.0.attn_temp.qkv.weight": "pytorch_model-00001.bin",
37
+ "blocks.0.attn_temp.qkv.bias": "pytorch_model-00001.bin",
38
+ "blocks.0.attn_temp.proj.weight": "pytorch_model-00001.bin",
39
+ "blocks.0.attn_temp.proj.bias": "pytorch_model-00001.bin",
40
+ "blocks.1.scale_shift_table": "pytorch_model-00001.bin",
41
+ "blocks.1.attn.qkv.weight": "pytorch_model-00001.bin",
42
+ "blocks.1.attn.qkv.bias": "pytorch_model-00001.bin",
43
+ "blocks.1.attn.proj.weight": "pytorch_model-00001.bin",
44
+ "blocks.1.attn.proj.bias": "pytorch_model-00001.bin",
45
+ "blocks.1.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
46
+ "blocks.1.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
47
+ "blocks.1.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
48
+ "blocks.1.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
49
+ "blocks.1.cross_attn.proj.weight": "pytorch_model-00001.bin",
50
+ "blocks.1.cross_attn.proj.bias": "pytorch_model-00001.bin",
51
+ "blocks.1.mlp.fc1.weight": "pytorch_model-00001.bin",
52
+ "blocks.1.mlp.fc1.bias": "pytorch_model-00001.bin",
53
+ "blocks.1.mlp.fc2.weight": "pytorch_model-00001.bin",
54
+ "blocks.1.mlp.fc2.bias": "pytorch_model-00001.bin",
55
+ "blocks.1.attn_temp.qkv.weight": "pytorch_model-00001.bin",
56
+ "blocks.1.attn_temp.qkv.bias": "pytorch_model-00001.bin",
57
+ "blocks.1.attn_temp.proj.weight": "pytorch_model-00001.bin",
58
+ "blocks.1.attn_temp.proj.bias": "pytorch_model-00001.bin",
59
+ "blocks.2.scale_shift_table": "pytorch_model-00001.bin",
60
+ "blocks.2.attn.qkv.weight": "pytorch_model-00001.bin",
61
+ "blocks.2.attn.qkv.bias": "pytorch_model-00001.bin",
62
+ "blocks.2.attn.proj.weight": "pytorch_model-00001.bin",
63
+ "blocks.2.attn.proj.bias": "pytorch_model-00001.bin",
64
+ "blocks.2.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
65
+ "blocks.2.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
66
+ "blocks.2.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
67
+ "blocks.2.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
68
+ "blocks.2.cross_attn.proj.weight": "pytorch_model-00001.bin",
69
+ "blocks.2.cross_attn.proj.bias": "pytorch_model-00001.bin",
70
+ "blocks.2.mlp.fc1.weight": "pytorch_model-00001.bin",
71
+ "blocks.2.mlp.fc1.bias": "pytorch_model-00001.bin",
72
+ "blocks.2.mlp.fc2.weight": "pytorch_model-00001.bin",
73
+ "blocks.2.mlp.fc2.bias": "pytorch_model-00001.bin",
74
+ "blocks.2.attn_temp.qkv.weight": "pytorch_model-00001.bin",
75
+ "blocks.2.attn_temp.qkv.bias": "pytorch_model-00001.bin",
76
+ "blocks.2.attn_temp.proj.weight": "pytorch_model-00001.bin",
77
+ "blocks.2.attn_temp.proj.bias": "pytorch_model-00001.bin",
78
+ "blocks.3.scale_shift_table": "pytorch_model-00001.bin",
79
+ "blocks.3.attn.qkv.weight": "pytorch_model-00001.bin",
80
+ "blocks.3.attn.qkv.bias": "pytorch_model-00001.bin",
81
+ "blocks.3.attn.proj.weight": "pytorch_model-00001.bin",
82
+ "blocks.3.attn.proj.bias": "pytorch_model-00001.bin",
83
+ "blocks.3.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
84
+ "blocks.3.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
85
+ "blocks.3.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
86
+ "blocks.3.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
87
+ "blocks.3.cross_attn.proj.weight": "pytorch_model-00001.bin",
88
+ "blocks.3.cross_attn.proj.bias": "pytorch_model-00001.bin",
89
+ "blocks.3.mlp.fc1.weight": "pytorch_model-00001.bin",
90
+ "blocks.3.mlp.fc1.bias": "pytorch_model-00001.bin",
91
+ "blocks.3.mlp.fc2.weight": "pytorch_model-00001.bin",
92
+ "blocks.3.mlp.fc2.bias": "pytorch_model-00001.bin",
93
+ "blocks.3.attn_temp.qkv.weight": "pytorch_model-00001.bin",
94
+ "blocks.3.attn_temp.qkv.bias": "pytorch_model-00001.bin",
95
+ "blocks.3.attn_temp.proj.weight": "pytorch_model-00001.bin",
96
+ "blocks.3.attn_temp.proj.bias": "pytorch_model-00001.bin",
97
+ "blocks.4.scale_shift_table": "pytorch_model-00001.bin",
98
+ "blocks.4.attn.qkv.weight": "pytorch_model-00001.bin",
99
+ "blocks.4.attn.qkv.bias": "pytorch_model-00001.bin",
100
+ "blocks.4.attn.proj.weight": "pytorch_model-00001.bin",
101
+ "blocks.4.attn.proj.bias": "pytorch_model-00001.bin",
102
+ "blocks.4.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
103
+ "blocks.4.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
104
+ "blocks.4.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
105
+ "blocks.4.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
106
+ "blocks.4.cross_attn.proj.weight": "pytorch_model-00001.bin",
107
+ "blocks.4.cross_attn.proj.bias": "pytorch_model-00001.bin",
108
+ "blocks.4.mlp.fc1.weight": "pytorch_model-00001.bin",
109
+ "blocks.4.mlp.fc1.bias": "pytorch_model-00001.bin",
110
+ "blocks.4.mlp.fc2.weight": "pytorch_model-00001.bin",
111
+ "blocks.4.mlp.fc2.bias": "pytorch_model-00001.bin",
112
+ "blocks.4.attn_temp.qkv.weight": "pytorch_model-00001.bin",
113
+ "blocks.4.attn_temp.qkv.bias": "pytorch_model-00001.bin",
114
+ "blocks.4.attn_temp.proj.weight": "pytorch_model-00001.bin",
115
+ "blocks.4.attn_temp.proj.bias": "pytorch_model-00001.bin",
116
+ "blocks.5.scale_shift_table": "pytorch_model-00001.bin",
117
+ "blocks.5.attn.qkv.weight": "pytorch_model-00001.bin",
118
+ "blocks.5.attn.qkv.bias": "pytorch_model-00001.bin",
119
+ "blocks.5.attn.proj.weight": "pytorch_model-00001.bin",
120
+ "blocks.5.attn.proj.bias": "pytorch_model-00001.bin",
121
+ "blocks.5.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
122
+ "blocks.5.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
123
+ "blocks.5.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
124
+ "blocks.5.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
125
+ "blocks.5.cross_attn.proj.weight": "pytorch_model-00001.bin",
126
+ "blocks.5.cross_attn.proj.bias": "pytorch_model-00001.bin",
127
+ "blocks.5.mlp.fc1.weight": "pytorch_model-00001.bin",
128
+ "blocks.5.mlp.fc1.bias": "pytorch_model-00001.bin",
129
+ "blocks.5.mlp.fc2.weight": "pytorch_model-00001.bin",
130
+ "blocks.5.mlp.fc2.bias": "pytorch_model-00001.bin",
131
+ "blocks.5.attn_temp.qkv.weight": "pytorch_model-00001.bin",
132
+ "blocks.5.attn_temp.qkv.bias": "pytorch_model-00001.bin",
133
+ "blocks.5.attn_temp.proj.weight": "pytorch_model-00001.bin",
134
+ "blocks.5.attn_temp.proj.bias": "pytorch_model-00001.bin",
135
+ "blocks.6.scale_shift_table": "pytorch_model-00001.bin",
136
+ "blocks.6.attn.qkv.weight": "pytorch_model-00001.bin",
137
+ "blocks.6.attn.qkv.bias": "pytorch_model-00001.bin",
138
+ "blocks.6.attn.proj.weight": "pytorch_model-00001.bin",
139
+ "blocks.6.attn.proj.bias": "pytorch_model-00001.bin",
140
+ "blocks.6.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
141
+ "blocks.6.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
142
+ "blocks.6.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
143
+ "blocks.6.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
144
+ "blocks.6.cross_attn.proj.weight": "pytorch_model-00001.bin",
145
+ "blocks.6.cross_attn.proj.bias": "pytorch_model-00001.bin",
146
+ "blocks.6.mlp.fc1.weight": "pytorch_model-00001.bin",
147
+ "blocks.6.mlp.fc1.bias": "pytorch_model-00001.bin",
148
+ "blocks.6.mlp.fc2.weight": "pytorch_model-00001.bin",
149
+ "blocks.6.mlp.fc2.bias": "pytorch_model-00001.bin",
150
+ "blocks.6.attn_temp.qkv.weight": "pytorch_model-00001.bin",
151
+ "blocks.6.attn_temp.qkv.bias": "pytorch_model-00001.bin",
152
+ "blocks.6.attn_temp.proj.weight": "pytorch_model-00001.bin",
153
+ "blocks.6.attn_temp.proj.bias": "pytorch_model-00001.bin",
154
+ "blocks.7.scale_shift_table": "pytorch_model-00001.bin",
155
+ "blocks.7.attn.qkv.weight": "pytorch_model-00001.bin",
156
+ "blocks.7.attn.qkv.bias": "pytorch_model-00001.bin",
157
+ "blocks.7.attn.proj.weight": "pytorch_model-00001.bin",
158
+ "blocks.7.attn.proj.bias": "pytorch_model-00001.bin",
159
+ "blocks.7.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
160
+ "blocks.7.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
161
+ "blocks.7.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
162
+ "blocks.7.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
163
+ "blocks.7.cross_attn.proj.weight": "pytorch_model-00001.bin",
164
+ "blocks.7.cross_attn.proj.bias": "pytorch_model-00001.bin",
165
+ "blocks.7.mlp.fc1.weight": "pytorch_model-00001.bin",
166
+ "blocks.7.mlp.fc1.bias": "pytorch_model-00001.bin",
167
+ "blocks.7.mlp.fc2.weight": "pytorch_model-00001.bin",
168
+ "blocks.7.mlp.fc2.bias": "pytorch_model-00001.bin",
169
+ "blocks.7.attn_temp.qkv.weight": "pytorch_model-00001.bin",
170
+ "blocks.7.attn_temp.qkv.bias": "pytorch_model-00001.bin",
171
+ "blocks.7.attn_temp.proj.weight": "pytorch_model-00001.bin",
172
+ "blocks.7.attn_temp.proj.bias": "pytorch_model-00001.bin",
173
+ "blocks.8.scale_shift_table": "pytorch_model-00001.bin",
174
+ "blocks.8.attn.qkv.weight": "pytorch_model-00001.bin",
175
+ "blocks.8.attn.qkv.bias": "pytorch_model-00001.bin",
176
+ "blocks.8.attn.proj.weight": "pytorch_model-00001.bin",
177
+ "blocks.8.attn.proj.bias": "pytorch_model-00001.bin",
178
+ "blocks.8.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
179
+ "blocks.8.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
180
+ "blocks.8.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
181
+ "blocks.8.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
182
+ "blocks.8.cross_attn.proj.weight": "pytorch_model-00001.bin",
183
+ "blocks.8.cross_attn.proj.bias": "pytorch_model-00001.bin",
184
+ "blocks.8.mlp.fc1.weight": "pytorch_model-00001.bin",
185
+ "blocks.8.mlp.fc1.bias": "pytorch_model-00001.bin",
186
+ "blocks.8.mlp.fc2.weight": "pytorch_model-00001.bin",
187
+ "blocks.8.mlp.fc2.bias": "pytorch_model-00001.bin",
188
+ "blocks.8.attn_temp.qkv.weight": "pytorch_model-00001.bin",
189
+ "blocks.8.attn_temp.qkv.bias": "pytorch_model-00001.bin",
190
+ "blocks.8.attn_temp.proj.weight": "pytorch_model-00001.bin",
191
+ "blocks.8.attn_temp.proj.bias": "pytorch_model-00001.bin",
192
+ "blocks.9.scale_shift_table": "pytorch_model-00001.bin",
193
+ "blocks.9.attn.qkv.weight": "pytorch_model-00001.bin",
194
+ "blocks.9.attn.qkv.bias": "pytorch_model-00001.bin",
195
+ "blocks.9.attn.proj.weight": "pytorch_model-00001.bin",
196
+ "blocks.9.attn.proj.bias": "pytorch_model-00001.bin",
197
+ "blocks.9.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
198
+ "blocks.9.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
199
+ "blocks.9.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
200
+ "blocks.9.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
201
+ "blocks.9.cross_attn.proj.weight": "pytorch_model-00001.bin",
202
+ "blocks.9.cross_attn.proj.bias": "pytorch_model-00001.bin",
203
+ "blocks.9.mlp.fc1.weight": "pytorch_model-00001.bin",
204
+ "blocks.9.mlp.fc1.bias": "pytorch_model-00001.bin",
205
+ "blocks.9.mlp.fc2.weight": "pytorch_model-00001.bin",
206
+ "blocks.9.mlp.fc2.bias": "pytorch_model-00001.bin",
207
+ "blocks.9.attn_temp.qkv.weight": "pytorch_model-00001.bin",
208
+ "blocks.9.attn_temp.qkv.bias": "pytorch_model-00001.bin",
209
+ "blocks.9.attn_temp.proj.weight": "pytorch_model-00001.bin",
210
+ "blocks.9.attn_temp.proj.bias": "pytorch_model-00001.bin",
211
+ "blocks.10.scale_shift_table": "pytorch_model-00001.bin",
212
+ "blocks.10.attn.qkv.weight": "pytorch_model-00001.bin",
213
+ "blocks.10.attn.qkv.bias": "pytorch_model-00001.bin",
214
+ "blocks.10.attn.proj.weight": "pytorch_model-00001.bin",
215
+ "blocks.10.attn.proj.bias": "pytorch_model-00001.bin",
216
+ "blocks.10.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
217
+ "blocks.10.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
218
+ "blocks.10.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
219
+ "blocks.10.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
220
+ "blocks.10.cross_attn.proj.weight": "pytorch_model-00001.bin",
221
+ "blocks.10.cross_attn.proj.bias": "pytorch_model-00001.bin",
222
+ "blocks.10.mlp.fc1.weight": "pytorch_model-00001.bin",
223
+ "blocks.10.mlp.fc1.bias": "pytorch_model-00001.bin",
224
+ "blocks.10.mlp.fc2.weight": "pytorch_model-00001.bin",
225
+ "blocks.10.mlp.fc2.bias": "pytorch_model-00001.bin",
226
+ "blocks.10.attn_temp.qkv.weight": "pytorch_model-00001.bin",
227
+ "blocks.10.attn_temp.qkv.bias": "pytorch_model-00001.bin",
228
+ "blocks.10.attn_temp.proj.weight": "pytorch_model-00001.bin",
229
+ "blocks.10.attn_temp.proj.bias": "pytorch_model-00001.bin",
230
+ "blocks.11.scale_shift_table": "pytorch_model-00001.bin",
231
+ "blocks.11.attn.qkv.weight": "pytorch_model-00001.bin",
232
+ "blocks.11.attn.qkv.bias": "pytorch_model-00001.bin",
233
+ "blocks.11.attn.proj.weight": "pytorch_model-00001.bin",
234
+ "blocks.11.attn.proj.bias": "pytorch_model-00001.bin",
235
+ "blocks.11.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
236
+ "blocks.11.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
237
+ "blocks.11.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
238
+ "blocks.11.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
239
+ "blocks.11.cross_attn.proj.weight": "pytorch_model-00001.bin",
240
+ "blocks.11.cross_attn.proj.bias": "pytorch_model-00001.bin",
241
+ "blocks.11.mlp.fc1.weight": "pytorch_model-00001.bin",
242
+ "blocks.11.mlp.fc1.bias": "pytorch_model-00001.bin",
243
+ "blocks.11.mlp.fc2.weight": "pytorch_model-00001.bin",
244
+ "blocks.11.mlp.fc2.bias": "pytorch_model-00001.bin",
245
+ "blocks.11.attn_temp.qkv.weight": "pytorch_model-00001.bin",
246
+ "blocks.11.attn_temp.qkv.bias": "pytorch_model-00001.bin",
247
+ "blocks.11.attn_temp.proj.weight": "pytorch_model-00001.bin",
248
+ "blocks.11.attn_temp.proj.bias": "pytorch_model-00001.bin",
249
+ "blocks.12.scale_shift_table": "pytorch_model-00001.bin",
250
+ "blocks.12.attn.qkv.weight": "pytorch_model-00001.bin",
251
+ "blocks.12.attn.qkv.bias": "pytorch_model-00001.bin",
252
+ "blocks.12.attn.proj.weight": "pytorch_model-00001.bin",
253
+ "blocks.12.attn.proj.bias": "pytorch_model-00001.bin",
254
+ "blocks.12.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
255
+ "blocks.12.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
256
+ "blocks.12.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
257
+ "blocks.12.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
258
+ "blocks.12.cross_attn.proj.weight": "pytorch_model-00001.bin",
259
+ "blocks.12.cross_attn.proj.bias": "pytorch_model-00001.bin",
260
+ "blocks.12.mlp.fc1.weight": "pytorch_model-00001.bin",
261
+ "blocks.12.mlp.fc1.bias": "pytorch_model-00001.bin",
262
+ "blocks.12.mlp.fc2.weight": "pytorch_model-00001.bin",
263
+ "blocks.12.mlp.fc2.bias": "pytorch_model-00001.bin",
264
+ "blocks.12.attn_temp.qkv.weight": "pytorch_model-00001.bin",
265
+ "blocks.12.attn_temp.qkv.bias": "pytorch_model-00001.bin",
266
+ "blocks.12.attn_temp.proj.weight": "pytorch_model-00001.bin",
267
+ "blocks.12.attn_temp.proj.bias": "pytorch_model-00001.bin",
268
+ "blocks.13.scale_shift_table": "pytorch_model-00001.bin",
269
+ "blocks.13.attn.qkv.weight": "pytorch_model-00001.bin",
270
+ "blocks.13.attn.qkv.bias": "pytorch_model-00001.bin",
271
+ "blocks.13.attn.proj.weight": "pytorch_model-00001.bin",
272
+ "blocks.13.attn.proj.bias": "pytorch_model-00001.bin",
273
+ "blocks.13.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
274
+ "blocks.13.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
275
+ "blocks.13.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
276
+ "blocks.13.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
277
+ "blocks.13.cross_attn.proj.weight": "pytorch_model-00001.bin",
278
+ "blocks.13.cross_attn.proj.bias": "pytorch_model-00001.bin",
279
+ "blocks.13.mlp.fc1.weight": "pytorch_model-00001.bin",
280
+ "blocks.13.mlp.fc1.bias": "pytorch_model-00001.bin",
281
+ "blocks.13.mlp.fc2.weight": "pytorch_model-00001.bin",
282
+ "blocks.13.mlp.fc2.bias": "pytorch_model-00001.bin",
283
+ "blocks.13.attn_temp.qkv.weight": "pytorch_model-00001.bin",
284
+ "blocks.13.attn_temp.qkv.bias": "pytorch_model-00001.bin",
285
+ "blocks.13.attn_temp.proj.weight": "pytorch_model-00001.bin",
286
+ "blocks.13.attn_temp.proj.bias": "pytorch_model-00001.bin",
287
+ "blocks.14.scale_shift_table": "pytorch_model-00001.bin",
288
+ "blocks.14.attn.qkv.weight": "pytorch_model-00001.bin",
289
+ "blocks.14.attn.qkv.bias": "pytorch_model-00001.bin",
290
+ "blocks.14.attn.proj.weight": "pytorch_model-00001.bin",
291
+ "blocks.14.attn.proj.bias": "pytorch_model-00001.bin",
292
+ "blocks.14.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
293
+ "blocks.14.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
294
+ "blocks.14.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
295
+ "blocks.14.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
296
+ "blocks.14.cross_attn.proj.weight": "pytorch_model-00001.bin",
297
+ "blocks.14.cross_attn.proj.bias": "pytorch_model-00001.bin",
298
+ "blocks.14.mlp.fc1.weight": "pytorch_model-00001.bin",
299
+ "blocks.14.mlp.fc1.bias": "pytorch_model-00001.bin",
300
+ "blocks.14.mlp.fc2.weight": "pytorch_model-00001.bin",
301
+ "blocks.14.mlp.fc2.bias": "pytorch_model-00001.bin",
302
+ "blocks.14.attn_temp.qkv.weight": "pytorch_model-00001.bin",
303
+ "blocks.14.attn_temp.qkv.bias": "pytorch_model-00001.bin",
304
+ "blocks.14.attn_temp.proj.weight": "pytorch_model-00001.bin",
305
+ "blocks.14.attn_temp.proj.bias": "pytorch_model-00001.bin",
306
+ "blocks.15.scale_shift_table": "pytorch_model-00001.bin",
307
+ "blocks.15.attn.qkv.weight": "pytorch_model-00001.bin",
308
+ "blocks.15.attn.qkv.bias": "pytorch_model-00001.bin",
309
+ "blocks.15.attn.proj.weight": "pytorch_model-00001.bin",
310
+ "blocks.15.attn.proj.bias": "pytorch_model-00001.bin",
311
+ "blocks.15.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
312
+ "blocks.15.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
313
+ "blocks.15.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
314
+ "blocks.15.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
315
+ "blocks.15.cross_attn.proj.weight": "pytorch_model-00001.bin",
316
+ "blocks.15.cross_attn.proj.bias": "pytorch_model-00001.bin",
317
+ "blocks.15.mlp.fc1.weight": "pytorch_model-00001.bin",
318
+ "blocks.15.mlp.fc1.bias": "pytorch_model-00001.bin",
319
+ "blocks.15.mlp.fc2.weight": "pytorch_model-00001.bin",
320
+ "blocks.15.mlp.fc2.bias": "pytorch_model-00001.bin",
321
+ "blocks.15.attn_temp.qkv.weight": "pytorch_model-00001.bin",
322
+ "blocks.15.attn_temp.qkv.bias": "pytorch_model-00001.bin",
323
+ "blocks.15.attn_temp.proj.weight": "pytorch_model-00001.bin",
324
+ "blocks.15.attn_temp.proj.bias": "pytorch_model-00001.bin",
325
+ "blocks.16.scale_shift_table": "pytorch_model-00001.bin",
326
+ "blocks.16.attn.qkv.weight": "pytorch_model-00001.bin",
327
+ "blocks.16.attn.qkv.bias": "pytorch_model-00001.bin",
328
+ "blocks.16.attn.proj.weight": "pytorch_model-00001.bin",
329
+ "blocks.16.attn.proj.bias": "pytorch_model-00001.bin",
330
+ "blocks.16.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
331
+ "blocks.16.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
332
+ "blocks.16.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
333
+ "blocks.16.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
334
+ "blocks.16.cross_attn.proj.weight": "pytorch_model-00001.bin",
335
+ "blocks.16.cross_attn.proj.bias": "pytorch_model-00001.bin",
336
+ "blocks.16.mlp.fc1.weight": "pytorch_model-00001.bin",
337
+ "blocks.16.mlp.fc1.bias": "pytorch_model-00001.bin",
338
+ "blocks.16.mlp.fc2.weight": "pytorch_model-00001.bin",
339
+ "blocks.16.mlp.fc2.bias": "pytorch_model-00001.bin",
340
+ "blocks.16.attn_temp.qkv.weight": "pytorch_model-00001.bin",
341
+ "blocks.16.attn_temp.qkv.bias": "pytorch_model-00001.bin",
342
+ "blocks.16.attn_temp.proj.weight": "pytorch_model-00001.bin",
343
+ "blocks.16.attn_temp.proj.bias": "pytorch_model-00001.bin",
344
+ "blocks.17.scale_shift_table": "pytorch_model-00001.bin",
345
+ "blocks.17.attn.qkv.weight": "pytorch_model-00001.bin",
346
+ "blocks.17.attn.qkv.bias": "pytorch_model-00001.bin",
347
+ "blocks.17.attn.proj.weight": "pytorch_model-00001.bin",
348
+ "blocks.17.attn.proj.bias": "pytorch_model-00001.bin",
349
+ "blocks.17.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
350
+ "blocks.17.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
351
+ "blocks.17.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
352
+ "blocks.17.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
353
+ "blocks.17.cross_attn.proj.weight": "pytorch_model-00001.bin",
354
+ "blocks.17.cross_attn.proj.bias": "pytorch_model-00001.bin",
355
+ "blocks.17.mlp.fc1.weight": "pytorch_model-00001.bin",
356
+ "blocks.17.mlp.fc1.bias": "pytorch_model-00001.bin",
357
+ "blocks.17.mlp.fc2.weight": "pytorch_model-00001.bin",
358
+ "blocks.17.mlp.fc2.bias": "pytorch_model-00001.bin",
359
+ "blocks.17.attn_temp.qkv.weight": "pytorch_model-00001.bin",
360
+ "blocks.17.attn_temp.qkv.bias": "pytorch_model-00001.bin",
361
+ "blocks.17.attn_temp.proj.weight": "pytorch_model-00001.bin",
362
+ "blocks.17.attn_temp.proj.bias": "pytorch_model-00001.bin",
363
+ "blocks.18.scale_shift_table": "pytorch_model-00001.bin",
364
+ "blocks.18.attn.qkv.weight": "pytorch_model-00001.bin",
365
+ "blocks.18.attn.qkv.bias": "pytorch_model-00001.bin",
366
+ "blocks.18.attn.proj.weight": "pytorch_model-00001.bin",
367
+ "blocks.18.attn.proj.bias": "pytorch_model-00001.bin",
368
+ "blocks.18.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
369
+ "blocks.18.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
370
+ "blocks.18.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
371
+ "blocks.18.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
372
+ "blocks.18.cross_attn.proj.weight": "pytorch_model-00001.bin",
373
+ "blocks.18.cross_attn.proj.bias": "pytorch_model-00001.bin",
374
+ "blocks.18.mlp.fc1.weight": "pytorch_model-00001.bin",
375
+ "blocks.18.mlp.fc1.bias": "pytorch_model-00001.bin",
376
+ "blocks.18.mlp.fc2.weight": "pytorch_model-00001.bin",
377
+ "blocks.18.mlp.fc2.bias": "pytorch_model-00001.bin",
378
+ "blocks.18.attn_temp.qkv.weight": "pytorch_model-00001.bin",
379
+ "blocks.18.attn_temp.qkv.bias": "pytorch_model-00001.bin",
380
+ "blocks.18.attn_temp.proj.weight": "pytorch_model-00001.bin",
381
+ "blocks.18.attn_temp.proj.bias": "pytorch_model-00001.bin",
382
+ "blocks.19.scale_shift_table": "pytorch_model-00001.bin",
383
+ "blocks.19.attn.qkv.weight": "pytorch_model-00001.bin",
384
+ "blocks.19.attn.qkv.bias": "pytorch_model-00001.bin",
385
+ "blocks.19.attn.proj.weight": "pytorch_model-00001.bin",
386
+ "blocks.19.attn.proj.bias": "pytorch_model-00001.bin",
387
+ "blocks.19.cross_attn.q_linear.weight": "pytorch_model-00001.bin",
388
+ "blocks.19.cross_attn.q_linear.bias": "pytorch_model-00001.bin",
389
+ "blocks.19.cross_attn.kv_linear.weight": "pytorch_model-00001.bin",
390
+ "blocks.19.cross_attn.kv_linear.bias": "pytorch_model-00001.bin",
391
+ "blocks.19.cross_attn.proj.weight": "pytorch_model-00001.bin",
392
+ "blocks.19.cross_attn.proj.bias": "pytorch_model-00001.bin",
393
+ "blocks.19.mlp.fc1.weight": "pytorch_model-00002.bin",
394
+ "blocks.19.mlp.fc1.bias": "pytorch_model-00002.bin",
395
+ "blocks.19.mlp.fc2.weight": "pytorch_model-00002.bin",
396
+ "blocks.19.mlp.fc2.bias": "pytorch_model-00002.bin",
397
+ "blocks.19.attn_temp.qkv.weight": "pytorch_model-00002.bin",
398
+ "blocks.19.attn_temp.qkv.bias": "pytorch_model-00002.bin",
399
+ "blocks.19.attn_temp.proj.weight": "pytorch_model-00002.bin",
400
+ "blocks.19.attn_temp.proj.bias": "pytorch_model-00002.bin",
401
+ "blocks.20.scale_shift_table": "pytorch_model-00002.bin",
402
+ "blocks.20.attn.qkv.weight": "pytorch_model-00002.bin",
403
+ "blocks.20.attn.qkv.bias": "pytorch_model-00002.bin",
404
+ "blocks.20.attn.proj.weight": "pytorch_model-00002.bin",
405
+ "blocks.20.attn.proj.bias": "pytorch_model-00002.bin",
406
+ "blocks.20.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
407
+ "blocks.20.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
408
+ "blocks.20.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
409
+ "blocks.20.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
410
+ "blocks.20.cross_attn.proj.weight": "pytorch_model-00002.bin",
411
+ "blocks.20.cross_attn.proj.bias": "pytorch_model-00002.bin",
412
+ "blocks.20.mlp.fc1.weight": "pytorch_model-00002.bin",
413
+ "blocks.20.mlp.fc1.bias": "pytorch_model-00002.bin",
414
+ "blocks.20.mlp.fc2.weight": "pytorch_model-00002.bin",
415
+ "blocks.20.mlp.fc2.bias": "pytorch_model-00002.bin",
416
+ "blocks.20.attn_temp.qkv.weight": "pytorch_model-00002.bin",
417
+ "blocks.20.attn_temp.qkv.bias": "pytorch_model-00002.bin",
418
+ "blocks.20.attn_temp.proj.weight": "pytorch_model-00002.bin",
419
+ "blocks.20.attn_temp.proj.bias": "pytorch_model-00002.bin",
420
+ "blocks.21.scale_shift_table": "pytorch_model-00002.bin",
421
+ "blocks.21.attn.qkv.weight": "pytorch_model-00002.bin",
422
+ "blocks.21.attn.qkv.bias": "pytorch_model-00002.bin",
423
+ "blocks.21.attn.proj.weight": "pytorch_model-00002.bin",
424
+ "blocks.21.attn.proj.bias": "pytorch_model-00002.bin",
425
+ "blocks.21.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
426
+ "blocks.21.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
427
+ "blocks.21.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
428
+ "blocks.21.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
429
+ "blocks.21.cross_attn.proj.weight": "pytorch_model-00002.bin",
430
+ "blocks.21.cross_attn.proj.bias": "pytorch_model-00002.bin",
431
+ "blocks.21.mlp.fc1.weight": "pytorch_model-00002.bin",
432
+ "blocks.21.mlp.fc1.bias": "pytorch_model-00002.bin",
433
+ "blocks.21.mlp.fc2.weight": "pytorch_model-00002.bin",
434
+ "blocks.21.mlp.fc2.bias": "pytorch_model-00002.bin",
435
+ "blocks.21.attn_temp.qkv.weight": "pytorch_model-00002.bin",
436
+ "blocks.21.attn_temp.qkv.bias": "pytorch_model-00002.bin",
437
+ "blocks.21.attn_temp.proj.weight": "pytorch_model-00002.bin",
438
+ "blocks.21.attn_temp.proj.bias": "pytorch_model-00002.bin",
439
+ "blocks.22.scale_shift_table": "pytorch_model-00002.bin",
440
+ "blocks.22.attn.qkv.weight": "pytorch_model-00002.bin",
441
+ "blocks.22.attn.qkv.bias": "pytorch_model-00002.bin",
442
+ "blocks.22.attn.proj.weight": "pytorch_model-00002.bin",
443
+ "blocks.22.attn.proj.bias": "pytorch_model-00002.bin",
444
+ "blocks.22.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
445
+ "blocks.22.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
446
+ "blocks.22.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
447
+ "blocks.22.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
448
+ "blocks.22.cross_attn.proj.weight": "pytorch_model-00002.bin",
449
+ "blocks.22.cross_attn.proj.bias": "pytorch_model-00002.bin",
450
+ "blocks.22.mlp.fc1.weight": "pytorch_model-00002.bin",
451
+ "blocks.22.mlp.fc1.bias": "pytorch_model-00002.bin",
452
+ "blocks.22.mlp.fc2.weight": "pytorch_model-00002.bin",
453
+ "blocks.22.mlp.fc2.bias": "pytorch_model-00002.bin",
454
+ "blocks.22.attn_temp.qkv.weight": "pytorch_model-00002.bin",
455
+ "blocks.22.attn_temp.qkv.bias": "pytorch_model-00002.bin",
456
+ "blocks.22.attn_temp.proj.weight": "pytorch_model-00002.bin",
457
+ "blocks.22.attn_temp.proj.bias": "pytorch_model-00002.bin",
458
+ "blocks.23.scale_shift_table": "pytorch_model-00002.bin",
459
+ "blocks.23.attn.qkv.weight": "pytorch_model-00002.bin",
460
+ "blocks.23.attn.qkv.bias": "pytorch_model-00002.bin",
461
+ "blocks.23.attn.proj.weight": "pytorch_model-00002.bin",
462
+ "blocks.23.attn.proj.bias": "pytorch_model-00002.bin",
463
+ "blocks.23.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
464
+ "blocks.23.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
465
+ "blocks.23.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
466
+ "blocks.23.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
467
+ "blocks.23.cross_attn.proj.weight": "pytorch_model-00002.bin",
468
+ "blocks.23.cross_attn.proj.bias": "pytorch_model-00002.bin",
469
+ "blocks.23.mlp.fc1.weight": "pytorch_model-00002.bin",
470
+ "blocks.23.mlp.fc1.bias": "pytorch_model-00002.bin",
471
+ "blocks.23.mlp.fc2.weight": "pytorch_model-00002.bin",
472
+ "blocks.23.mlp.fc2.bias": "pytorch_model-00002.bin",
473
+ "blocks.23.attn_temp.qkv.weight": "pytorch_model-00002.bin",
474
+ "blocks.23.attn_temp.qkv.bias": "pytorch_model-00002.bin",
475
+ "blocks.23.attn_temp.proj.weight": "pytorch_model-00002.bin",
476
+ "blocks.23.attn_temp.proj.bias": "pytorch_model-00002.bin",
477
+ "blocks.24.scale_shift_table": "pytorch_model-00002.bin",
478
+ "blocks.24.attn.qkv.weight": "pytorch_model-00002.bin",
479
+ "blocks.24.attn.qkv.bias": "pytorch_model-00002.bin",
480
+ "blocks.24.attn.proj.weight": "pytorch_model-00002.bin",
481
+ "blocks.24.attn.proj.bias": "pytorch_model-00002.bin",
482
+ "blocks.24.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
483
+ "blocks.24.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
484
+ "blocks.24.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
485
+ "blocks.24.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
486
+ "blocks.24.cross_attn.proj.weight": "pytorch_model-00002.bin",
487
+ "blocks.24.cross_attn.proj.bias": "pytorch_model-00002.bin",
488
+ "blocks.24.mlp.fc1.weight": "pytorch_model-00002.bin",
489
+ "blocks.24.mlp.fc1.bias": "pytorch_model-00002.bin",
490
+ "blocks.24.mlp.fc2.weight": "pytorch_model-00002.bin",
491
+ "blocks.24.mlp.fc2.bias": "pytorch_model-00002.bin",
492
+ "blocks.24.attn_temp.qkv.weight": "pytorch_model-00002.bin",
493
+ "blocks.24.attn_temp.qkv.bias": "pytorch_model-00002.bin",
494
+ "blocks.24.attn_temp.proj.weight": "pytorch_model-00002.bin",
495
+ "blocks.24.attn_temp.proj.bias": "pytorch_model-00002.bin",
496
+ "blocks.25.scale_shift_table": "pytorch_model-00002.bin",
497
+ "blocks.25.attn.qkv.weight": "pytorch_model-00002.bin",
498
+ "blocks.25.attn.qkv.bias": "pytorch_model-00002.bin",
499
+ "blocks.25.attn.proj.weight": "pytorch_model-00002.bin",
500
+ "blocks.25.attn.proj.bias": "pytorch_model-00002.bin",
501
+ "blocks.25.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
502
+ "blocks.25.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
503
+ "blocks.25.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
504
+ "blocks.25.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
505
+ "blocks.25.cross_attn.proj.weight": "pytorch_model-00002.bin",
506
+ "blocks.25.cross_attn.proj.bias": "pytorch_model-00002.bin",
507
+ "blocks.25.mlp.fc1.weight": "pytorch_model-00002.bin",
508
+ "blocks.25.mlp.fc1.bias": "pytorch_model-00002.bin",
509
+ "blocks.25.mlp.fc2.weight": "pytorch_model-00002.bin",
510
+ "blocks.25.mlp.fc2.bias": "pytorch_model-00002.bin",
511
+ "blocks.25.attn_temp.qkv.weight": "pytorch_model-00002.bin",
512
+ "blocks.25.attn_temp.qkv.bias": "pytorch_model-00002.bin",
513
+ "blocks.25.attn_temp.proj.weight": "pytorch_model-00002.bin",
514
+ "blocks.25.attn_temp.proj.bias": "pytorch_model-00002.bin",
515
+ "blocks.26.scale_shift_table": "pytorch_model-00002.bin",
516
+ "blocks.26.attn.qkv.weight": "pytorch_model-00002.bin",
517
+ "blocks.26.attn.qkv.bias": "pytorch_model-00002.bin",
518
+ "blocks.26.attn.proj.weight": "pytorch_model-00002.bin",
519
+ "blocks.26.attn.proj.bias": "pytorch_model-00002.bin",
520
+ "blocks.26.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
521
+ "blocks.26.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
522
+ "blocks.26.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
523
+ "blocks.26.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
524
+ "blocks.26.cross_attn.proj.weight": "pytorch_model-00002.bin",
525
+ "blocks.26.cross_attn.proj.bias": "pytorch_model-00002.bin",
526
+ "blocks.26.mlp.fc1.weight": "pytorch_model-00002.bin",
527
+ "blocks.26.mlp.fc1.bias": "pytorch_model-00002.bin",
528
+ "blocks.26.mlp.fc2.weight": "pytorch_model-00002.bin",
529
+ "blocks.26.mlp.fc2.bias": "pytorch_model-00002.bin",
530
+ "blocks.26.attn_temp.qkv.weight": "pytorch_model-00002.bin",
531
+ "blocks.26.attn_temp.qkv.bias": "pytorch_model-00002.bin",
532
+ "blocks.26.attn_temp.proj.weight": "pytorch_model-00002.bin",
533
+ "blocks.26.attn_temp.proj.bias": "pytorch_model-00002.bin",
534
+ "blocks.27.scale_shift_table": "pytorch_model-00002.bin",
535
+ "blocks.27.attn.qkv.weight": "pytorch_model-00002.bin",
536
+ "blocks.27.attn.qkv.bias": "pytorch_model-00002.bin",
537
+ "blocks.27.attn.proj.weight": "pytorch_model-00002.bin",
538
+ "blocks.27.attn.proj.bias": "pytorch_model-00002.bin",
539
+ "blocks.27.cross_attn.q_linear.weight": "pytorch_model-00002.bin",
540
+ "blocks.27.cross_attn.q_linear.bias": "pytorch_model-00002.bin",
541
+ "blocks.27.cross_attn.kv_linear.weight": "pytorch_model-00002.bin",
542
+ "blocks.27.cross_attn.kv_linear.bias": "pytorch_model-00002.bin",
543
+ "blocks.27.cross_attn.proj.weight": "pytorch_model-00002.bin",
544
+ "blocks.27.cross_attn.proj.bias": "pytorch_model-00002.bin",
545
+ "blocks.27.mlp.fc1.weight": "pytorch_model-00002.bin",
546
+ "blocks.27.mlp.fc1.bias": "pytorch_model-00002.bin",
547
+ "blocks.27.mlp.fc2.weight": "pytorch_model-00002.bin",
548
+ "blocks.27.mlp.fc2.bias": "pytorch_model-00002.bin",
549
+ "blocks.27.attn_temp.qkv.weight": "pytorch_model-00002.bin",
550
+ "blocks.27.attn_temp.qkv.bias": "pytorch_model-00002.bin",
551
+ "blocks.27.attn_temp.proj.weight": "pytorch_model-00002.bin",
552
+ "blocks.27.attn_temp.proj.bias": "pytorch_model-00002.bin",
553
+ "final_layer.scale_shift_table": "pytorch_model-00002.bin",
554
+ "final_layer.linear.weight": "pytorch_model-00002.bin",
555
+ "final_layer.linear.bias": "pytorch_model-00002.bin"
556
+ }
557
+ }
model_ckpt.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d99dfc7bd1d786b1a2c61913eeb5e77a0a6a86d4e068157e15dcc83c8f792c
3
+ size 3042022948