Hugging Face's logo

austinsilveria
/
tricksy-opt-6.7b

Model card Files Community
1

Upload folder using huggingface_hub

#1
by austinsilveria - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+648
-0
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. .gitattributes +162 -0
  2. decoder.embed_positions.weight +3 -0
  3. decoder.embed_tokens.weight +3 -0
  4. decoder.final_layer_norm.bias +0 -0
  5. decoder.final_layer_norm.weight +0 -0
  6. decoder.layers.0.attn.mlp-sparsity-predictor.1.weight +3 -0
  7. decoder.layers.0.attn.mlp-sparsity-predictor.2.weight +3 -0
  8. decoder.layers.0.fc1.bias +0 -0
  9. decoder.layers.0.fc1.weight +3 -0
  10. decoder.layers.0.fc2.bias +0 -0
  11. decoder.layers.0.fc2.weight +3 -0
  12. decoder.layers.0.final_layer_norm.bias +0 -0
  13. decoder.layers.0.final_layer_norm.weight +0 -0
  14. decoder.layers.0.self_attn.catted_head_biases +0 -0
  15. decoder.layers.0.self_attn.catted_head_weights +3 -0
  16. decoder.layers.0.self_attn.out_proj.bias +0 -0
  17. decoder.layers.0.self_attn_layer_norm.bias +0 -0
  18. decoder.layers.0.self_attn_layer_norm.weight +0 -0
  19. decoder.layers.1.attn.mlp-sparsity-predictor.1.weight +3 -0
  20. decoder.layers.1.attn.mlp-sparsity-predictor.2.weight +3 -0
  21. decoder.layers.1.fc1.bias +0 -0
  22. decoder.layers.1.fc1.weight +3 -0
  23. decoder.layers.1.fc2.bias +0 -0
  24. decoder.layers.1.fc2.weight +3 -0
  25. decoder.layers.1.final_layer_norm.bias +0 -0
  26. decoder.layers.1.final_layer_norm.weight +0 -0
  27. decoder.layers.1.self_attn.catted_head_biases +0 -0
  28. decoder.layers.1.self_attn.catted_head_weights +3 -0
  29. decoder.layers.1.self_attn.out_proj.bias +0 -0
  30. decoder.layers.1.self_attn_layer_norm.bias +0 -0
  31. decoder.layers.1.self_attn_layer_norm.weight +0 -0
  32. decoder.layers.10.attn.mlp-sparsity-predictor.1.weight +3 -0
  33. decoder.layers.10.attn.mlp-sparsity-predictor.2.weight +3 -0
  34. decoder.layers.10.fc1.bias +0 -0
  35. decoder.layers.10.fc1.weight +3 -0
  36. decoder.layers.10.fc2.bias +0 -0
  37. decoder.layers.10.fc2.weight +3 -0
  38. decoder.layers.10.final_layer_norm.bias +0 -0
  39. decoder.layers.10.final_layer_norm.weight +0 -0
  40. decoder.layers.10.self_attn.catted_head_biases +0 -0
  41. decoder.layers.10.self_attn.catted_head_weights +3 -0
  42. decoder.layers.10.self_attn.out_proj.bias +0 -0
  43. decoder.layers.10.self_attn_layer_norm.bias +0 -0
  44. decoder.layers.10.self_attn_layer_norm.weight +0 -0
  45. decoder.layers.11.attn.mlp-sparsity-predictor.1.weight +3 -0
  46. decoder.layers.11.attn.mlp-sparsity-predictor.2.weight +3 -0
  47. decoder.layers.11.fc1.bias +0 -0
  48. decoder.layers.11.fc1.weight +3 -0
  49. decoder.layers.11.fc2.bias +0 -0
  50. decoder.layers.11.fc2.weight +3 -0
.gitattributes CHANGED
@@ -33,3 +33,165 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ decoder.embed_positions.weight filter=lfs diff=lfs merge=lfs -text
37
+ decoder.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
38
+ decoder.layers.0.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
39
+ decoder.layers.0.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
40
+ decoder.layers.0.fc1.weight filter=lfs diff=lfs merge=lfs -text
41
+ decoder.layers.0.fc2.weight filter=lfs diff=lfs merge=lfs -text
42
+ decoder.layers.0.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
43
+ decoder.layers.1.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
44
+ decoder.layers.1.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
45
+ decoder.layers.1.fc1.weight filter=lfs diff=lfs merge=lfs -text
46
+ decoder.layers.1.fc2.weight filter=lfs diff=lfs merge=lfs -text
47
+ decoder.layers.1.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
48
+ decoder.layers.10.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
49
+ decoder.layers.10.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
50
+ decoder.layers.10.fc1.weight filter=lfs diff=lfs merge=lfs -text
51
+ decoder.layers.10.fc2.weight filter=lfs diff=lfs merge=lfs -text
52
+ decoder.layers.10.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
53
+ decoder.layers.11.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
54
+ decoder.layers.11.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
55
+ decoder.layers.11.fc1.weight filter=lfs diff=lfs merge=lfs -text
56
+ decoder.layers.11.fc2.weight filter=lfs diff=lfs merge=lfs -text
57
+ decoder.layers.11.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
58
+ decoder.layers.12.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
59
+ decoder.layers.12.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
60
+ decoder.layers.12.fc1.weight filter=lfs diff=lfs merge=lfs -text
61
+ decoder.layers.12.fc2.weight filter=lfs diff=lfs merge=lfs -text
62
+ decoder.layers.12.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
63
+ decoder.layers.13.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
64
+ decoder.layers.13.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
65
+ decoder.layers.13.fc1.weight filter=lfs diff=lfs merge=lfs -text
66
+ decoder.layers.13.fc2.weight filter=lfs diff=lfs merge=lfs -text
67
+ decoder.layers.13.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
68
+ decoder.layers.14.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
69
+ decoder.layers.14.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
70
+ decoder.layers.14.fc1.weight filter=lfs diff=lfs merge=lfs -text
71
+ decoder.layers.14.fc2.weight filter=lfs diff=lfs merge=lfs -text
72
+ decoder.layers.14.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
73
+ decoder.layers.15.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
74
+ decoder.layers.15.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
75
+ decoder.layers.15.fc1.weight filter=lfs diff=lfs merge=lfs -text
76
+ decoder.layers.15.fc2.weight filter=lfs diff=lfs merge=lfs -text
77
+ decoder.layers.15.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
78
+ decoder.layers.16.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
79
+ decoder.layers.16.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
80
+ decoder.layers.16.fc1.weight filter=lfs diff=lfs merge=lfs -text
81
+ decoder.layers.16.fc2.weight filter=lfs diff=lfs merge=lfs -text
82
+ decoder.layers.16.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
83
+ decoder.layers.17.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
84
+ decoder.layers.17.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
85
+ decoder.layers.17.fc1.weight filter=lfs diff=lfs merge=lfs -text
86
+ decoder.layers.17.fc2.weight filter=lfs diff=lfs merge=lfs -text
87
+ decoder.layers.17.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
88
+ decoder.layers.18.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
89
+ decoder.layers.18.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
90
+ decoder.layers.18.fc1.weight filter=lfs diff=lfs merge=lfs -text
91
+ decoder.layers.18.fc2.weight filter=lfs diff=lfs merge=lfs -text
92
+ decoder.layers.18.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
93
+ decoder.layers.19.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
94
+ decoder.layers.19.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
95
+ decoder.layers.19.fc1.weight filter=lfs diff=lfs merge=lfs -text
96
+ decoder.layers.19.fc2.weight filter=lfs diff=lfs merge=lfs -text
97
+ decoder.layers.19.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
98
+ decoder.layers.2.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
99
+ decoder.layers.2.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
100
+ decoder.layers.2.fc1.weight filter=lfs diff=lfs merge=lfs -text
101
+ decoder.layers.2.fc2.weight filter=lfs diff=lfs merge=lfs -text
102
+ decoder.layers.2.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
103
+ decoder.layers.20.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
104
+ decoder.layers.20.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
105
+ decoder.layers.20.fc1.weight filter=lfs diff=lfs merge=lfs -text
106
+ decoder.layers.20.fc2.weight filter=lfs diff=lfs merge=lfs -text
107
+ decoder.layers.20.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
108
+ decoder.layers.21.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
109
+ decoder.layers.21.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
110
+ decoder.layers.21.fc1.weight filter=lfs diff=lfs merge=lfs -text
111
+ decoder.layers.21.fc2.weight filter=lfs diff=lfs merge=lfs -text
112
+ decoder.layers.21.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
113
+ decoder.layers.22.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
114
+ decoder.layers.22.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
115
+ decoder.layers.22.fc1.weight filter=lfs diff=lfs merge=lfs -text
116
+ decoder.layers.22.fc2.weight filter=lfs diff=lfs merge=lfs -text
117
+ decoder.layers.22.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
118
+ decoder.layers.23.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
119
+ decoder.layers.23.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
120
+ decoder.layers.23.fc1.weight filter=lfs diff=lfs merge=lfs -text
121
+ decoder.layers.23.fc2.weight filter=lfs diff=lfs merge=lfs -text
122
+ decoder.layers.23.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
123
+ decoder.layers.24.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
124
+ decoder.layers.24.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
125
+ decoder.layers.24.fc1.weight filter=lfs diff=lfs merge=lfs -text
126
+ decoder.layers.24.fc2.weight filter=lfs diff=lfs merge=lfs -text
127
+ decoder.layers.24.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
128
+ decoder.layers.25.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
129
+ decoder.layers.25.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
130
+ decoder.layers.25.fc1.weight filter=lfs diff=lfs merge=lfs -text
131
+ decoder.layers.25.fc2.weight filter=lfs diff=lfs merge=lfs -text
132
+ decoder.layers.25.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
133
+ decoder.layers.26.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
134
+ decoder.layers.26.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
135
+ decoder.layers.26.fc1.weight filter=lfs diff=lfs merge=lfs -text
136
+ decoder.layers.26.fc2.weight filter=lfs diff=lfs merge=lfs -text
137
+ decoder.layers.26.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
138
+ decoder.layers.27.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
139
+ decoder.layers.27.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
140
+ decoder.layers.27.fc1.weight filter=lfs diff=lfs merge=lfs -text
141
+ decoder.layers.27.fc2.weight filter=lfs diff=lfs merge=lfs -text
142
+ decoder.layers.27.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
143
+ decoder.layers.28.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
144
+ decoder.layers.28.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
145
+ decoder.layers.28.fc1.weight filter=lfs diff=lfs merge=lfs -text
146
+ decoder.layers.28.fc2.weight filter=lfs diff=lfs merge=lfs -text
147
+ decoder.layers.28.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
148
+ decoder.layers.29.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
149
+ decoder.layers.29.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
150
+ decoder.layers.29.fc1.weight filter=lfs diff=lfs merge=lfs -text
151
+ decoder.layers.29.fc2.weight filter=lfs diff=lfs merge=lfs -text
152
+ decoder.layers.29.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
153
+ decoder.layers.3.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
154
+ decoder.layers.3.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
155
+ decoder.layers.3.fc1.weight filter=lfs diff=lfs merge=lfs -text
156
+ decoder.layers.3.fc2.weight filter=lfs diff=lfs merge=lfs -text
157
+ decoder.layers.3.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
158
+ decoder.layers.30.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
159
+ decoder.layers.30.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
160
+ decoder.layers.30.fc1.weight filter=lfs diff=lfs merge=lfs -text
161
+ decoder.layers.30.fc2.weight filter=lfs diff=lfs merge=lfs -text
162
+ decoder.layers.30.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
163
+ decoder.layers.31.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
164
+ decoder.layers.31.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
165
+ decoder.layers.31.fc1.weight filter=lfs diff=lfs merge=lfs -text
166
+ decoder.layers.31.fc2.weight filter=lfs diff=lfs merge=lfs -text
167
+ decoder.layers.31.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
168
+ decoder.layers.4.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
169
+ decoder.layers.4.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
170
+ decoder.layers.4.fc1.weight filter=lfs diff=lfs merge=lfs -text
171
+ decoder.layers.4.fc2.weight filter=lfs diff=lfs merge=lfs -text
172
+ decoder.layers.4.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
173
+ decoder.layers.5.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
174
+ decoder.layers.5.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
175
+ decoder.layers.5.fc1.weight filter=lfs diff=lfs merge=lfs -text
176
+ decoder.layers.5.fc2.weight filter=lfs diff=lfs merge=lfs -text
177
+ decoder.layers.5.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
178
+ decoder.layers.6.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
179
+ decoder.layers.6.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
180
+ decoder.layers.6.fc1.weight filter=lfs diff=lfs merge=lfs -text
181
+ decoder.layers.6.fc2.weight filter=lfs diff=lfs merge=lfs -text
182
+ decoder.layers.6.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
183
+ decoder.layers.7.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
184
+ decoder.layers.7.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
185
+ decoder.layers.7.fc1.weight filter=lfs diff=lfs merge=lfs -text
186
+ decoder.layers.7.fc2.weight filter=lfs diff=lfs merge=lfs -text
187
+ decoder.layers.7.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
188
+ decoder.layers.8.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
189
+ decoder.layers.8.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
190
+ decoder.layers.8.fc1.weight filter=lfs diff=lfs merge=lfs -text
191
+ decoder.layers.8.fc2.weight filter=lfs diff=lfs merge=lfs -text
192
+ decoder.layers.8.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
193
+ decoder.layers.9.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
194
+ decoder.layers.9.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
195
+ decoder.layers.9.fc1.weight filter=lfs diff=lfs merge=lfs -text
196
+ decoder.layers.9.fc2.weight filter=lfs diff=lfs merge=lfs -text
197
+ decoder.layers.9.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
decoder.embed_positions.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99409a66a54c1814f4eb2babef878e82420fc42d79a1eb62f2c5994aef4bcae
3
+ size 16793600
decoder.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f71222f1b3324dfc52c36f06f5e853ead9d4b8675f06ca2fba1f8cb711dc6d3
3
+ size 411828224
decoder.final_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.final_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.attn.mlp-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04524974d28edccec90649f62e0baff166ab034dfc81f6ed884ff346e0e9e4cb
3
+ size 16385503
decoder.layers.0.attn.mlp-sparsity-predictor.2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57ff9189e0f481f140750e11e7c1683561eae9b412f1589308845b7cf6f7cee
3
+ size 65537503
decoder.layers.0.fc1.bias ADDED
Binary file (32.8 kB). View file
 
decoder.layers.0.fc1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624577e95d741dad71c323791825d3c83135eb737e352792cb9f627c68276bd3
3
+ size 134217728
decoder.layers.0.fc2.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.fc2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc7b3ac50d16acb223a3a7d02aa8aa743353667ad67481ee024269a1c42f97d
3
+ size 134217728
decoder.layers.0.final_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.final_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.self_attn.catted_head_biases ADDED
Binary file (24.6 kB). View file
 
decoder.layers.0.self_attn.catted_head_weights ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795b20c5b3a18c2bc80a2bc681c2054c805d67dccb8a6ba73980549d72882a1d
3
+ size 134217728
decoder.layers.0.self_attn.out_proj.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.self_attn_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.0.self_attn_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.attn.mlp-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1fb19f05ad95ccad667dc0e99981f65ec05cc05f66e27714a930ad8c3dbfb9c
3
+ size 16385503
decoder.layers.1.attn.mlp-sparsity-predictor.2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d690ce63f8a932d1a525bdf14ae844fbb0c496bfddb0a12cd291d2cded36ddc
3
+ size 65537503
decoder.layers.1.fc1.bias ADDED
Binary file (32.8 kB). View file
 
decoder.layers.1.fc1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c9f900cf8e342aca2aecd33646d3105702c6534c141ee9b6a764ac0402c7e0
3
+ size 134217728
decoder.layers.1.fc2.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.fc2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051a1e2625f34611fac22cb25f085b8fb5c5191eb85ad7f4c7fa9f3943374517
3
+ size 134217728
decoder.layers.1.final_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.final_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.self_attn.catted_head_biases ADDED
Binary file (24.6 kB). View file
 
decoder.layers.1.self_attn.catted_head_weights ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf706b423b6dc5ceacda6b60195c682102c48e795f13ae1e0c1a0c5ad889b40
3
+ size 134217728
decoder.layers.1.self_attn.out_proj.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.self_attn_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.1.self_attn_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.attn.mlp-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c914f1983c69800167ad4955a5c54caeb79d57bee8ea168cddbac1439dd8aa58
3
+ size 16385508
decoder.layers.10.attn.mlp-sparsity-predictor.2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87a0b3c12612213b5733d2822db9f27fd9b6e906ccda22463c5957ebdf0bc02
3
+ size 65537508
decoder.layers.10.fc1.bias ADDED
Binary file (32.8 kB). View file
 
decoder.layers.10.fc1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e534a218dd650a8db4082fc44e65904c0ce54573f1b03afe2257fa7f727079
3
+ size 134217728
decoder.layers.10.fc2.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.fc2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b3109d685b3832bca53405945fc6164a17bcdbf9d25995cdbabf83af84305b
3
+ size 134217728
decoder.layers.10.final_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.final_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.self_attn.catted_head_biases ADDED
Binary file (24.6 kB). View file
 
decoder.layers.10.self_attn.catted_head_weights ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff57b3d68c9e0229e81693379f718665bbc0b7c42b63188366084c1398e4a02
3
+ size 134217728
decoder.layers.10.self_attn.out_proj.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.self_attn_layer_norm.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.10.self_attn_layer_norm.weight ADDED
Binary file (8.19 kB). View file
 
decoder.layers.11.attn.mlp-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089940488a8842f90b1c25e052999464907371449f055a4197eb9a151766d46c
3
+ size 16385508
decoder.layers.11.attn.mlp-sparsity-predictor.2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d131ff308eab53c8ef277aee59bc1fa76a8bc15eb71f4ac05ad4b8694997103
3
+ size 65537508
decoder.layers.11.fc1.bias ADDED
Binary file (32.8 kB). View file
 
decoder.layers.11.fc1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319969355fbefee636d3ae2579a232ab893716ae254b77c63e9a59d9896e54f1
3
+ size 134217728
decoder.layers.11.fc2.bias ADDED
Binary file (8.19 kB). View file
 
decoder.layers.11.fc2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc58fca0eec26caea1fcc5cc59446bb2543c93288c6225d1de28ec68e22e4c8
3
+ size 134217728