Hugging Face's logo

austinsilveria
/
tricksy-opt-30b

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
+1160
-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 +290 -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.-1.attn-head-sparsity-predictor.1.weight +3 -0
  7. decoder.layers.-1.attn-head-sparsity-predictor.2.weight +0 -0
  8. decoder.layers.0.attn-head-sparsity-predictor.1.weight +3 -0
  9. decoder.layers.0.attn-head-sparsity-predictor.2.weight +0 -0
  10. decoder.layers.0.attn.mlp-sparsity-predictor.1.weight +3 -0
  11. decoder.layers.0.attn.mlp-sparsity-predictor.2.weight +3 -0
  12. decoder.layers.0.fc1.bias +0 -0
  13. decoder.layers.0.fc1.weight +3 -0
  14. decoder.layers.0.fc2.bias +0 -0
  15. decoder.layers.0.fc2.weight +3 -0
  16. decoder.layers.0.final_layer_norm.bias +0 -0
  17. decoder.layers.0.final_layer_norm.weight +0 -0
  18. decoder.layers.0.self_attn.catted_head_biases +0 -0
  19. decoder.layers.0.self_attn.catted_head_weights +3 -0
  20. decoder.layers.0.self_attn.out_proj.bias +0 -0
  21. decoder.layers.0.self_attn_layer_norm.bias +0 -0
  22. decoder.layers.0.self_attn_layer_norm.weight +0 -0
  23. decoder.layers.1.attn-head-sparsity-predictor.1.weight +3 -0
  24. decoder.layers.1.attn-head-sparsity-predictor.2.weight +0 -0
  25. decoder.layers.1.attn.mlp-sparsity-predictor.1.weight +3 -0
  26. decoder.layers.1.attn.mlp-sparsity-predictor.2.weight +3 -0
  27. decoder.layers.1.fc1.bias +0 -0
  28. decoder.layers.1.fc1.weight +3 -0
  29. decoder.layers.1.fc2.bias +0 -0
  30. decoder.layers.1.fc2.weight +3 -0
  31. decoder.layers.1.final_layer_norm.bias +0 -0
  32. decoder.layers.1.final_layer_norm.weight +0 -0
  33. decoder.layers.1.self_attn.catted_head_biases +0 -0
  34. decoder.layers.1.self_attn.catted_head_weights +3 -0
  35. decoder.layers.1.self_attn.out_proj.bias +0 -0
  36. decoder.layers.1.self_attn_layer_norm.bias +0 -0
  37. decoder.layers.1.self_attn_layer_norm.weight +0 -0
  38. decoder.layers.10.attn-head-sparsity-predictor.1.weight +3 -0
  39. decoder.layers.10.attn-head-sparsity-predictor.2.weight +0 -0
  40. decoder.layers.10.attn.mlp-sparsity-predictor.1.weight +3 -0
  41. decoder.layers.10.attn.mlp-sparsity-predictor.2.weight +3 -0
  42. decoder.layers.10.fc1.bias +0 -0
  43. decoder.layers.10.fc1.weight +3 -0
  44. decoder.layers.10.fc2.bias +0 -0
  45. decoder.layers.10.fc2.weight +3 -0
  46. decoder.layers.10.final_layer_norm.bias +0 -0
  47. decoder.layers.10.final_layer_norm.weight +0 -0
  48. decoder.layers.10.self_attn.catted_head_biases +0 -0
  49. decoder.layers.10.self_attn.catted_head_weights +3 -0
  50. decoder.layers.10.self_attn.out_proj.bias +0 -0
.gitattributes CHANGED
@@ -33,3 +33,293 @@ 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.-1.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
39
+ decoder.layers.0.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
40
+ decoder.layers.0.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
41
+ decoder.layers.0.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
42
+ decoder.layers.0.fc1.weight filter=lfs diff=lfs merge=lfs -text
43
+ decoder.layers.0.fc2.weight filter=lfs diff=lfs merge=lfs -text
44
+ decoder.layers.0.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
45
+ decoder.layers.1.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
46
+ decoder.layers.1.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
47
+ decoder.layers.1.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
48
+ decoder.layers.1.fc1.weight filter=lfs diff=lfs merge=lfs -text
49
+ decoder.layers.1.fc2.weight filter=lfs diff=lfs merge=lfs -text
50
+ decoder.layers.1.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
51
+ decoder.layers.10.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
52
+ decoder.layers.10.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
53
+ decoder.layers.10.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
54
+ decoder.layers.10.fc1.weight filter=lfs diff=lfs merge=lfs -text
55
+ decoder.layers.10.fc2.weight filter=lfs diff=lfs merge=lfs -text
56
+ decoder.layers.10.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
57
+ decoder.layers.11.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
58
+ decoder.layers.11.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
59
+ decoder.layers.11.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
60
+ decoder.layers.11.fc1.weight filter=lfs diff=lfs merge=lfs -text
61
+ decoder.layers.11.fc2.weight filter=lfs diff=lfs merge=lfs -text
62
+ decoder.layers.11.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
63
+ decoder.layers.12.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
64
+ decoder.layers.12.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
65
+ decoder.layers.12.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
66
+ decoder.layers.12.fc1.weight filter=lfs diff=lfs merge=lfs -text
67
+ decoder.layers.12.fc2.weight filter=lfs diff=lfs merge=lfs -text
68
+ decoder.layers.12.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
69
+ decoder.layers.13.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
70
+ decoder.layers.13.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
71
+ decoder.layers.13.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
72
+ decoder.layers.13.fc1.weight filter=lfs diff=lfs merge=lfs -text
73
+ decoder.layers.13.fc2.weight filter=lfs diff=lfs merge=lfs -text
74
+ decoder.layers.13.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
75
+ decoder.layers.14.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
76
+ decoder.layers.14.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
77
+ decoder.layers.14.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
78
+ decoder.layers.14.fc1.weight filter=lfs diff=lfs merge=lfs -text
79
+ decoder.layers.14.fc2.weight filter=lfs diff=lfs merge=lfs -text
80
+ decoder.layers.14.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
81
+ decoder.layers.15.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
82
+ decoder.layers.15.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
83
+ decoder.layers.15.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
84
+ decoder.layers.15.fc1.weight filter=lfs diff=lfs merge=lfs -text
85
+ decoder.layers.15.fc2.weight filter=lfs diff=lfs merge=lfs -text
86
+ decoder.layers.15.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
87
+ decoder.layers.16.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
88
+ decoder.layers.16.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
89
+ decoder.layers.16.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
90
+ decoder.layers.16.fc1.weight filter=lfs diff=lfs merge=lfs -text
91
+ decoder.layers.16.fc2.weight filter=lfs diff=lfs merge=lfs -text
92
+ decoder.layers.16.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
93
+ decoder.layers.17.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
94
+ decoder.layers.17.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
95
+ decoder.layers.17.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
96
+ decoder.layers.17.fc1.weight filter=lfs diff=lfs merge=lfs -text
97
+ decoder.layers.17.fc2.weight filter=lfs diff=lfs merge=lfs -text
98
+ decoder.layers.17.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
99
+ decoder.layers.18.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
100
+ decoder.layers.18.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
101
+ decoder.layers.18.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
102
+ decoder.layers.18.fc1.weight filter=lfs diff=lfs merge=lfs -text
103
+ decoder.layers.18.fc2.weight filter=lfs diff=lfs merge=lfs -text
104
+ decoder.layers.18.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
105
+ decoder.layers.19.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
106
+ decoder.layers.19.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
107
+ decoder.layers.19.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
108
+ decoder.layers.19.fc1.weight filter=lfs diff=lfs merge=lfs -text
109
+ decoder.layers.19.fc2.weight filter=lfs diff=lfs merge=lfs -text
110
+ decoder.layers.19.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
111
+ decoder.layers.2.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
112
+ decoder.layers.2.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
113
+ decoder.layers.2.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
114
+ decoder.layers.2.fc1.weight filter=lfs diff=lfs merge=lfs -text
115
+ decoder.layers.2.fc2.weight filter=lfs diff=lfs merge=lfs -text
116
+ decoder.layers.2.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
117
+ decoder.layers.20.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
118
+ decoder.layers.20.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
119
+ decoder.layers.20.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
120
+ decoder.layers.20.fc1.weight filter=lfs diff=lfs merge=lfs -text
121
+ decoder.layers.20.fc2.weight filter=lfs diff=lfs merge=lfs -text
122
+ decoder.layers.20.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
123
+ decoder.layers.21.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
124
+ decoder.layers.21.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
125
+ decoder.layers.21.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
126
+ decoder.layers.21.fc1.weight filter=lfs diff=lfs merge=lfs -text
127
+ decoder.layers.21.fc2.weight filter=lfs diff=lfs merge=lfs -text
128
+ decoder.layers.21.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
129
+ decoder.layers.22.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
130
+ decoder.layers.22.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
131
+ decoder.layers.22.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
132
+ decoder.layers.22.fc1.weight filter=lfs diff=lfs merge=lfs -text
133
+ decoder.layers.22.fc2.weight filter=lfs diff=lfs merge=lfs -text
134
+ decoder.layers.22.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
135
+ decoder.layers.23.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
136
+ decoder.layers.23.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
137
+ decoder.layers.23.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
138
+ decoder.layers.23.fc1.weight filter=lfs diff=lfs merge=lfs -text
139
+ decoder.layers.23.fc2.weight filter=lfs diff=lfs merge=lfs -text
140
+ decoder.layers.23.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
141
+ decoder.layers.24.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
142
+ decoder.layers.24.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
143
+ decoder.layers.24.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
144
+ decoder.layers.24.fc1.weight filter=lfs diff=lfs merge=lfs -text
145
+ decoder.layers.24.fc2.weight filter=lfs diff=lfs merge=lfs -text
146
+ decoder.layers.24.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
147
+ decoder.layers.25.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
148
+ decoder.layers.25.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
149
+ decoder.layers.25.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
150
+ decoder.layers.25.fc1.weight filter=lfs diff=lfs merge=lfs -text
151
+ decoder.layers.25.fc2.weight filter=lfs diff=lfs merge=lfs -text
152
+ decoder.layers.25.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
153
+ decoder.layers.26.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
154
+ decoder.layers.26.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
155
+ decoder.layers.26.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
156
+ decoder.layers.26.fc1.weight filter=lfs diff=lfs merge=lfs -text
157
+ decoder.layers.26.fc2.weight filter=lfs diff=lfs merge=lfs -text
158
+ decoder.layers.26.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
159
+ decoder.layers.27.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
160
+ decoder.layers.27.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
161
+ decoder.layers.27.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
162
+ decoder.layers.27.fc1.weight filter=lfs diff=lfs merge=lfs -text
163
+ decoder.layers.27.fc2.weight filter=lfs diff=lfs merge=lfs -text
164
+ decoder.layers.27.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
165
+ decoder.layers.28.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
166
+ decoder.layers.28.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
167
+ decoder.layers.28.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
168
+ decoder.layers.28.fc1.weight filter=lfs diff=lfs merge=lfs -text
169
+ decoder.layers.28.fc2.weight filter=lfs diff=lfs merge=lfs -text
170
+ decoder.layers.28.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
171
+ decoder.layers.29.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
172
+ decoder.layers.29.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
173
+ decoder.layers.29.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
174
+ decoder.layers.29.fc1.weight filter=lfs diff=lfs merge=lfs -text
175
+ decoder.layers.29.fc2.weight filter=lfs diff=lfs merge=lfs -text
176
+ decoder.layers.29.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
177
+ decoder.layers.3.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
178
+ decoder.layers.3.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
179
+ decoder.layers.3.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
180
+ decoder.layers.3.fc1.weight filter=lfs diff=lfs merge=lfs -text
181
+ decoder.layers.3.fc2.weight filter=lfs diff=lfs merge=lfs -text
182
+ decoder.layers.3.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
183
+ decoder.layers.30.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
184
+ decoder.layers.30.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
185
+ decoder.layers.30.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
186
+ decoder.layers.30.fc1.weight filter=lfs diff=lfs merge=lfs -text
187
+ decoder.layers.30.fc2.weight filter=lfs diff=lfs merge=lfs -text
188
+ decoder.layers.30.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
189
+ decoder.layers.31.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
190
+ decoder.layers.31.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
191
+ decoder.layers.31.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
192
+ decoder.layers.31.fc1.weight filter=lfs diff=lfs merge=lfs -text
193
+ decoder.layers.31.fc2.weight filter=lfs diff=lfs merge=lfs -text
194
+ decoder.layers.31.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
195
+ decoder.layers.32.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
196
+ decoder.layers.32.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
197
+ decoder.layers.32.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
198
+ decoder.layers.32.fc1.weight filter=lfs diff=lfs merge=lfs -text
199
+ decoder.layers.32.fc2.weight filter=lfs diff=lfs merge=lfs -text
200
+ decoder.layers.32.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
201
+ decoder.layers.33.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
202
+ decoder.layers.33.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
203
+ decoder.layers.33.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
204
+ decoder.layers.33.fc1.weight filter=lfs diff=lfs merge=lfs -text
205
+ decoder.layers.33.fc2.weight filter=lfs diff=lfs merge=lfs -text
206
+ decoder.layers.33.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
207
+ decoder.layers.34.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
208
+ decoder.layers.34.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
209
+ decoder.layers.34.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
210
+ decoder.layers.34.fc1.weight filter=lfs diff=lfs merge=lfs -text
211
+ decoder.layers.34.fc2.weight filter=lfs diff=lfs merge=lfs -text
212
+ decoder.layers.34.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
213
+ decoder.layers.35.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
214
+ decoder.layers.35.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
215
+ decoder.layers.35.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
216
+ decoder.layers.35.fc1.weight filter=lfs diff=lfs merge=lfs -text
217
+ decoder.layers.35.fc2.weight filter=lfs diff=lfs merge=lfs -text
218
+ decoder.layers.35.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
219
+ decoder.layers.36.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
220
+ decoder.layers.36.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
221
+ decoder.layers.36.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
222
+ decoder.layers.36.fc1.weight filter=lfs diff=lfs merge=lfs -text
223
+ decoder.layers.36.fc2.weight filter=lfs diff=lfs merge=lfs -text
224
+ decoder.layers.36.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
225
+ decoder.layers.37.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
226
+ decoder.layers.37.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
227
+ decoder.layers.37.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
228
+ decoder.layers.37.fc1.weight filter=lfs diff=lfs merge=lfs -text
229
+ decoder.layers.37.fc2.weight filter=lfs diff=lfs merge=lfs -text
230
+ decoder.layers.37.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
231
+ decoder.layers.38.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
232
+ decoder.layers.38.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
233
+ decoder.layers.38.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
234
+ decoder.layers.38.fc1.weight filter=lfs diff=lfs merge=lfs -text
235
+ decoder.layers.38.fc2.weight filter=lfs diff=lfs merge=lfs -text
236
+ decoder.layers.38.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
237
+ decoder.layers.39.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
238
+ decoder.layers.39.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
239
+ decoder.layers.39.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
240
+ decoder.layers.39.fc1.weight filter=lfs diff=lfs merge=lfs -text
241
+ decoder.layers.39.fc2.weight filter=lfs diff=lfs merge=lfs -text
242
+ decoder.layers.39.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
243
+ decoder.layers.4.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
244
+ decoder.layers.4.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
245
+ decoder.layers.4.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
246
+ decoder.layers.4.fc1.weight filter=lfs diff=lfs merge=lfs -text
247
+ decoder.layers.4.fc2.weight filter=lfs diff=lfs merge=lfs -text
248
+ decoder.layers.4.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
249
+ decoder.layers.40.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
250
+ decoder.layers.40.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
251
+ decoder.layers.40.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
252
+ decoder.layers.40.fc1.weight filter=lfs diff=lfs merge=lfs -text
253
+ decoder.layers.40.fc2.weight filter=lfs diff=lfs merge=lfs -text
254
+ decoder.layers.40.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
255
+ decoder.layers.41.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
256
+ decoder.layers.41.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
257
+ decoder.layers.41.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
258
+ decoder.layers.41.fc1.weight filter=lfs diff=lfs merge=lfs -text
259
+ decoder.layers.41.fc2.weight filter=lfs diff=lfs merge=lfs -text
260
+ decoder.layers.41.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
261
+ decoder.layers.42.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
262
+ decoder.layers.42.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
263
+ decoder.layers.42.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
264
+ decoder.layers.42.fc1.weight filter=lfs diff=lfs merge=lfs -text
265
+ decoder.layers.42.fc2.weight filter=lfs diff=lfs merge=lfs -text
266
+ decoder.layers.42.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
267
+ decoder.layers.43.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
268
+ decoder.layers.43.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
269
+ decoder.layers.43.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
270
+ decoder.layers.43.fc1.weight filter=lfs diff=lfs merge=lfs -text
271
+ decoder.layers.43.fc2.weight filter=lfs diff=lfs merge=lfs -text
272
+ decoder.layers.43.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
273
+ decoder.layers.44.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
274
+ decoder.layers.44.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
275
+ decoder.layers.44.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
276
+ decoder.layers.44.fc1.weight filter=lfs diff=lfs merge=lfs -text
277
+ decoder.layers.44.fc2.weight filter=lfs diff=lfs merge=lfs -text
278
+ decoder.layers.44.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
279
+ decoder.layers.45.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
280
+ decoder.layers.45.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
281
+ decoder.layers.45.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
282
+ decoder.layers.45.fc1.weight filter=lfs diff=lfs merge=lfs -text
283
+ decoder.layers.45.fc2.weight filter=lfs diff=lfs merge=lfs -text
284
+ decoder.layers.45.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
285
+ decoder.layers.46.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
286
+ decoder.layers.46.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
287
+ decoder.layers.46.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
288
+ decoder.layers.46.fc1.weight filter=lfs diff=lfs merge=lfs -text
289
+ decoder.layers.46.fc2.weight filter=lfs diff=lfs merge=lfs -text
290
+ decoder.layers.46.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
291
+ decoder.layers.47.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
292
+ decoder.layers.47.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
293
+ decoder.layers.47.fc1.weight filter=lfs diff=lfs merge=lfs -text
294
+ decoder.layers.47.fc2.weight filter=lfs diff=lfs merge=lfs -text
295
+ decoder.layers.47.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
296
+ decoder.layers.5.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
297
+ decoder.layers.5.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
298
+ decoder.layers.5.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
299
+ decoder.layers.5.fc1.weight filter=lfs diff=lfs merge=lfs -text
300
+ decoder.layers.5.fc2.weight filter=lfs diff=lfs merge=lfs -text
301
+ decoder.layers.5.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
302
+ decoder.layers.6.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
303
+ decoder.layers.6.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
304
+ decoder.layers.6.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
305
+ decoder.layers.6.fc1.weight filter=lfs diff=lfs merge=lfs -text
306
+ decoder.layers.6.fc2.weight filter=lfs diff=lfs merge=lfs -text
307
+ decoder.layers.6.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
308
+ decoder.layers.7.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
309
+ decoder.layers.7.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
310
+ decoder.layers.7.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
311
+ decoder.layers.7.fc1.weight filter=lfs diff=lfs merge=lfs -text
312
+ decoder.layers.7.fc2.weight filter=lfs diff=lfs merge=lfs -text
313
+ decoder.layers.7.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
314
+ decoder.layers.8.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
315
+ decoder.layers.8.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
316
+ decoder.layers.8.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
317
+ decoder.layers.8.fc1.weight filter=lfs diff=lfs merge=lfs -text
318
+ decoder.layers.8.fc2.weight filter=lfs diff=lfs merge=lfs -text
319
+ decoder.layers.8.self_attn.catted_head_weights filter=lfs diff=lfs merge=lfs -text
320
+ decoder.layers.9.attn-head-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
321
+ decoder.layers.9.attn.mlp-sparsity-predictor.1.weight filter=lfs diff=lfs merge=lfs -text
322
+ decoder.layers.9.attn.mlp-sparsity-predictor.2.weight filter=lfs diff=lfs merge=lfs -text
323
+ decoder.layers.9.fc1.weight filter=lfs diff=lfs merge=lfs -text
324
+ decoder.layers.9.fc2.weight filter=lfs diff=lfs merge=lfs -text
325
+ 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 sha256:3cf00ad035ead79d2ed48ec3d522561ef720f15bffa949e4bb19a9113f3c5942
3
+ size 29388800
decoder.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476ae65e6101e387c458e4f97bb25b202a40c544be169b01f1f3c992c2bce87f
3
+ size 720699392
decoder.final_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.final_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.-1.attn-head-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0367c5f848f51d25dedf960ddb2c1b77f64cdb5de0a84b450ec72877eca7839b
3
+ size 28673513
decoder.layers.-1.attn-head-sparsity-predictor.2.weight ADDED
Binary file (226 kB). View file
 
decoder.layers.0.attn-head-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a22abccbac13fa4eedebdc25223ee424dece7854b1ce2d5ceaecdd2ec382b7a
3
+ size 28673508
decoder.layers.0.attn-head-sparsity-predictor.2.weight ADDED
Binary file (226 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 sha256:57417f7b96f250b51647ecaa6c3d3f948d48b1b3943f33dac4a352b177addb45
3
+ size 28673334
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:c51abfab2cdb85d3f751b3ce6c5d0208e0be24a113a92e9c3c6cc5fae8d64b9e
3
+ size 114689334
decoder.layers.0.fc1.bias ADDED
Binary file (57.3 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:e7be7e5e24f7f51375dacf99b97f45795e1e16272def0f0b4291ca4e8ef50047
3
+ size 411041792
decoder.layers.0.fc2.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.0.fc2.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0043b590c01d29da4d352510110585a1ab32a1a964cfbd9a64c08facf5c323bc
3
+ size 411041792
decoder.layers.0.final_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.0.final_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.0.self_attn.catted_head_biases ADDED
Binary file (43 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 sha256:5941fc85b3da59c91af7f8337cc9f3646c451b562433adda2982aa8448ea4534
3
+ size 411041792
decoder.layers.0.self_attn.out_proj.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.0.self_attn_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.0.self_attn_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.1.attn-head-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d21336cb726e7b71c67fef9ea1172dc8ce7a07e8259c8c4a6430d8d7b7fb71b
3
+ size 28673508
decoder.layers.1.attn-head-sparsity-predictor.2.weight ADDED
Binary file (226 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 sha256:219e2ac10da9e400afcbe461b0f9e08060fe9c2853033e98bdab2c73477ff2fd
3
+ size 28673503
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:dc71c4d33a69bb53d0184d02c2fe7770d40376b779ade6dbc91792399c0fdf8d
3
+ size 114689503
decoder.layers.1.fc1.bias ADDED
Binary file (57.3 kB). View file
 
decoder.layers.1.fc1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d7617e85bf07bce9dea5dd02c24350cd7bc817efb8d09d693de879ef0821fa
3
+ size 411041792
decoder.layers.1.fc2.bias ADDED
Binary file (14.3 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:ff95a862905f51cff395770d52d8d4d0749616038faee552f0c2470a843aa3bc
3
+ size 411041792
decoder.layers.1.final_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.1.final_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.1.self_attn.catted_head_biases ADDED
Binary file (43 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 sha256:268f002e7b1eb3fabd1767ce104ff449e492936658cc6e7c19a038262f30b5bf
3
+ size 411041792
decoder.layers.1.self_attn.out_proj.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.1.self_attn_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.1.self_attn_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.10.attn-head-sparsity-predictor.1.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e828b35fe897e574c3c400bdbcf4c0cbb282be057cdd855367dab21ab073b226
3
+ size 28673513
decoder.layers.10.attn-head-sparsity-predictor.2.weight ADDED
Binary file (226 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:c8db4523cba617e4b78d1d9e3c900da5e8999c4a3d70650755562a590adae391
3
+ size 28673508
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 sha256:49e295828515f15e474bf68db2fea679dd9fb0e30b2f2a7d51da9676c6d292f5
3
+ size 114689508
decoder.layers.10.fc1.bias ADDED
Binary file (57.3 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:dc4836d9b2b382d49cad6e60922c107cc1cfab8f0b17dba5e9326ecf08f4002c
3
+ size 411041792
decoder.layers.10.fc2.bias ADDED
Binary file (14.3 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:efddc1e98aa94538dcd9b047f840f825b240b956c2a2f0c4d057c82f8f6e3c28
3
+ size 411041792
decoder.layers.10.final_layer_norm.bias ADDED
Binary file (14.3 kB). View file
 
decoder.layers.10.final_layer_norm.weight ADDED
Binary file (14.3 kB). View file
 
decoder.layers.10.self_attn.catted_head_biases ADDED
Binary file (43 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 sha256:68858918d1d1f339ce7c211a973cb84b42e7b53fdc4e9f6401ac6f3f6372d4d7
3
+ size 411041792
decoder.layers.10.self_attn.out_proj.bias ADDED
Binary file (14.3 kB). View file