cfu commited on
Commit
6b86bfd
·
verified ·
1 Parent(s): e6b6a75

Upload ONNX files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +198 -0
  2. model.embed_tokens.weight +3 -0
  3. model.layers.0.input_layernorm.weight +0 -0
  4. model.layers.0.post_attention_layernorm.weight +0 -0
  5. model.layers.0.self_attn.q_proj.bias +0 -0
  6. model.layers.1.input_layernorm.weight +0 -0
  7. model.layers.1.post_attention_layernorm.weight +0 -0
  8. model.layers.1.self_attn.q_proj.bias +0 -0
  9. model.layers.10.input_layernorm.weight +0 -0
  10. model.layers.10.post_attention_layernorm.weight +0 -0
  11. model.layers.10.self_attn.q_proj.bias +0 -0
  12. model.layers.11.input_layernorm.weight +0 -0
  13. model.layers.11.post_attention_layernorm.weight +0 -0
  14. model.layers.11.self_attn.q_proj.bias +0 -0
  15. model.layers.12.input_layernorm.weight +0 -0
  16. model.layers.12.post_attention_layernorm.weight +0 -0
  17. model.layers.12.self_attn.q_proj.bias +0 -0
  18. model.layers.13.input_layernorm.weight +0 -0
  19. model.layers.13.post_attention_layernorm.weight +0 -0
  20. model.layers.13.self_attn.q_proj.bias +0 -0
  21. model.layers.14.input_layernorm.weight +0 -0
  22. model.layers.14.post_attention_layernorm.weight +0 -0
  23. model.layers.14.self_attn.q_proj.bias +0 -0
  24. model.layers.15.input_layernorm.weight +0 -0
  25. model.layers.15.post_attention_layernorm.weight +0 -0
  26. model.layers.15.self_attn.q_proj.bias +0 -0
  27. model.layers.16.input_layernorm.weight +0 -0
  28. model.layers.16.post_attention_layernorm.weight +0 -0
  29. model.layers.16.self_attn.q_proj.bias +0 -0
  30. model.layers.17.input_layernorm.weight +0 -0
  31. model.layers.17.post_attention_layernorm.weight +0 -0
  32. model.layers.17.self_attn.q_proj.bias +0 -0
  33. model.layers.18.input_layernorm.weight +0 -0
  34. model.layers.18.post_attention_layernorm.weight +0 -0
  35. model.layers.18.self_attn.q_proj.bias +0 -0
  36. model.layers.19.input_layernorm.weight +0 -0
  37. model.layers.19.post_attention_layernorm.weight +0 -0
  38. model.layers.19.self_attn.q_proj.bias +0 -0
  39. model.layers.2.input_layernorm.weight +0 -0
  40. model.layers.2.post_attention_layernorm.weight +0 -0
  41. model.layers.2.self_attn.q_proj.bias +0 -0
  42. model.layers.20.input_layernorm.weight +0 -0
  43. model.layers.20.post_attention_layernorm.weight +0 -0
  44. model.layers.20.self_attn.q_proj.bias +0 -0
  45. model.layers.21.input_layernorm.weight +0 -0
  46. model.layers.21.post_attention_layernorm.weight +0 -0
  47. model.layers.21.self_attn.q_proj.bias +0 -0
  48. model.layers.22.input_layernorm.weight +0 -0
  49. model.layers.22.post_attention_layernorm.weight +0 -0
  50. model.layers.22.self_attn.q_proj.bias +0 -0
.gitattributes CHANGED
@@ -34,3 +34,201 @@ saved_model/**/* 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
  tokenizer.json 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
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ model.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
38
+ onnx__MatMul_8143 filter=lfs diff=lfs merge=lfs -text
39
+ onnx__MatMul_8150 filter=lfs diff=lfs merge=lfs -text
40
+ onnx__MatMul_8151 filter=lfs diff=lfs merge=lfs -text
41
+ onnx__MatMul_8174 filter=lfs diff=lfs merge=lfs -text
42
+ onnx__MatMul_8175 filter=lfs diff=lfs merge=lfs -text
43
+ onnx__MatMul_8176 filter=lfs diff=lfs merge=lfs -text
44
+ onnx__MatMul_8177 filter=lfs diff=lfs merge=lfs -text
45
+ onnx__MatMul_8178 filter=lfs diff=lfs merge=lfs -text
46
+ onnx__MatMul_8185 filter=lfs diff=lfs merge=lfs -text
47
+ onnx__MatMul_8186 filter=lfs diff=lfs merge=lfs -text
48
+ onnx__MatMul_8209 filter=lfs diff=lfs merge=lfs -text
49
+ onnx__MatMul_8210 filter=lfs diff=lfs merge=lfs -text
50
+ onnx__MatMul_8211 filter=lfs diff=lfs merge=lfs -text
51
+ onnx__MatMul_8212 filter=lfs diff=lfs merge=lfs -text
52
+ onnx__MatMul_8213 filter=lfs diff=lfs merge=lfs -text
53
+ onnx__MatMul_8220 filter=lfs diff=lfs merge=lfs -text
54
+ onnx__MatMul_8221 filter=lfs diff=lfs merge=lfs -text
55
+ onnx__MatMul_8244 filter=lfs diff=lfs merge=lfs -text
56
+ onnx__MatMul_8245 filter=lfs diff=lfs merge=lfs -text
57
+ onnx__MatMul_8246 filter=lfs diff=lfs merge=lfs -text
58
+ onnx__MatMul_8247 filter=lfs diff=lfs merge=lfs -text
59
+ onnx__MatMul_8248 filter=lfs diff=lfs merge=lfs -text
60
+ onnx__MatMul_8255 filter=lfs diff=lfs merge=lfs -text
61
+ onnx__MatMul_8256 filter=lfs diff=lfs merge=lfs -text
62
+ onnx__MatMul_8279 filter=lfs diff=lfs merge=lfs -text
63
+ onnx__MatMul_8280 filter=lfs diff=lfs merge=lfs -text
64
+ onnx__MatMul_8281 filter=lfs diff=lfs merge=lfs -text
65
+ onnx__MatMul_8282 filter=lfs diff=lfs merge=lfs -text
66
+ onnx__MatMul_8283 filter=lfs diff=lfs merge=lfs -text
67
+ onnx__MatMul_8290 filter=lfs diff=lfs merge=lfs -text
68
+ onnx__MatMul_8291 filter=lfs diff=lfs merge=lfs -text
69
+ onnx__MatMul_8314 filter=lfs diff=lfs merge=lfs -text
70
+ onnx__MatMul_8315 filter=lfs diff=lfs merge=lfs -text
71
+ onnx__MatMul_8316 filter=lfs diff=lfs merge=lfs -text
72
+ onnx__MatMul_8317 filter=lfs diff=lfs merge=lfs -text
73
+ onnx__MatMul_8318 filter=lfs diff=lfs merge=lfs -text
74
+ onnx__MatMul_8325 filter=lfs diff=lfs merge=lfs -text
75
+ onnx__MatMul_8326 filter=lfs diff=lfs merge=lfs -text
76
+ onnx__MatMul_8349 filter=lfs diff=lfs merge=lfs -text
77
+ onnx__MatMul_8350 filter=lfs diff=lfs merge=lfs -text
78
+ onnx__MatMul_8351 filter=lfs diff=lfs merge=lfs -text
79
+ onnx__MatMul_8352 filter=lfs diff=lfs merge=lfs -text
80
+ onnx__MatMul_8353 filter=lfs diff=lfs merge=lfs -text
81
+ onnx__MatMul_8360 filter=lfs diff=lfs merge=lfs -text
82
+ onnx__MatMul_8361 filter=lfs diff=lfs merge=lfs -text
83
+ onnx__MatMul_8384 filter=lfs diff=lfs merge=lfs -text
84
+ onnx__MatMul_8385 filter=lfs diff=lfs merge=lfs -text
85
+ onnx__MatMul_8386 filter=lfs diff=lfs merge=lfs -text
86
+ onnx__MatMul_8387 filter=lfs diff=lfs merge=lfs -text
87
+ onnx__MatMul_8388 filter=lfs diff=lfs merge=lfs -text
88
+ onnx__MatMul_8395 filter=lfs diff=lfs merge=lfs -text
89
+ onnx__MatMul_8396 filter=lfs diff=lfs merge=lfs -text
90
+ onnx__MatMul_8419 filter=lfs diff=lfs merge=lfs -text
91
+ onnx__MatMul_8420 filter=lfs diff=lfs merge=lfs -text
92
+ onnx__MatMul_8421 filter=lfs diff=lfs merge=lfs -text
93
+ onnx__MatMul_8422 filter=lfs diff=lfs merge=lfs -text
94
+ onnx__MatMul_8423 filter=lfs diff=lfs merge=lfs -text
95
+ onnx__MatMul_8430 filter=lfs diff=lfs merge=lfs -text
96
+ onnx__MatMul_8431 filter=lfs diff=lfs merge=lfs -text
97
+ onnx__MatMul_8454 filter=lfs diff=lfs merge=lfs -text
98
+ onnx__MatMul_8455 filter=lfs diff=lfs merge=lfs -text
99
+ onnx__MatMul_8456 filter=lfs diff=lfs merge=lfs -text
100
+ onnx__MatMul_8457 filter=lfs diff=lfs merge=lfs -text
101
+ onnx__MatMul_8458 filter=lfs diff=lfs merge=lfs -text
102
+ onnx__MatMul_8465 filter=lfs diff=lfs merge=lfs -text
103
+ onnx__MatMul_8466 filter=lfs diff=lfs merge=lfs -text
104
+ onnx__MatMul_8489 filter=lfs diff=lfs merge=lfs -text
105
+ onnx__MatMul_8490 filter=lfs diff=lfs merge=lfs -text
106
+ onnx__MatMul_8491 filter=lfs diff=lfs merge=lfs -text
107
+ onnx__MatMul_8492 filter=lfs diff=lfs merge=lfs -text
108
+ onnx__MatMul_8493 filter=lfs diff=lfs merge=lfs -text
109
+ onnx__MatMul_8500 filter=lfs diff=lfs merge=lfs -text
110
+ onnx__MatMul_8501 filter=lfs diff=lfs merge=lfs -text
111
+ onnx__MatMul_8524 filter=lfs diff=lfs merge=lfs -text
112
+ onnx__MatMul_8525 filter=lfs diff=lfs merge=lfs -text
113
+ onnx__MatMul_8526 filter=lfs diff=lfs merge=lfs -text
114
+ onnx__MatMul_8527 filter=lfs diff=lfs merge=lfs -text
115
+ onnx__MatMul_8528 filter=lfs diff=lfs merge=lfs -text
116
+ onnx__MatMul_8535 filter=lfs diff=lfs merge=lfs -text
117
+ onnx__MatMul_8536 filter=lfs diff=lfs merge=lfs -text
118
+ onnx__MatMul_8559 filter=lfs diff=lfs merge=lfs -text
119
+ onnx__MatMul_8560 filter=lfs diff=lfs merge=lfs -text
120
+ onnx__MatMul_8561 filter=lfs diff=lfs merge=lfs -text
121
+ onnx__MatMul_8562 filter=lfs diff=lfs merge=lfs -text
122
+ onnx__MatMul_8563 filter=lfs diff=lfs merge=lfs -text
123
+ onnx__MatMul_8570 filter=lfs diff=lfs merge=lfs -text
124
+ onnx__MatMul_8571 filter=lfs diff=lfs merge=lfs -text
125
+ onnx__MatMul_8594 filter=lfs diff=lfs merge=lfs -text
126
+ onnx__MatMul_8595 filter=lfs diff=lfs merge=lfs -text
127
+ onnx__MatMul_8596 filter=lfs diff=lfs merge=lfs -text
128
+ onnx__MatMul_8597 filter=lfs diff=lfs merge=lfs -text
129
+ onnx__MatMul_8598 filter=lfs diff=lfs merge=lfs -text
130
+ onnx__MatMul_8605 filter=lfs diff=lfs merge=lfs -text
131
+ onnx__MatMul_8606 filter=lfs diff=lfs merge=lfs -text
132
+ onnx__MatMul_8629 filter=lfs diff=lfs merge=lfs -text
133
+ onnx__MatMul_8630 filter=lfs diff=lfs merge=lfs -text
134
+ onnx__MatMul_8631 filter=lfs diff=lfs merge=lfs -text
135
+ onnx__MatMul_8632 filter=lfs diff=lfs merge=lfs -text
136
+ onnx__MatMul_8633 filter=lfs diff=lfs merge=lfs -text
137
+ onnx__MatMul_8640 filter=lfs diff=lfs merge=lfs -text
138
+ onnx__MatMul_8641 filter=lfs diff=lfs merge=lfs -text
139
+ onnx__MatMul_8664 filter=lfs diff=lfs merge=lfs -text
140
+ onnx__MatMul_8665 filter=lfs diff=lfs merge=lfs -text
141
+ onnx__MatMul_8666 filter=lfs diff=lfs merge=lfs -text
142
+ onnx__MatMul_8667 filter=lfs diff=lfs merge=lfs -text
143
+ onnx__MatMul_8668 filter=lfs diff=lfs merge=lfs -text
144
+ onnx__MatMul_8675 filter=lfs diff=lfs merge=lfs -text
145
+ onnx__MatMul_8676 filter=lfs diff=lfs merge=lfs -text
146
+ onnx__MatMul_8699 filter=lfs diff=lfs merge=lfs -text
147
+ onnx__MatMul_8700 filter=lfs diff=lfs merge=lfs -text
148
+ onnx__MatMul_8701 filter=lfs diff=lfs merge=lfs -text
149
+ onnx__MatMul_8702 filter=lfs diff=lfs merge=lfs -text
150
+ onnx__MatMul_8703 filter=lfs diff=lfs merge=lfs -text
151
+ onnx__MatMul_8710 filter=lfs diff=lfs merge=lfs -text
152
+ onnx__MatMul_8711 filter=lfs diff=lfs merge=lfs -text
153
+ onnx__MatMul_8734 filter=lfs diff=lfs merge=lfs -text
154
+ onnx__MatMul_8735 filter=lfs diff=lfs merge=lfs -text
155
+ onnx__MatMul_8736 filter=lfs diff=lfs merge=lfs -text
156
+ onnx__MatMul_8737 filter=lfs diff=lfs merge=lfs -text
157
+ onnx__MatMul_8738 filter=lfs diff=lfs merge=lfs -text
158
+ onnx__MatMul_8745 filter=lfs diff=lfs merge=lfs -text
159
+ onnx__MatMul_8746 filter=lfs diff=lfs merge=lfs -text
160
+ onnx__MatMul_8769 filter=lfs diff=lfs merge=lfs -text
161
+ onnx__MatMul_8770 filter=lfs diff=lfs merge=lfs -text
162
+ onnx__MatMul_8771 filter=lfs diff=lfs merge=lfs -text
163
+ onnx__MatMul_8772 filter=lfs diff=lfs merge=lfs -text
164
+ onnx__MatMul_8773 filter=lfs diff=lfs merge=lfs -text
165
+ onnx__MatMul_8780 filter=lfs diff=lfs merge=lfs -text
166
+ onnx__MatMul_8781 filter=lfs diff=lfs merge=lfs -text
167
+ onnx__MatMul_8804 filter=lfs diff=lfs merge=lfs -text
168
+ onnx__MatMul_8805 filter=lfs diff=lfs merge=lfs -text
169
+ onnx__MatMul_8806 filter=lfs diff=lfs merge=lfs -text
170
+ onnx__MatMul_8807 filter=lfs diff=lfs merge=lfs -text
171
+ onnx__MatMul_8808 filter=lfs diff=lfs merge=lfs -text
172
+ onnx__MatMul_8815 filter=lfs diff=lfs merge=lfs -text
173
+ onnx__MatMul_8816 filter=lfs diff=lfs merge=lfs -text
174
+ onnx__MatMul_8839 filter=lfs diff=lfs merge=lfs -text
175
+ onnx__MatMul_8840 filter=lfs diff=lfs merge=lfs -text
176
+ onnx__MatMul_8841 filter=lfs diff=lfs merge=lfs -text
177
+ onnx__MatMul_8842 filter=lfs diff=lfs merge=lfs -text
178
+ onnx__MatMul_8843 filter=lfs diff=lfs merge=lfs -text
179
+ onnx__MatMul_8850 filter=lfs diff=lfs merge=lfs -text
180
+ onnx__MatMul_8851 filter=lfs diff=lfs merge=lfs -text
181
+ onnx__MatMul_8874 filter=lfs diff=lfs merge=lfs -text
182
+ onnx__MatMul_8875 filter=lfs diff=lfs merge=lfs -text
183
+ onnx__MatMul_8876 filter=lfs diff=lfs merge=lfs -text
184
+ onnx__MatMul_8877 filter=lfs diff=lfs merge=lfs -text
185
+ onnx__MatMul_8878 filter=lfs diff=lfs merge=lfs -text
186
+ onnx__MatMul_8885 filter=lfs diff=lfs merge=lfs -text
187
+ onnx__MatMul_8886 filter=lfs diff=lfs merge=lfs -text
188
+ onnx__MatMul_8909 filter=lfs diff=lfs merge=lfs -text
189
+ onnx__MatMul_8910 filter=lfs diff=lfs merge=lfs -text
190
+ onnx__MatMul_8911 filter=lfs diff=lfs merge=lfs -text
191
+ onnx__MatMul_8912 filter=lfs diff=lfs merge=lfs -text
192
+ onnx__MatMul_8913 filter=lfs diff=lfs merge=lfs -text
193
+ onnx__MatMul_8920 filter=lfs diff=lfs merge=lfs -text
194
+ onnx__MatMul_8921 filter=lfs diff=lfs merge=lfs -text
195
+ onnx__MatMul_8944 filter=lfs diff=lfs merge=lfs -text
196
+ onnx__MatMul_8945 filter=lfs diff=lfs merge=lfs -text
197
+ onnx__MatMul_8946 filter=lfs diff=lfs merge=lfs -text
198
+ onnx__MatMul_8947 filter=lfs diff=lfs merge=lfs -text
199
+ onnx__MatMul_8948 filter=lfs diff=lfs merge=lfs -text
200
+ onnx__MatMul_8955 filter=lfs diff=lfs merge=lfs -text
201
+ onnx__MatMul_8956 filter=lfs diff=lfs merge=lfs -text
202
+ onnx__MatMul_8979 filter=lfs diff=lfs merge=lfs -text
203
+ onnx__MatMul_8980 filter=lfs diff=lfs merge=lfs -text
204
+ onnx__MatMul_8981 filter=lfs diff=lfs merge=lfs -text
205
+ onnx__MatMul_8982 filter=lfs diff=lfs merge=lfs -text
206
+ onnx__MatMul_8983 filter=lfs diff=lfs merge=lfs -text
207
+ onnx__MatMul_8990 filter=lfs diff=lfs merge=lfs -text
208
+ onnx__MatMul_8991 filter=lfs diff=lfs merge=lfs -text
209
+ onnx__MatMul_9014 filter=lfs diff=lfs merge=lfs -text
210
+ onnx__MatMul_9015 filter=lfs diff=lfs merge=lfs -text
211
+ onnx__MatMul_9016 filter=lfs diff=lfs merge=lfs -text
212
+ onnx__MatMul_9017 filter=lfs diff=lfs merge=lfs -text
213
+ onnx__MatMul_9018 filter=lfs diff=lfs merge=lfs -text
214
+ onnx__MatMul_9025 filter=lfs diff=lfs merge=lfs -text
215
+ onnx__MatMul_9026 filter=lfs diff=lfs merge=lfs -text
216
+ onnx__MatMul_9049 filter=lfs diff=lfs merge=lfs -text
217
+ onnx__MatMul_9050 filter=lfs diff=lfs merge=lfs -text
218
+ onnx__MatMul_9051 filter=lfs diff=lfs merge=lfs -text
219
+ onnx__MatMul_9052 filter=lfs diff=lfs merge=lfs -text
220
+ onnx__MatMul_9053 filter=lfs diff=lfs merge=lfs -text
221
+ onnx__MatMul_9060 filter=lfs diff=lfs merge=lfs -text
222
+ onnx__MatMul_9061 filter=lfs diff=lfs merge=lfs -text
223
+ onnx__MatMul_9084 filter=lfs diff=lfs merge=lfs -text
224
+ onnx__MatMul_9085 filter=lfs diff=lfs merge=lfs -text
225
+ onnx__MatMul_9086 filter=lfs diff=lfs merge=lfs -text
226
+ onnx__MatMul_9087 filter=lfs diff=lfs merge=lfs -text
227
+ onnx__MatMul_9088 filter=lfs diff=lfs merge=lfs -text
228
+ onnx__MatMul_9095 filter=lfs diff=lfs merge=lfs -text
229
+ onnx__MatMul_9096 filter=lfs diff=lfs merge=lfs -text
230
+ onnx__MatMul_9119 filter=lfs diff=lfs merge=lfs -text
231
+ onnx__MatMul_9120 filter=lfs diff=lfs merge=lfs -text
232
+ onnx__MatMul_9121 filter=lfs diff=lfs merge=lfs -text
233
+ onnx__MatMul_9122 filter=lfs diff=lfs merge=lfs -text
234
+ onnx__MatMul_9123 filter=lfs diff=lfs merge=lfs -text
model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887b9c33f46daf50787cecfde7d43efe1f96b1632ed2c0031d2b84ca975417bb
3
+ size 933494784
model.layers.0.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.0.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.0.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.1.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.1.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.1.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.10.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.10.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.10.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.11.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.11.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.11.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.12.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.12.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.12.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.13.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.13.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.13.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.14.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.14.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.14.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.15.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.15.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.15.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.16.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.16.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.16.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.17.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.17.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.17.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.18.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.18.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.18.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.19.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.19.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.19.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.2.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.2.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.2.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.20.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.20.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.20.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.21.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.21.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.21.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file
 
model.layers.22.input_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.22.post_attention_layernorm.weight ADDED
Binary file (6.14 kB). View file
 
model.layers.22.self_attn.q_proj.bias ADDED
Binary file (6.14 kB). View file