Hugging Face's logo

mlc-ai
/
Phi-3-mini-4k-instruct-q0f16-MLC

MLC-LLM
web-llm
Model card Files
xet
Community
mengshyu commited on
Commit
5851c13
·
verified ·
1 Parent(s): 1ef7361

Initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. added_tokens.json +13 -0
  2. logs.txt +257 -0
  3. mlc-chat-config.json +83 -0
  4. ndarray-cache.json +0 -0
  5. params_shard_0.bin +3 -0
  6. params_shard_1.bin +3 -0
  7. params_shard_10.bin +3 -0
  8. params_shard_100.bin +3 -0
  9. params_shard_101.bin +3 -0
  10. params_shard_102.bin +3 -0
  11. params_shard_103.bin +3 -0
  12. params_shard_104.bin +3 -0
  13. params_shard_105.bin +3 -0
  14. params_shard_106.bin +3 -0
  15. params_shard_107.bin +3 -0
  16. params_shard_108.bin +3 -0
  17. params_shard_109.bin +3 -0
  18. params_shard_11.bin +3 -0
  19. params_shard_110.bin +3 -0
  20. params_shard_111.bin +3 -0
  21. params_shard_112.bin +3 -0
  22. params_shard_113.bin +3 -0
  23. params_shard_114.bin +3 -0
  24. params_shard_115.bin +3 -0
  25. params_shard_116.bin +3 -0
  26. params_shard_117.bin +3 -0
  27. params_shard_118.bin +3 -0
  28. params_shard_119.bin +3 -0
  29. params_shard_12.bin +3 -0
  30. params_shard_120.bin +3 -0
  31. params_shard_121.bin +3 -0
  32. params_shard_122.bin +3 -0
  33. params_shard_123.bin +3 -0
  34. params_shard_124.bin +3 -0
  35. params_shard_125.bin +3 -0
  36. params_shard_126.bin +3 -0
  37. params_shard_127.bin +3 -0
  38. params_shard_128.bin +3 -0
  39. params_shard_129.bin +3 -0
  40. params_shard_13.bin +3 -0
  41. params_shard_14.bin +3 -0
  42. params_shard_15.bin +3 -0
  43. params_shard_16.bin +3 -0
  44. params_shard_17.bin +3 -0
  45. params_shard_18.bin +3 -0
  46. params_shard_19.bin +3 -0
  47. params_shard_2.bin +3 -0
  48. params_shard_20.bin +3 -0
  49. params_shard_21.bin +3 -0
  50. params_shard_22.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 32000,
3
+ "<|assistant|>": 32001,
4
+ "<|placeholder1|>": 32002,
5
+ "<|placeholder2|>": 32003,
6
+ "<|placeholder3|>": 32004,
7
+ "<|placeholder4|>": 32005,
8
+ "<|system|>": 32006,
9
+ "<|end|>": 32007,
10
+ "<|placeholder5|>": 32008,
11
+ "<|placeholder6|>": 32009,
12
+ "<|user|>": 32010
13
+ }
logs.txt ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/195 [00:00<?, ?it/s]
1
 
 
2
  0%| | 0/195 [00:00<?, ?it/s]
3
 
 
4
  0%| | 0/195 [00:00<?, ?it/s]
5
  1%| | 1/195 [00:01<04:13, 1.31s/it]
6
 
 
7
  1%| | 1/195 [00:01<04:13, 1.31s/it]
8
 
 
9
  1%| | 1/195 [00:01<04:13, 1.31s/it]
10
  2%|▏ | 3/195 [00:01<01:15, 2.54it/s]
11
 
 
12
  2%|▏ | 3/195 [00:01<01:15, 2.54it/s]
13
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
14
 
 
15
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
16
 
 
17
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
18
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
19
 
 
20
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
21
 
 
22
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
23
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
24
 
 
25
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
26
 
 
27
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
28
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
29
 
 
30
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
31
 
 
32
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
33
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
34
 
 
35
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
36
 
 
37
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
38
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
39
 
 
40
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
41
 
 
42
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
43
  8%|▊ | 16/195 [00:02<00:21, 8.16it/s]
44
 
 
45
  8%|▊ | 16/195 [00:02<00:21, 8.16it/s]
46
 
 
47
  8%|▊ | 16/195 [00:03<00:21, 8.16it/s]
48
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
49
 
 
50
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
51
 
 
52
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
53
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
54
 
 
55
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
56
 
 
57
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
58
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
59
 
 
60
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
61
 
 
62
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
63
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
64
 
 
65
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
66
 
 
67
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
68
  13%|█▎ | 26/195 [00:03<00:16, 10.09it/s]
69
 
 
70
  13%|█▎ | 26/195 [00:04<00:16, 10.09it/s]
71
 
 
72
  13%|█▎ | 26/195 [00:04<00:16, 10.09it/s]
73
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
74
 
 
75
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
76
 
 
77
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
78
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
79
 
 
80
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
81
 
 
82
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
83
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
84
 
 
85
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
86
 
 
87
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
88
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
89
 
 
90
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
91
 
 
92
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
93
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
94
 
 
95
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
96
 
 
97
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
98
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
99
 
 
100
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
101
 
 
102
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
103
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
104
 
 
105
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
106
 
 
107
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
108
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
109
 
 
110
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
111
 
 
112
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
113
  23%|██▎ | 44/195 [00:05<00:14, 10.37it/s]
114
 
 
115
  23%|██▎ | 44/195 [00:05<00:14, 10.37it/s]
116
 
 
117
  23%|██▎ | 44/195 [00:06<00:14, 10.37it/s]
118
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
119
 
 
120
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
121
 
 
122
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
123
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
124
 
 
125
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
126
 
 
127
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
128
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
129
 
 
130
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
131
 
 
132
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
133
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
134
 
 
135
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
136
 
 
137
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
138
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
139
 
 
140
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
141
 
 
142
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
143
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
144
 
 
145
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
146
 
 
147
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
148
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
149
 
 
150
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
151
 
 
152
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
153
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
154
 
 
155
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
156
 
 
157
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
158
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
159
 
 
160
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
161
 
 
162
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
163
  33%|███▎ | 64/195 [00:07<00:14, 9.13it/s]
164
 
 
165
  33%|███▎ | 64/195 [00:07<00:14, 9.13it/s]
166
 
 
167
  33%|███▎ | 64/195 [00:08<00:14, 9.13it/s]
168
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
169
 
 
170
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
171
 
 
172
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
173
 
 
174
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
175
 
 
176
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
177
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
178
 
 
179
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
180
 
 
181
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
182
  36%|███▌ | 70/195 [00:09<00:23, 5.34it/s]
183
 
 
184
  36%|███▌ | 70/195 [00:09<00:23, 5.34it/s]
185
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
186
 
 
187
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
188
 
 
189
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
190
 
 
191
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
192
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
193
 
 
194
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
195
 
 
196
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
197
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
198
 
 
199
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
200
 
 
201
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
202
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
203
 
 
204
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
205
 
 
206
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
207
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
208
 
 
209
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
210
 
 
211
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
212
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
213
 
 
214
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
215
 
 
216
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
217
  43%|████▎ | 84/195 [00:10<00:13, 8.31it/s]
218
 
 
219
  43%|████▎ | 84/195 [00:11<00:13, 8.31it/s]
220
 
 
221
  43%|████▎ | 84/195 [00:11<00:13, 8.31it/s]
222
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
223
 
 
224
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
225
 
 
226
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
227
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
228
 
 
229
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
230
 
 
231
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
232
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
233
 
 
234
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
235
 
 
236
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
237
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
238
 
 
239
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
240
 
 
241
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
242
  48%|████▊ | 94/195 [00:11<00:10, 10.10it/s]
243
 
 
244
  48%|████▊ | 94/195 [00:12<00:10, 10.10it/s]
245
 
 
246
  48%|████▊ | 94/195 [00:12<00:10, 10.10it/s]
247
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
248
 
 
249
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
250
 
 
251
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
252
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
253
 
 
254
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
255
 
 
256
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
257
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
258
 
 
259
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
260
 
 
261
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
262
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
263
 
 
264
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
265
 
 
266
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
267
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
268
 
 
269
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
270
 
 
271
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
272
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
273
 
 
274
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
275
 
 
276
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
277
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
278
 
 
279
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
280
 
 
281
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
282
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
283
 
 
284
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
285
 
 
286
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
287
  57%|█████▋ | 112/195 [00:13<00:07, 10.41it/s]
288
 
 
289
  57%|█████▋ | 112/195 [00:13<00:07, 10.41it/s]
290
 
 
291
  57%|█████▋ | 112/195 [00:14<00:07, 10.41it/s]
292
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
293
 
 
294
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
295
 
 
296
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
297
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
298
 
 
299
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
300
 
 
301
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
302
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
303
 
 
304
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
305
 
 
306
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
307
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
308
 
 
309
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
310
 
 
311
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
312
  63%|██████▎ | 122/195 [00:14<00:07, 9.34it/s]
313
 
 
314
  63%|██████▎ | 122/195 [00:14<00:07, 9.34it/s]
315
 
 
316
  63%|██████▎ | 122/195 [00:15<00:07, 9.34it/s]
317
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
318
 
 
319
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
320
 
 
321
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
322
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
323
 
 
324
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
325
 
 
326
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
327
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
328
 
 
329
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
330
 
 
331
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
332
  67%|██████▋ | 130/195 [00:15<00:06, 10.43it/s]
333
 
 
334
  67%|██████▋ | 130/195 [00:15<00:06, 10.43it/s]
335
 
 
336
  67%|██████▋ | 130/195 [00:16<00:06, 10.43it/s]
337
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
338
 
 
339
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
340
 
 
341
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
342
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
343
 
 
344
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
345
 
 
346
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
347
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
348
 
 
349
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
350
 
 
351
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
352
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
353
 
 
354
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
355
 
 
356
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
357
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
358
 
 
359
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
360
 
 
361
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
362
  73%|███████▎ | 142/195 [00:16<00:05, 10.42it/s]
363
 
 
364
  73%|███████▎ | 142/195 [00:17<00:05, 10.42it/s]
365
 
 
366
  73%|███████▎ | 142/195 [00:17<00:05, 10.42it/s]
367
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
368
 
 
369
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
370
 
 
371
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
372
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
373
 
 
374
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
375
 
 
376
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
377
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
378
 
 
379
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
380
 
 
381
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
382
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
383
 
 
384
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
385
 
 
386
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
387
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
388
 
 
389
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
390
 
 
391
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
392
 
 
393
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
394
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
395
 
 
396
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
397
 
 
398
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
399
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
400
 
 
401
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
402
 
 
403
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
404
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
405
 
 
406
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
407
 
 
408
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
409
  83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
410
 
 
411
  83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
412
 
 
413
  83%|████████▎ | 161/195 [00:19<00:03, 10.67it/s]
414
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
415
 
 
416
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
417
 
 
418
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
419
  85%|████████▍ | 165/195 [00:19<00:03, 9.46it/s]
420
 
 
421
  85%|��███████▍ | 165/195 [00:19<00:03, 9.46it/s]
422
 
 
423
  85%|████████▍ | 165/195 [00:19<00:03, 9.46it/s]
424
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
425
 
 
426
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
427
 
 
428
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
429
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
430
 
 
431
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
432
 
 
433
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
434
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
435
 
 
436
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
437
 
 
438
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
439
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
440
 
 
441
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
442
 
 
443
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
444
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
445
 
 
446
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
447
 
 
448
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
449
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
450
 
 
451
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
452
 
 
453
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
454
  92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
455
 
 
456
  92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
457
 
 
458
  92%|█████████▏| 179/195 [00:21<00:01, 10.42it/s]
459
  93%|█████████▎| 181/195 [00:21<00:01, 9.15it/s]
460
 
 
461
  93%|██���██████▎| 181/195 [00:21<00:01, 9.15it/s]
462
 
 
463
  93%|█████████▎| 181/195 [00:21<00:01, 9.15it/s]
464
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
465
 
 
466
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
467
 
 
468
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
469
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
470
 
 
471
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
472
 
 
473
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
474
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
475
 
 
476
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
477
 
 
478
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
479
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
480
 
 
481
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
482
 
 
483
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
484
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
485
 
 
486
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
487
 
 
488
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
489
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
490
 
 
491
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
492
 
 
493
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
 
 
 
 
 
 
 
 
 
 
1
+ /home/msyu/workspace/venv/bin/python -m mlc_llm gen_config /tmp/tmpy7oe9l51/repo --quantization q0f16 --conv-template phi-3 --output /tmp/tmpg82xy6xr
2
+ [2024-05-08 13:36:57] INFO auto_config.py:115: Found model configuration: /tmp/tmpy7oe9l51/repo/config.json
3
+ [2024-05-08 13:36:57] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
4
+ [2024-05-08 13:36:57] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
5
+ [2024-05-08 13:36:57] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
6
+ [2024-05-08 13:36:57] INFO config.py:106: Overriding max_batch_size from 1 to 80
7
+ [2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
8
+ [2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007]
9
+ [2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 32000
10
+ [2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.model. Copying to /tmp/tmpg82xy6xr/tokenizer.model
11
+ [2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.json. Copying to /tmp/tmpg82xy6xr/tokenizer.json
12
+ [2024-05-08 13:36:57] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpy7oe9l51/repo/vocab.json
13
+ [2024-05-08 13:36:57] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpy7oe9l51/repo/merges.txt
14
+ [2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/added_tokens.json. Copying to /tmp/tmpg82xy6xr/added_tokens.json
15
+ [2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer_config.json. Copying to /tmp/tmpg82xy6xr/tokenizer_config.json
16
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting temperature: 0.7
17
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
18
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
19
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
20
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting top_p: 0.95
21
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
22
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
23
+ [2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
24
+ [2024-05-08 13:36:57] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpg82xy6xr/mlc-chat-config.json
25
+ /home/msyu/workspace/venv/bin/python -m mlc_llm convert_weight /tmp/tmpy7oe9l51/repo --quantization q0f16 --source-format auto --output /tmp/tmpg82xy6xr
26
+ [2024-05-08 13:36:58] INFO auto_config.py:115: Found model configuration: /tmp/tmpy7oe9l51/repo/config.json
27
+ [2024-05-08 13:36:59] INFO auto_device.py:79: Found device: cuda:0
28
+ [2024-05-08 13:36:59] INFO auto_device.py:88: Not found device: rocm:0
29
+ [2024-05-08 13:37:00] INFO auto_device.py:88: Not found device: metal:0
30
+ [2024-05-08 13:37:01] INFO auto_device.py:88: Not found device: vulkan:0
31
+ [2024-05-08 13:37:01] INFO auto_device.py:79: Found device: opencl:0
32
+ [2024-05-08 13:37:01] INFO auto_device.py:35: Using device: cuda:0
33
+ [2024-05-08 13:37:01] INFO auto_weight.py:70: Finding weights in: /tmp/tmpy7oe9l51/repo
34
+ [2024-05-08 13:37:01] INFO auto_weight.py:136: Not found Huggingface PyTorch
35
+ [2024-05-08 13:37:01] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
36
+ [2024-05-08 13:37:01] INFO auto_weight.py:106: Using source weight configuration: /tmp/tmpy7oe9l51/repo/model.safetensors.index.json. Use `--source` to override.
37
+ [2024-05-08 13:37:01] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
38
+ [2024-05-08 13:37:01] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
39
+ [2024-05-08 13:37:01] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
40
+ [2024-05-08 13:37:01] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
41
+ Weight conversion with arguments:
42
+ --config /tmp/tmpy7oe9l51/repo/config.json
43
+ --quantization NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
44
+ --model-type phi3
45
+ --device cuda:0
46
+ --source /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
47
+ --source-format huggingface-safetensor
48
+ --output /tmp/tmpg82xy6xr
49
+ Start storing to cache /tmp/tmpg82xy6xr
50
+
51
  0%| | 0/195 [00:00<?, ?it/s]
52
 
53
+
54
  0%| | 0/195 [00:00<?, ?it/s]
55
 
56
+
57
  0%| | 0/195 [00:00<?, ?it/s]
58
  1%| | 1/195 [00:01<04:13, 1.31s/it]
59
 
60
+
61
  1%| | 1/195 [00:01<04:13, 1.31s/it]
62
 
63
+
64
  1%| | 1/195 [00:01<04:13, 1.31s/it]
65
  2%|▏ | 3/195 [00:01<01:15, 2.54it/s]
66
 
67
+
68
  2%|▏ | 3/195 [00:01<01:15, 2.54it/s]
69
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
70
 
71
+
72
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
73
 
74
+
75
  2%|▏ | 4/195 [00:01<01:07, 2.82it/s]
76
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
77
 
78
+
79
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
80
 
81
+
82
  3%|▎ | 6/195 [00:01<00:41, 4.57it/s]
83
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
84
 
85
+
86
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
87
 
88
+
89
  4%|▍ | 8/195 [00:02<00:29, 6.36it/s]
90
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
91
 
92
+
93
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
94
 
95
+
96
  5%|▌ | 10/195 [00:02<00:28, 6.56it/s]
97
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
98
 
99
+
100
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
101
 
102
+
103
  6%|▌ | 12/195 [00:02<00:24, 7.54it/s]
104
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
105
 
106
+
107
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
108
 
109
+
110
  7%|▋ | 14/195 [00:02<00:20, 8.89it/s]
111
  8%|▊ | 16/195 [00:02<00:21, 8.16it/s]
112
 
113
+
114
  8%|▊ | 16/195 [00:02<00:21, 8.16it/s]
115
 
116
+
117
  8%|▊ | 16/195 [00:03<00:21, 8.16it/s]
118
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
119
 
120
+
121
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
122
 
123
+
124
  9%|▉ | 18/195 [00:03<00:20, 8.55it/s]
125
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
126
 
127
+
128
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
129
 
130
+
131
  10%|█ | 20/195 [00:03<00:18, 9.72it/s]
132
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
133
 
134
+
135
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
136
 
137
+
138
  11%|█▏ | 22/195 [00:03<00:19, 8.66it/s]
139
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
140
 
141
+
142
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
143
 
144
+
145
  12%|█▏ | 24/195 [00:03<00:19, 8.96it/s]
146
  13%|█▎ | 26/195 [00:03<00:16, 10.09it/s]
147
 
148
+
149
  13%|█▎ | 26/195 [00:04<00:16, 10.09it/s]
150
 
151
+
152
  13%|█▎ | 26/195 [00:04<00:16, 10.09it/s]
153
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
154
 
155
+
156
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
157
 
158
+
159
  14%|█▍ | 28/195 [00:04<00:18, 8.95it/s]
160
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
161
 
162
+
163
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
164
 
165
+
166
  15%|█▌ | 30/195 [00:04<00:17, 9.18it/s]
167
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
168
 
169
+
170
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
171
 
172
+
173
  16%|█▋ | 32/195 [00:04<00:15, 10.29it/s]
174
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
175
 
176
+
177
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
178
 
179
+
180
  17%|█▋ | 34/195 [00:04<00:17, 9.06it/s]
181
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
182
 
183
+
184
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
185
 
186
+
187
  18%|█▊ | 36/195 [00:05<00:17, 9.26it/s]
188
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
189
 
190
+
191
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
192
 
193
+
194
  19%|█▉ | 38/195 [00:05<00:15, 10.35it/s]
195
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
196
 
197
+
198
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
199
 
200
+
201
  21%|██ | 40/195 [00:05<00:17, 9.10it/s]
202
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
203
 
204
+
205
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
206
 
207
+
208
  22%|██▏ | 42/195 [00:05<00:16, 9.29it/s]
209
  23%|██▎ | 44/195 [00:05<00:14, 10.37it/s]
210
 
211
+
212
  23%|██▎ | 44/195 [00:05<00:14, 10.37it/s]
213
 
214
+
215
  23%|██▎ | 44/195 [00:06<00:14, 10.37it/s]
216
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
217
 
218
+
219
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
220
 
221
+
222
  24%|██▎ | 46/195 [00:06<00:16, 9.11it/s]
223
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
224
 
225
+
226
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
227
 
228
+
229
  25%|██▍ | 48/195 [00:06<00:15, 9.29it/s]
230
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
231
 
232
+
233
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
234
 
235
+
236
  26%|██▌ | 50/195 [00:06<00:13, 10.37it/s]
237
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
238
 
239
+
240
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
241
 
242
+
243
  27%|██▋ | 52/195 [00:06<00:15, 9.12it/s]
244
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
245
 
246
+
247
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
248
 
249
+
250
  28%|██▊ | 54/195 [00:06<00:15, 9.31it/s]
251
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
252
 
253
+
254
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
255
 
256
+
257
  29%|██▊ | 56/195 [00:07<00:13, 10.39it/s]
258
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
259
 
260
+
261
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
262
 
263
+
264
  30%|██▉ | 58/195 [00:07<00:15, 9.12it/s]
265
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
266
 
267
+
268
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
269
 
270
+
271
  31%|███ | 60/195 [00:07<00:14, 9.31it/s]
272
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
273
 
274
+
275
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
276
 
277
+
278
  32%|███▏ | 62/195 [00:07<00:12, 10.38it/s]
279
  33%|███▎ | 64/195 [00:07<00:14, 9.13it/s]
280
 
281
+
282
  33%|███▎ | 64/195 [00:07<00:14, 9.13it/s]
283
 
284
+
285
  33%|███▎ | 64/195 [00:08<00:14, 9.13it/s]
286
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
287
 
288
+
289
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
290
 
291
+
292
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
293
 
294
+
295
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
296
 
297
+
298
  34%|███▍ | 66/195 [00:08<00:13, 9.31it/s]
299
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
300
 
301
+
302
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
303
 
304
+
305
  35%|███▍ | 68/195 [00:09<00:30, 4.23it/s]
306
  36%|███▌ | 70/195 [00:09<00:23, 5.34it/s]
307
 
308
+
309
  36%|███▌ | 70/195 [00:09<00:23, 5.34it/s]
310
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
311
 
312
+
313
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
314
 
315
+
316
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
317
 
318
+
319
  36%|███▋ | 71/195 [00:09<00:25, 4.93it/s]
320
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
321
 
322
+
323
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
324
 
325
+
326
  38%|███▊ | 74/195 [00:09<00:17, 6.86it/s]
327
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
328
 
329
+
330
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
331
 
332
+
333
  39%|███▉ | 76/195 [00:10<00:14, 8.09it/s]
334
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
335
 
336
+
337
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
338
 
339
+
340
  40%|████ | 78/195 [00:10<00:15, 7.41it/s]
341
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
342
 
343
+
344
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
345
 
346
+
347
  41%|████ | 80/195 [00:10<00:14, 7.92it/s]
348
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
349
 
350
+
351
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
352
 
353
+
354
  42%|████▏ | 82/195 [00:10<00:12, 9.07it/s]
355
  43%|████▎ | 84/195 [00:10<00:13, 8.31it/s]
356
 
357
+
358
  43%|████▎ | 84/195 [00:11<00:13, 8.31it/s]
359
 
360
+
361
  43%|████▎ | 84/195 [00:11<00:13, 8.31it/s]
362
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
363
 
364
+
365
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
366
 
367
+
368
  44%|████▍ | 86/195 [00:11<00:12, 8.62it/s]
369
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
370
 
371
+
372
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
373
 
374
+
375
  45%|████▌ | 88/195 [00:11<00:11, 9.73it/s]
376
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
377
 
378
+
379
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
380
 
381
+
382
  46%|████▌ | 90/195 [00:11<00:12, 8.67it/s]
383
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
384
 
385
+
386
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
387
 
388
+
389
  47%|████▋ | 92/195 [00:11<00:11, 8.97it/s]
390
  48%|████▊ | 94/195 [00:11<00:10, 10.10it/s]
391
 
392
+
393
  48%|████▊ | 94/195 [00:12<00:10, 10.10it/s]
394
 
395
+
396
  48%|████▊ | 94/195 [00:12<00:10, 10.10it/s]
397
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
398
 
399
+
400
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
401
 
402
+
403
  49%|████▉ | 96/195 [00:12<00:11, 8.98it/s]
404
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
405
 
406
+
407
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
408
 
409
+
410
  50%|█████ | 98/195 [00:12<00:10, 9.20it/s]
411
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
412
 
413
+
414
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
415
 
416
+
417
  51%|█████▏ | 100/195 [00:12<00:09, 10.31it/s]
418
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
419
 
420
+
421
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
422
 
423
+
424
  52%|█████▏ | 102/195 [00:12<00:10, 9.10it/s]
425
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
426
 
427
+
428
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
429
 
430
+
431
  53%|█████▎ | 104/195 [00:13<00:09, 9.29it/s]
432
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
433
 
434
+
435
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
436
 
437
+
438
  54%|█████▍ | 106/195 [00:13<00:08, 10.38it/s]
439
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
440
 
441
+
442
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
443
 
444
+
445
  55%|█████▌ | 108/195 [00:13<00:09, 9.14it/s]
446
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
447
 
448
+
449
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
450
 
451
+
452
  56%|█████▋ | 110/195 [00:13<00:09, 9.33it/s]
453
  57%|█████▋ | 112/195 [00:13<00:07, 10.41it/s]
454
 
455
+
456
  57%|█████▋ | 112/195 [00:13<00:07, 10.41it/s]
457
 
458
+
459
  57%|█████▋ | 112/195 [00:14<00:07, 10.41it/s]
460
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
461
 
462
+
463
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
464
 
465
+
466
  58%|█████▊ | 114/195 [00:14<00:08, 9.15it/s]
467
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
468
 
469
+
470
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
471
 
472
+
473
  59%|█████▉ | 116/195 [00:14<00:08, 9.34it/s]
474
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
475
 
476
+
477
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
478
 
479
+
480
  61%|██████ | 118/195 [00:14<00:07, 10.43it/s]
481
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
482
 
483
+
484
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
485
 
486
+
487
  62%|██████▏ | 120/195 [00:14<00:08, 9.16it/s]
488
  63%|██████▎ | 122/195 [00:14<00:07, 9.34it/s]
489
 
490
+
491
  63%|██████▎ | 122/195 [00:14<00:07, 9.34it/s]
492
 
493
+
494
  63%|██████▎ | 122/195 [00:15<00:07, 9.34it/s]
495
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
496
 
497
+
498
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
499
 
500
+
501
  64%|██████▎ | 124/195 [00:15<00:06, 10.42it/s]
502
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
503
 
504
+
505
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
506
 
507
+
508
  65%|██████▍ | 126/195 [00:15<00:07, 9.16it/s]
509
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
510
 
511
+
512
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
513
 
514
+
515
  66%|██████▌ | 128/195 [00:15<00:07, 9.34it/s]
516
  67%|██████▋ | 130/195 [00:15<00:06, 10.43it/s]
517
 
518
+
519
  67%|██████▋ | 130/195 [00:15<00:06, 10.43it/s]
520
 
521
+
522
  67%|██████▋ | 130/195 [00:16<00:06, 10.43it/s]
523
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
524
 
525
+
526
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
527
 
528
+
529
  68%|██████▊ | 132/195 [00:16<00:06, 9.16it/s]
530
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
531
 
532
+
533
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
534
 
535
+
536
  69%|██████▊ | 134/195 [00:16<00:06, 9.33it/s]
537
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
538
 
539
+
540
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
541
 
542
+
543
  70%|██████▉ | 136/195 [00:16<00:05, 10.42it/s]
544
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
545
 
546
+
547
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
548
 
549
+
550
  71%|███████ | 138/195 [00:16<00:06, 9.16it/s]
551
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
552
 
553
+
554
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
555
 
556
+
557
  72%|███████▏ | 140/195 [00:16<00:05, 9.34it/s]
558
  73%|███████▎ | 142/195 [00:16<00:05, 10.42it/s]
559
 
560
+
561
  73%|███████▎ | 142/195 [00:17<00:05, 10.42it/s]
562
 
563
+
564
  73%|███████▎ | 142/195 [00:17<00:05, 10.42it/s]
565
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
566
 
567
+
568
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
569
 
570
+
571
  74%|███████▍ | 144/195 [00:17<00:05, 9.16it/s]
572
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
573
 
574
+
575
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
576
 
577
+
578
  75%|███████▍ | 146/195 [00:17<00:05, 9.34it/s]
579
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
580
 
581
+
582
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
583
 
584
+
585
  76%|███████▌ | 148/195 [00:17<00:04, 10.42it/s]
586
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
587
 
588
+
589
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
590
 
591
+
592
  77%|███████▋ | 150/195 [00:17<00:04, 9.16it/s]
593
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
594
 
595
+
596
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
597
 
598
+
599
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
600
 
601
+
602
  78%|███████▊ | 152/195 [00:18<00:04, 9.33it/s]
603
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
604
 
605
+
606
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
607
 
608
+
609
  79%|███████▉ | 155/195 [00:18<00:03, 11.11it/s]
610
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
611
 
612
+
613
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
614
 
615
+
616
  81%|████████ | 157/195 [00:18<00:03, 9.65it/s]
617
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
618
 
619
+
620
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
621
 
622
+
623
  82%|████████▏ | 159/195 [00:18<00:03, 9.70it/s]
624
  83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
625
 
626
+
627
  83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
628
 
629
+
630
  83%|████████▎ | 161/195 [00:19<00:03, 10.67it/s]
631
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
632
 
633
+
634
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
635
 
636
+
637
  84%|████████▎ | 163/195 [00:19<00:03, 9.33it/s]
638
  85%|████████▍ | 165/195 [00:19<00:03, 9.46it/s]
639
 
640
+
641
  85%|��███████▍ | 165/195 [00:19<00:03, 9.46it/s]
642
 
643
+
644
  85%|████████▍ | 165/195 [00:19<00:03, 9.46it/s]
645
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
646
 
647
+
648
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
649
 
650
+
651
  86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
652
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
653
 
654
+
655
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
656
 
657
+
658
  87%|████████▋ | 169/195 [00:19<00:02, 9.22it/s]
659
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
660
 
661
+
662
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
663
 
664
+
665
  88%|████████▊ | 171/195 [00:20<00:02, 9.38it/s]
666
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
667
 
668
+
669
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
670
 
671
+
672
  89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
673
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
674
 
675
+
676
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
677
 
678
+
679
  90%|████████▉ | 175/195 [00:20<00:02, 9.17it/s]
680
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
681
 
682
+
683
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
684
 
685
+
686
  91%|█████████ | 177/195 [00:20<00:01, 9.34it/s]
687
  92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
688
 
689
+
690
  92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
691
 
692
+
693
  92%|█████████▏| 179/195 [00:21<00:01, 10.42it/s]
694
  93%|█████████▎| 181/195 [00:21<00:01, 9.15it/s]
695
 
696
+
697
  93%|██���██████▎| 181/195 [00:21<00:01, 9.15it/s]
698
 
699
+
700
  93%|█████████▎| 181/195 [00:21<00:01, 9.15it/s]
701
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
702
 
703
+
704
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
705
 
706
+
707
  94%|█████████▍| 183/195 [00:21<00:01, 9.33it/s]
708
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
709
 
710
+
711
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
712
 
713
+
714
  95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
715
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
716
 
717
+
718
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
719
 
720
+
721
  96%|█████████▌| 187/195 [00:21<00:00, 9.14it/s]
722
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
723
 
724
+
725
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
726
 
727
+
728
  97%|█████████▋| 189/195 [00:21<00:00, 9.33it/s]
729
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
730
 
731
+
732
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
733
 
734
+
735
  98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
736
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
737
 
738
+
739
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
740
 
741
+
742
  99%|█████████▉| 193/195 [00:22<00:00, 9.13it/s]
743
+ [2024-05-08 13:37:25] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpy7oe9l51/repo/model-00001-of-00002.safetensors
744
+ [2024-05-08 13:37:25] INFO stats.py:76: Time usage: HF loading: 1.450 sec; Pre-quantization mapping: 5.723 sec; Quantization: 0.000 sec
745
+ [2024-05-08 13:37:25] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
746
+ [2024-05-08 13:37:25] INFO convert_weight.py:155: Parameter size after quantization: 7.117 GB
747
+ [2024-05-08 13:37:25] INFO convert_weight.py:160: Total parameters: 3,821,079,552
748
+ [2024-05-08 13:37:25] INFO convert_weight.py:161: Bits per parameter: 16.000
749
+ [2024-05-08 13:37:25] INFO convert_weight.py:166: Saved to directory: /tmp/tmpg82xy6xr
750
+
751
+ All finished, 130 total shards committed, record saved to /tmp/tmpg82xy6xr/ndarray-cache.json
mlc-chat-config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "phi3",
3
+ "quantization": "q0f16",
4
+ "model_config": {
5
+ "model_type": "phi3",
6
+ "hidden_size": 3072,
7
+ "vocab_size": 32064,
8
+ "num_hidden_layers": 32,
9
+ "num_attention_heads": 32,
10
+ "intermediate_size": 8192,
11
+ "rms_norm_eps": 1e-05,
12
+ "num_key_value_heads": 32,
13
+ "position_embedding_base": 10000.0,
14
+ "context_window_size": 4096,
15
+ "prefill_chunk_size": 2048,
16
+ "head_dim": 96,
17
+ "tensor_parallel_shards": 1,
18
+ "max_batch_size": 80
19
+ },
20
+ "vocab_size": 32064,
21
+ "context_window_size": 4096,
22
+ "sliding_window_size": -1,
23
+ "prefill_chunk_size": 2048,
24
+ "attention_sink_size": -1,
25
+ "tensor_parallel_shards": 1,
26
+ "mean_gen_len": 128,
27
+ "max_gen_len": 512,
28
+ "shift_fill_factor": 0.3,
29
+ "temperature": 0.7,
30
+ "presence_penalty": 0.0,
31
+ "frequency_penalty": 0.0,
32
+ "repetition_penalty": 1.0,
33
+ "top_p": 0.95,
34
+ "conv_template": {
35
+ "name": "phi-3",
36
+ "system_template": "<|system|>\n{system_message}",
37
+ "system_message": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user.",
38
+ "system_prefix_token_ids": [
39
+ 1
40
+ ],
41
+ "add_role_after_system_message": true,
42
+ "roles": {
43
+ "user": "<|user|>",
44
+ "assistant": "<|assistant|>"
45
+ },
46
+ "role_templates": {
47
+ "user": "{user_message}",
48
+ "assistant": "{assistant_message}",
49
+ "tool": "{tool_message}"
50
+ },
51
+ "messages": [],
52
+ "seps": [
53
+ "<|end|>\n"
54
+ ],
55
+ "role_content_sep": "\n",
56
+ "role_empty_sep": "\n",
57
+ "stop_str": [
58
+ "<|endoftext|>"
59
+ ],
60
+ "stop_token_ids": [
61
+ 32000,
62
+ 32001,
63
+ 32007
64
+ ],
65
+ "function_string": "",
66
+ "use_function_calling": false
67
+ },
68
+ "pad_token_id": 32000,
69
+ "bos_token_id": 1,
70
+ "eos_token_id": [
71
+ 32000,
72
+ 32001,
73
+ 32007
74
+ ],
75
+ "tokenizer_files": [
76
+ "tokenizer.model",
77
+ "tokenizer.json",
78
+ "added_tokens.json",
79
+ "tokenizer_config.json"
80
+ ],
81
+ "token_table_postproc_method": "byte_fallback",
82
+ "version": "0.1.0"
83
+ }
ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f6ce4c0566e1035774ee75a934ffcb58d51dc20a5bcdd8c2a74433becf565d
3
+ size 197001216
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298488115a6fd27e607d24df2373e152f73598e4bd860da624fd9f39f6bb98de
3
+ size 50331648
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8af7196fa73d8ba5a5babc543b9e8dbbc8d1e2dd1a434f5353888e9ebb6afb
3
+ size 56623104
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8544aab8f592204056dbd4dcc4a09c351c3a574fc4067561dcd4711f8cb21e4c
3
+ size 18874368
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4786937ee53da3ab35b6440dbc22babd23811af59c5ef4c1c61bb9c7662ef13e
3
+ size 50331648
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999ffe143dbaade865fd510608a5803e7851ad6c36fe5633718b94a212325186
3
+ size 100663296
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c113f6740e75d090ae5e5dda433a706462af040b26065213132dd2f9f2aeabfe
3
+ size 18874368
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b938e3fec35a8f7e558a26c2b83b141c193ec931afac235b7e402153b1984b0
3
+ size 56623104
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57612e1b40a51f2b311c75e6aee9b42fd72ba56d7bcbbdb29b1095be73237b8
3
+ size 50331648
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2196d0231f9b06deb8c34997bab9ea31a461981f5e6daded885cca722102fc
3
+ size 100663296
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646aef6a6f7f03158af09c4df8b2b65f5b2b8f23e5b7117cea8562c79d17f817
3
+ size 18874368
params_shard_108.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea80f5e943b36d93366393cc637e8d1bd21efd41ad1af45620f5f9a5902e5cfa
3
+ size 56623104
params_shard_109.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5ccd7899c75a75eb4e7c81f787a11030feb8880aed644ed22909c1f7e4358d
3
+ size 50331648
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff641e91d92c92b3bdab87ce44bd057ba887cc6e14942f305a4159756704f1b
3
+ size 50331648
params_shard_110.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a4a4a27eb374862dcb62c0eb7b387cca41b0e8cf0ab23c2ec77f6bd2fadc96
3
+ size 100663296
params_shard_111.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15691582973b5d08e9a10fd7cd9565e4a5a8ca301b9fd6380e1e185f0693ff2a
3
+ size 18874368
params_shard_112.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df329fb69b6cd0e755673ee6c45d82ebfcac49af4b5237093c942ba0bff123f4
3
+ size 56623104
params_shard_113.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd292857ac71d144bbfde66eaae2fcb9ad84023c59d98120418d1fb79d7d32a
3
+ size 50331648
params_shard_114.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61790dac2a8e7384282776b72f2e48bf74d19425c05f949e626f992149060954
3
+ size 100663296
params_shard_115.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355da08dd871b3999ba256810753f9b3cd0a9507a7346c1062838efc1a374957
3
+ size 18874368
params_shard_116.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe7eda308a0563c120007756f1f0c5a5acde6c8184eb93714e075602be658e
3
+ size 56623104
params_shard_117.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94eed71126ebbe2c7cf2092518193f2aca8b2014986403c1313b8831fa086952
3
+ size 50331648
params_shard_118.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61170af6ff402851f070075e2b3fcea44fe5f88ce42f594e2dc8e7bad1534736
3
+ size 100663296
params_shard_119.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72808bf3c676ef7ac1c912d8f48b97a542bc47a206cbc7c68a640e454157fbd
3
+ size 18874368
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f727558fba7d83222b6a244330a46adf82af26ad3f7b64d8c4ced582871695f2
3
+ size 100663296
params_shard_120.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6223e1890e6e8919f1887f70b8621ba1fcd88268bc56404d721eba2de5e79c1
3
+ size 56623104
params_shard_121.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c809984899c167b10546b236376ab064f5c7b65e048fef1520b7b9c964e6a1
3
+ size 50331648
params_shard_122.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb1e6aebd6841f462ecbcc4d524d976e17cd3343edb7fd74c4c66a5f086a9ca
3
+ size 100663296
params_shard_123.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4f4d496dda015be71702693315307b6cd326ecf5a5c8d4dda033ffae8265b9
3
+ size 18874368
params_shard_124.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e770f5bd726597ec6f76c4dc91325aceef33d4681ef8d5605bb28d3fe913a96a
3
+ size 56623104
params_shard_125.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53888301d51a3af7884f38ef3c5114cf692cebb13afad90e9d0c6ffac0a20acd
3
+ size 50331648
params_shard_126.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3326abc9750595c472a73cce0bc6b7c7584791ebdffd3dd3bf456d45e37fe4
3
+ size 100663296
params_shard_127.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cf60df37c184d24fa3e26970d3cfa2b0cdcca0f30cebebe41c5cc05b711af7
3
+ size 18874368
params_shard_128.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251aae451757a591edc241cdb38e0c82d452a615eed66991686ac0676cec214b
3
+ size 56623104
params_shard_129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d426576c1432f9816ac2605eb9634d983f6fafba9fd4dfeafee6c6fa7d54a5fd
3
+ size 19273728
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b620f1100d235cca9b1a8f5813ec2dc242aa6587de4a1e57fef8444a3c538543
3
+ size 18874368
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9baeb4a3b4512ed6cba411e2e50cf3b5a1f756a5f8b8793fadb72afb3e168496
3
+ size 56623104
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0001309515efbd0332c17f65bef7d9a021788a5d38a0512dc0233c28440fbf
3
+ size 50331648
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a2f8b0e145fd1bb31b86dd16b50d9c30223b90a1a24acad8b9c4f7918b8e7e
3
+ size 100663296
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240a1528b2aff56d6e9737f76c2aa6982d15fa0e320bb46888d3f9fe4568e955
3
+ size 18874368
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc1c7c980ce6f2d7960e925a61e0528fad4b8c601f6f82d0bbba2e7673248e5
3
+ size 56623104
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b25d5b417fc2c043090e6a238d6d617d61bbc5b6ea8328a1e9933adbe78225
3
+ size 50331648
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9adb5ed55b079b48151d35713be9ce5ddd6c7b92d46876498048b2975b0ed7
3
+ size 100663296
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c663f55a1bca4ab657c70691540b927a77f07783027b097aef3d6e214c0693
3
+ size 100663296
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d152ac5c056f23bb457a2fe2dedc65cb84a92d80beca8828f22d3a92feffee2
3
+ size 18874368
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfd2d2ca8742a814a74b7aab86f0636d49024ea34f2bfa4f6b0415530687a7c
3
+ size 56623104