Hugging Face's logo

Tlopex
/
stablelm-2-zephyr-1_6b-q0f16-MLC

Model card Files Community
Tlopex commited on
Commit
af9695b
·
verified ·
1 Parent(s): f5658ff

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. logs.txt +281 -0
  2. merges.txt +0 -0
  3. mlc-chat-config.json +76 -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_11.bin +3 -0
  9. params_shard_12.bin +3 -0
  10. params_shard_13.bin +3 -0
  11. params_shard_14.bin +3 -0
  12. params_shard_15.bin +3 -0
  13. params_shard_16.bin +3 -0
  14. params_shard_17.bin +3 -0
  15. params_shard_18.bin +3 -0
  16. params_shard_19.bin +3 -0
  17. params_shard_2.bin +3 -0
  18. params_shard_20.bin +3 -0
  19. params_shard_21.bin +3 -0
  20. params_shard_22.bin +3 -0
  21. params_shard_23.bin +3 -0
  22. params_shard_24.bin +3 -0
  23. params_shard_25.bin +3 -0
  24. params_shard_26.bin +3 -0
  25. params_shard_27.bin +3 -0
  26. params_shard_28.bin +3 -0
  27. params_shard_29.bin +3 -0
  28. params_shard_3.bin +3 -0
  29. params_shard_30.bin +3 -0
  30. params_shard_31.bin +3 -0
  31. params_shard_32.bin +3 -0
  32. params_shard_33.bin +3 -0
  33. params_shard_34.bin +3 -0
  34. params_shard_35.bin +3 -0
  35. params_shard_36.bin +3 -0
  36. params_shard_37.bin +3 -0
  37. params_shard_38.bin +3 -0
  38. params_shard_39.bin +3 -0
  39. params_shard_4.bin +3 -0
  40. params_shard_40.bin +3 -0
  41. params_shard_41.bin +3 -0
  42. params_shard_42.bin +3 -0
  43. params_shard_43.bin +3 -0
  44. params_shard_44.bin +3 -0
  45. params_shard_45.bin +3 -0
  46. params_shard_46.bin +3 -0
  47. params_shard_47.bin +3 -0
  48. params_shard_48.bin +3 -0
  49. params_shard_49.bin +3 -0
  50. params_shard_5.bin +3 -0
logs.txt ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/220 [00:00<?, ?it/s]
1
 
 
2
  0%| | 0/220 [00:00<?, ?it/s]
3
 
 
4
  0%| | 0/220 [00:03<?, ?it/s]
5
  0%| | 1/220 [00:04<17:07, 4.69s/it]
6
 
 
7
  0%| | 1/220 [00:06<17:07, 4.69s/it]
8
  1%| | 2/220 [00:07<13:33, 3.73s/it]
9
 
 
10
  1%| | 2/220 [00:07<13:33, 3.73s/it]
11
 
 
12
  1%| | 2/220 [00:07<13:33, 3.73s/it]
13
 
 
14
  1%| | 2/220 [00:07<13:33, 3.73s/it]
15
 
 
16
  1%| | 2/220 [00:08<13:33, 3.73s/it]
17
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
18
 
 
19
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
20
 
 
21
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
22
 
 
23
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
24
 
 
25
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
26
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
27
 
 
28
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
29
 
 
30
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
31
 
 
32
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
33
 
 
34
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
35
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
36
 
 
37
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
38
 
 
39
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
40
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
41
 
 
42
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
43
 
 
44
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
45
 
 
46
  7%|▋ | 16/220 [00:09<00:55, 3.68it/s]
47
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
48
 
 
49
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
50
 
 
51
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
52
 
 
53
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
54
 
 
55
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
56
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
57
 
 
58
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
59
 
 
60
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
61
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
62
 
 
63
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
64
 
 
65
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
66
 
 
67
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
68
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
69
 
 
70
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
71
 
 
72
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
73
 
 
74
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
75
 
 
76
  13%|█▎ | 28/220 [00:10<00:22, 8.46it/s]
77
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
78
 
 
79
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
80
 
 
81
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
82
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
83
 
 
84
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
85
 
 
86
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
87
 
 
88
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
89
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
90
 
 
91
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
92
 
 
93
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
94
 
 
95
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
96
 
 
97
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
98
  19%|█▊ | 41/220 [00:10<00:14, 12.77it/s]
99
 
 
100
  19%|█▊ | 41/220 [00:11<00:14, 12.77it/s]
101
 
 
102
  19%|█▊ | 41/220 [00:11<00:14, 12.77it/s]
103
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
104
 
 
105
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
106
 
 
107
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
108
 
 
109
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
110
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
111
 
 
112
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
113
 
 
114
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
115
 
 
116
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
117
 
 
118
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
119
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
120
 
 
121
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
122
 
 
123
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
124
 
 
125
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
126
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
127
 
 
128
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
129
 
 
130
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
131
 
 
132
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
133
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
134
 
 
135
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
136
 
 
137
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
138
 
 
139
  25%|██▌ | 56/220 [00:12<00:11, 14.10it/s]
140
 
 
141
  25%|██▌ | 56/220 [00:12<00:11, 14.10it/s]
142
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
143
 
 
144
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
145
 
 
146
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
147
 
 
148
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
149
 
 
150
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
151
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
152
 
 
153
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
154
 
 
155
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
156
 
 
157
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
158
 
 
159
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
160
  31%|███ | 68/220 [00:12<00:09, 16.82it/s]
161
 
 
162
  31%|███ | 68/220 [00:12<00:09, 16.82it/s]
163
 
 
164
  31%|███ | 68/220 [00:13<00:09, 16.82it/s]
165
 
 
166
  31%|███ | 68/220 [00:13<00:09, 16.82it/s]
167
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
168
 
 
169
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
170
 
 
171
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
172
 
 
173
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
174
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
175
 
 
176
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
177
 
 
178
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
179
 
 
180
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
181
 
 
182
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
183
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
184
 
 
185
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
186
 
 
187
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
188
 
 
189
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
190
 
 
191
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
192
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
193
 
 
194
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
195
 
 
196
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
197
 
 
198
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
199
 
 
200
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
201
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
202
 
 
203
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
204
 
 
205
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
206
 
 
207
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
208
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
209
 
 
210
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
211
 
 
212
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
213
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
214
 
 
215
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
216
 
 
217
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
218
 
 
219
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
220
 
 
221
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
222
  43%|████▎ | 95/220 [00:14<00:07, 15.78it/s]
223
 
 
224
  43%|████▎ | 95/220 [00:14<00:07, 15.78it/s]
225
 
 
226
  43%|████▎ | 95/220 [00:15<00:07, 15.78it/s]
227
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
228
 
 
229
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
230
 
 
231
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
232
 
 
233
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
234
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
235
 
 
236
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
237
 
 
238
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
239
 
 
240
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
241
 
 
242
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
243
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
244
 
 
245
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
246
 
 
247
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
248
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
249
 
 
250
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
251
 
 
252
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
253
 
 
254
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
255
  50%|████▉ | 109/220 [00:15<00:08, 12.63it/s]
256
 
 
257
  50%|████▉ | 109/220 [00:15<00:08, 12.63it/s]
258
 
 
259
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
260
 
 
261
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
262
 
 
263
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
264
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
265
 
 
266
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
267
 
 
268
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
269
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
270
 
 
271
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
272
 
 
273
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
274
 
 
275
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
276
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
277
 
 
278
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
279
 
 
280
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
281
 
 
282
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
283
 
 
284
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
285
  55%|█████▌ | 122/220 [00:16<00:06, 15.23it/s]
286
 
 
287
  55%|█████▌ | 122/220 [00:17<00:06, 15.23it/s]
288
 
 
289
  55%|█████▌ | 122/220 [00:17<00:06, 15.23it/s]
290
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
291
 
 
292
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
293
 
 
294
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
295
 
 
296
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
297
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
298
 
 
299
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
300
 
 
301
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
302
 
 
303
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
304
 
 
305
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
306
  60%|█████▉ | 131/220 [00:17<00:05, 15.18it/s]
307
 
 
308
  60%|█████▉ | 131/220 [00:17<00:05, 15.18it/s]
309
 
 
310
  60%|█████▉ | 131/220 [00:18<00:05, 15.18it/s]
311
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
312
 
 
313
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
314
 
 
315
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
316
 
 
317
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
318
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
319
 
 
320
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
321
 
 
322
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
323
 
 
324
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
325
 
 
326
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
327
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
328
 
 
329
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
330
 
 
331
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
332
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
333
 
 
334
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
335
 
 
336
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
337
 
 
338
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
339
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
340
 
 
341
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
342
 
 
343
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
344
 
 
345
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
346
 
 
347
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
348
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
349
 
 
350
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
351
 
 
352
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
353
 
 
354
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
355
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
356
 
 
357
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
358
 
 
359
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
360
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
361
 
 
362
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
363
 
 
364
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
365
 
 
366
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
367
 
 
368
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
369
  72%|███████▏ | 158/220 [00:19<00:04, 15.25it/s]
370
 
 
371
  72%|███████▏ | 158/220 [00:19<00:04, 15.25it/s]
372
 
 
373
  72%|███████▏ | 158/220 [00:20<00:04, 15.25it/s]
374
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
375
 
 
376
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
377
 
 
378
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
379
 
 
380
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
381
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
382
 
 
383
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
384
 
 
385
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
386
 
 
387
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
388
 
 
389
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
390
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
391
 
 
392
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
393
 
 
394
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
395
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
396
 
 
397
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
398
 
 
399
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
400
 
 
401
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
402
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
403
 
 
404
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
405
 
 
406
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
407
 
 
408
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
409
 
 
410
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
411
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
412
 
 
413
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
414
 
 
415
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
416
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
417
 
 
418
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
419
 
 
420
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
421
 
 
422
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
423
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
424
 
 
425
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
426
 
 
427
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
428
 
 
429
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
430
 
 
431
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
432
  84%|████████▍ | 185/220 [00:21<00:02, 15.33it/s]
433
 
 
434
  84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
435
 
 
436
  84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
437
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
438
 
 
439
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
440
 
 
441
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
442
 
 
443
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
444
 
 
445
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
446
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
447
 
 
448
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
449
 
 
450
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
451
 
 
452
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
453
 
 
454
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
455
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
456
 
 
457
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
458
 
 
459
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
460
 
 
461
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
462
 
 
463
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
464
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
465
 
 
466
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
467
 
 
468
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
469
 
 
470
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
471
 
 
472
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
473
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
474
 
 
475
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
476
 
 
477
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
478
 
 
479
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
480
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
481
 
 
482
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
483
 
 
484
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
485
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
486
 
 
487
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
488
 
 
489
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
490
 
 
491
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
492
 
 
493
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
494
  96%|█████████▋| 212/220 [00:23<00:00, 15.54it/s]
495
 
 
496
  96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
497
 
 
498
  96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
499
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
500
 
 
501
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
502
 
 
503
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
504
 
 
505
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
506
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
507
 
 
508
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
509
 
 
510
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
511
 
 
512
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
 
 
 
 
 
 
 
 
 
 
1
+ /usr/bin/python3 -m mlc_llm gen_config dist/models/stablelm-2-zephyr-1_6b --quantization q0f16 --conv-template stablelm-2 --output /tmp/tmphm3edhbu --context-window-size 4096
2
+ [2024-05-24 17:02:51] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
3
+ [2024-05-24 17:02:51] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
4
+ [2024-05-24 17:02:51] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
5
+ [2024-05-24 17:02:51] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
6
+ [2024-05-24 17:02:51] INFO config.py:106: Overriding context_window_size from 4096 to 4096
7
+ [2024-05-24 17:02:51] INFO config.py:106: Overriding max_batch_size from 1 to 80
8
+ [2024-05-24 17:02:51] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 100257
9
+ [2024-05-24 17:02:51] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: 100257
10
+ [2024-05-24 17:02:51] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.model
11
+ [2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.json. Copying to /tmp/tmphm3edhbu/tokenizer.json
12
+ [2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/vocab.json. Copying to /tmp/tmphm3edhbu/vocab.json
13
+ [2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/merges.txt. Copying to /tmp/tmphm3edhbu/merges.txt
14
+ [2024-05-24 17:02:51] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/added_tokens.json
15
+ [2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer_config.json. Copying to /tmp/tmphm3edhbu/tokenizer_config.json
16
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting pad_token_id: 0
17
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting temperature: 0.7
18
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
19
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
20
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
21
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting top_p: 0.95
22
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
23
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
24
+ [2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-05-24 17:02:51] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmphm3edhbu/mlc-chat-config.json
26
+ /usr/bin/python3 -m mlc_llm convert_weight dist/models/stablelm-2-zephyr-1_6b --quantization q0f16 --source-format auto --output /tmp/tmphm3edhbu
27
+ [2024-05-24 17:02:52] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
28
+ [2024-05-24 17:02:54] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-05-24 17:02:55] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-05-24 17:02:56] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-05-24 17:02:57] INFO auto_device.py:88: Not found device: vulkan:0
32
+ [2024-05-24 17:02:58] INFO auto_device.py:88: Not found device: opencl:0
33
+ [2024-05-24 17:02:58] INFO auto_device.py:35: Using device: cuda:0
34
+ [2024-05-24 17:02:58] INFO auto_weight.py:70: Finding weights in: dist/models/stablelm-2-zephyr-1_6b
35
+ [2024-05-24 17:02:58] INFO auto_weight.py:136: Not found Huggingface PyTorch
36
+ [2024-05-24 17:02:58] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
37
+ [2024-05-24 17:02:58] INFO auto_weight.py:106: Using source weight configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json. Use `--source` to override.
38
+ [2024-05-24 17:02:58] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
39
+ [2024-05-24 17:02:58] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
40
+ [2024-05-24 17:02:58] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
41
+ [2024-05-24 17:02:58] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
42
+ Weight conversion with arguments:
43
+ --config dist/models/stablelm-2-zephyr-1_6b/config.json
44
+ --quantization NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
45
+ --model-type stablelm
46
+ --device cuda:0
47
+ --source dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
48
+ --source-format huggingface-safetensor
49
+ --output /tmp/tmphm3edhbu
50
+ Start storing to cache /tmp/tmphm3edhbu
51
+
52
  0%| | 0/220 [00:00<?, ?it/s]
53
 
54
+
55
  0%| | 0/220 [00:00<?, ?it/s]
56
 
57
+
58
  0%| | 0/220 [00:03<?, ?it/s]
59
  0%| | 1/220 [00:04<17:07, 4.69s/it]
60
 
61
+
62
  0%| | 1/220 [00:06<17:07, 4.69s/it]
63
  1%| | 2/220 [00:07<13:33, 3.73s/it]
64
 
65
+
66
  1%| | 2/220 [00:07<13:33, 3.73s/it]
67
 
68
+
69
  1%| | 2/220 [00:07<13:33, 3.73s/it]
70
 
71
+
72
  1%| | 2/220 [00:07<13:33, 3.73s/it]
73
 
74
+
75
  1%| | 2/220 [00:08<13:33, 3.73s/it]
76
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
77
 
78
+
79
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
80
 
81
+
82
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
83
 
84
+
85
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
86
 
87
+
88
  3%|▎ | 6/220 [00:08<03:20, 1.07it/s]
89
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
90
 
91
+
92
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
93
 
94
+
95
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
96
 
97
+
98
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
99
 
100
+
101
  5%|▍ | 10/220 [00:08<01:40, 2.09it/s]
102
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
103
 
104
+
105
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
106
 
107
+
108
  6%|▋ | 14/220 [00:08<00:59, 3.47it/s]
109
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
110
 
111
+
112
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
113
 
114
+
115
  7%|▋ | 16/220 [00:08<00:55, 3.68it/s]
116
 
117
+
118
  7%|▋ | 16/220 [00:09<00:55, 3.68it/s]
119
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
120
 
121
+
122
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
123
 
124
+
125
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
126
 
127
+
128
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
129
 
130
+
131
  9%|▊ | 19/220 [00:09<00:39, 5.12it/s]
132
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
133
 
134
+
135
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
136
 
137
+
138
  10%|█ | 23/220 [00:09<00:26, 7.38it/s]
139
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
140
 
141
+
142
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
143
 
144
+
145
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
146
 
147
+
148
  11%|█▏ | 25/220 [00:09<00:29, 6.56it/s]
149
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
150
 
151
+
152
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
153
 
154
+
155
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
156
 
157
+
158
  13%|█▎ | 28/220 [00:09<00:22, 8.46it/s]
159
 
160
+
161
  13%|█▎ | 28/220 [00:10<00:22, 8.46it/s]
162
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
163
 
164
+
165
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
166
 
167
+
168
  15%|█▍ | 32/220 [00:10<00:19, 9.72it/s]
169
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
170
 
171
+
172
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
173
 
174
+
175
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
176
 
177
+
178
  15%|█▌ | 34/220 [00:10<00:23, 7.88it/s]
179
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
180
 
181
+
182
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
183
 
184
+
185
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
186
 
187
+
188
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
189
 
190
+
191
  17%|█▋ | 37/220 [00:10<00:18, 9.88it/s]
192
  19%|█▊ | 41/220 [00:10<00:14, 12.77it/s]
193
 
194
+
195
  19%|█▊ | 41/220 [00:11<00:14, 12.77it/s]
196
 
197
+
198
  19%|█▊ | 41/220 [00:11<00:14, 12.77it/s]
199
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
200
 
201
+
202
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
203
 
204
+
205
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
206
 
207
+
208
  20%|█▉ | 43/220 [00:11<00:17, 10.03it/s]
209
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
210
 
211
+
212
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
213
 
214
+
215
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
216
 
217
+
218
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
219
 
220
+
221
  21%|██ | 46/220 [00:11<00:13, 12.64it/s]
222
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
223
 
224
+
225
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
226
 
227
+
228
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
229
 
230
+
231
  23%|██▎ | 50/220 [00:11<00:10, 16.44it/s]
232
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
233
 
234
+
235
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
236
 
237
+
238
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
239
 
240
+
241
  24%|██▍ | 53/220 [00:11<00:12, 13.00it/s]
242
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
243
 
244
+
245
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
246
 
247
+
248
  25%|██▌ | 56/220 [00:11<00:11, 14.10it/s]
249
 
250
+
251
  25%|██▌ | 56/220 [00:12<00:11, 14.10it/s]
252
 
253
+
254
  25%|██▌ | 56/220 [00:12<00:11, 14.10it/s]
255
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
256
 
257
+
258
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
259
 
260
+
261
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
262
 
263
+
264
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
265
 
266
+
267
  27%|██▋ | 60/220 [00:12<00:13, 11.51it/s]
268
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
269
 
270
+
271
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
272
 
273
+
274
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
275
 
276
+
277
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
278
 
279
+
280
  29%|██▉ | 64/220 [00:12<00:10, 14.48it/s]
281
  31%|███ | 68/220 [00:12<00:09, 16.82it/s]
282
 
283
+
284
  31%|███ | 68/220 [00:12<00:09, 16.82it/s]
285
 
286
+
287
  31%|███ | 68/220 [00:13<00:09, 16.82it/s]
288
 
289
+
290
  31%|███ | 68/220 [00:13<00:09, 16.82it/s]
291
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
292
 
293
+
294
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
295
 
296
+
297
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
298
 
299
+
300
  32%|███▏ | 71/220 [00:13<00:11, 13.30it/s]
301
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
302
 
303
+
304
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
305
 
306
+
307
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
308
 
309
+
310
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
311
 
312
+
313
  34%|███▎ | 74/220 [00:13<00:10, 14.27it/s]
314
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
315
 
316
+
317
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
318
 
319
+
320
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
321
 
322
+
323
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
324
 
325
+
326
  35%|███▌ | 78/220 [00:13<00:11, 11.86it/s]
327
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
328
 
329
+
330
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
331
 
332
+
333
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
334
 
335
+
336
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
337
 
338
+
339
  37%|███▋ | 82/220 [00:13<00:09, 14.75it/s]
340
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
341
 
342
+
343
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
344
 
345
+
346
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
347
 
348
+
349
  39%|███▉ | 86/220 [00:14<00:07, 16.99it/s]
350
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
351
 
352
+
353
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
354
 
355
+
356
  40%|████ | 89/220 [00:14<00:10, 12.61it/s]
357
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
358
 
359
+
360
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
361
 
362
+
363
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
364
 
365
+
366
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
367
 
368
+
369
  41%|████▏ | 91/220 [00:14<00:09, 13.06it/s]
370
  43%|████▎ | 95/220 [00:14<00:07, 15.78it/s]
371
 
372
+
373
  43%|████▎ | 95/220 [00:14<00:07, 15.78it/s]
374
 
375
+
376
  43%|████▎ | 95/220 [00:15<00:07, 15.78it/s]
377
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
378
 
379
+
380
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
381
 
382
+
383
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
384
 
385
+
386
  44%|████▍ | 97/220 [00:15<00:11, 10.74it/s]
387
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
388
 
389
+
390
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
391
 
392
+
393
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
394
 
395
+
396
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
397
 
398
+
399
  45%|████▌ | 100/220 [00:15<00:09, 12.85it/s]
400
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
401
 
402
+
403
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
404
 
405
+
406
  47%|████▋ | 104/220 [00:15<00:07, 15.71it/s]
407
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
408
 
409
+
410
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
411
 
412
+
413
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
414
 
415
+
416
  48%|████▊ | 106/220 [00:15<00:10, 10.56it/s]
417
  50%|████▉ | 109/220 [00:15<00:08, 12.63it/s]
418
 
419
+
420
  50%|████▉ | 109/220 [00:15<00:08, 12.63it/s]
421
 
422
+
423
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
424
 
425
+
426
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
427
 
428
+
429
  50%|████▉ | 109/220 [00:16<00:08, 12.63it/s]
430
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
431
 
432
+
433
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
434
 
435
+
436
  51%|█████▏ | 113/220 [00:16<00:06, 15.44it/s]
437
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
438
 
439
+
440
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
441
 
442
+
443
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
444
 
445
+
446
  52%|█████▏ | 115/220 [00:16<00:10, 10.34it/s]
447
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
448
 
449
+
450
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
451
 
452
+
453
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
454
 
455
+
456
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
457
 
458
+
459
  54%|█████▎ | 118/220 [00:16<00:08, 12.43it/s]
460
  55%|█████▌ | 122/220 [00:16<00:06, 15.23it/s]
461
 
462
+
463
  55%|█████▌ | 122/220 [00:17<00:06, 15.23it/s]
464
 
465
+
466
  55%|█████▌ | 122/220 [00:17<00:06, 15.23it/s]
467
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
468
 
469
+
470
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
471
 
472
+
473
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
474
 
475
+
476
  56%|█████▋ | 124/220 [00:17<00:09, 10.31it/s]
477
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
478
 
479
+
480
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
481
 
482
+
483
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
484
 
485
+
486
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
487
 
488
+
489
  58%|█████▊ | 127/220 [00:17<00:07, 12.39it/s]
490
  60%|█████▉ | 131/220 [00:17<00:05, 15.18it/s]
491
 
492
+
493
  60%|█████▉ | 131/220 [00:17<00:05, 15.18it/s]
494
 
495
+
496
  60%|█████▉ | 131/220 [00:18<00:05, 15.18it/s]
497
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
498
 
499
+
500
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
501
 
502
+
503
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
504
 
505
+
506
  60%|██████ | 133/220 [00:18<00:08, 10.29it/s]
507
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
508
 
509
+
510
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
511
 
512
+
513
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
514
 
515
+
516
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
517
 
518
+
519
  62%|██████▏ | 136/220 [00:18<00:06, 12.42it/s]
520
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
521
 
522
+
523
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
524
 
525
+
526
  64%|██████▎ | 140/220 [00:18<00:05, 15.30it/s]
527
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
528
 
529
+
530
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
531
 
532
+
533
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
534
 
535
+
536
  65%|██████▍ | 142/220 [00:18<00:07, 10.42it/s]
537
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
538
 
539
+
540
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
541
 
542
+
543
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
544
 
545
+
546
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
547
 
548
+
549
  66%|██████▌ | 145/220 [00:18<00:05, 12.72it/s]
550
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
551
 
552
+
553
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
554
 
555
+
556
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
557
 
558
+
559
  68%|██████▊ | 149/220 [00:19<00:04, 15.53it/s]
560
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
561
 
562
+
563
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
564
 
565
+
566
  69%|██████▉ | 152/220 [00:19<00:05, 11.57it/s]
567
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
568
 
569
+
570
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
571
 
572
+
573
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
574
 
575
+
576
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
577
 
578
+
579
  70%|███████ | 154/220 [00:19<00:05, 12.24it/s]
580
  72%|███████▏ | 158/220 [00:19<00:04, 15.25it/s]
581
 
582
+
583
  72%|███████▏ | 158/220 [00:19<00:04, 15.25it/s]
584
 
585
+
586
  72%|███████▏ | 158/220 [00:20<00:04, 15.25it/s]
587
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
588
 
589
+
590
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
591
 
592
+
593
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
594
 
595
+
596
  73%|███████▎ | 160/220 [00:20<00:05, 10.43it/s]
597
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
598
 
599
+
600
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
601
 
602
+
603
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
604
 
605
+
606
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
607
 
608
+
609
  74%|███████▍ | 163/220 [00:20<00:04, 12.57it/s]
610
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
611
 
612
+
613
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
614
 
615
+
616
  76%|███████▌ | 167/220 [00:20<00:03, 15.44it/s]
617
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
618
 
619
+
620
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
621
 
622
+
623
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
624
 
625
+
626
  77%|███████▋ | 169/220 [00:20<00:04, 10.40it/s]
627
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
628
 
629
+
630
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
631
 
632
+
633
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
634
 
635
+
636
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
637
 
638
+
639
  78%|███████▊ | 172/220 [00:21<00:03, 12.53it/s]
640
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
641
 
642
+
643
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
644
 
645
+
646
  80%|████████ | 176/220 [00:21<00:02, 15.31it/s]
647
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
648
 
649
+
650
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
651
 
652
+
653
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
654
 
655
+
656
  81%|████████ | 178/220 [00:21<00:04, 10.26it/s]
657
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
658
 
659
+
660
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
661
 
662
+
663
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
664
 
665
+
666
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
667
 
668
+
669
  82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
670
  84%|████████▍ | 185/220 [00:21<00:02, 15.33it/s]
671
 
672
+
673
  84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
674
 
675
+
676
  84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
677
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
678
 
679
+
680
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
681
 
682
+
683
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
684
 
685
+
686
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
687
 
688
+
689
  85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
690
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
691
 
692
+
693
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
694
 
695
+
696
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
697
 
698
+
699
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
700
 
701
+
702
  87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
703
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
704
 
705
+
706
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
707
 
708
+
709
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
710
 
711
+
712
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
713
 
714
+
715
  89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
716
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
717
 
718
+
719
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
720
 
721
+
722
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
723
 
724
+
725
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
726
 
727
+
728
  90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
729
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
730
 
731
+
732
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
733
 
734
+
735
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
736
 
737
+
738
  92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
739
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
740
 
741
+
742
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
743
 
744
+
745
  94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
746
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
747
 
748
+
749
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
750
 
751
+
752
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
753
 
754
+
755
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
756
 
757
+
758
  95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
759
  96%|█████████▋| 212/220 [00:23<00:00, 15.54it/s]
760
 
761
+
762
  96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
763
 
764
+
765
  96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
766
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
767
 
768
+
769
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
770
 
771
+
772
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
773
 
774
+
775
  97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
776
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
777
 
778
+
779
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
780
 
781
+
782
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
783
 
784
+
785
  99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
786
+ [2024-05-24 17:03:24] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/stablelm-2-zephyr-1_6b/model.safetensors
787
+ [2024-05-24 17:03:24] INFO stats.py:76: Time usage: HF loading: 1.644 sec; Pre-quantization mapping: 11.830 sec; Quantization: 0.000 sec
788
+ [2024-05-24 17:03:24] INFO stats.py:90: RAM usage: Peak RAM: 3.063 GB. Total bytes loaded from disk: 3.063 GB
789
+ [2024-05-24 17:03:24] INFO convert_weight.py:155: Parameter size after quantization: 3.063 GB
790
+ [2024-05-24 17:03:24] INFO convert_weight.py:160: Total parameters: 1,644,515,328
791
+ [2024-05-24 17:03:24] INFO convert_weight.py:161: Bits per parameter: 16.000
792
+ [2024-05-24 17:03:24] INFO convert_weight.py:166: Saved to directory: /tmp/tmphm3edhbu
793
+
794
+ All finished, 75 total shards committed, record saved to /tmp/tmphm3edhbu/ndarray-cache.json
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
mlc-chat-config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "stablelm",
3
+ "quantization": "q0f16",
4
+ "model_config": {
5
+ "vocab_size": 100352,
6
+ "hidden_size": 2048,
7
+ "num_hidden_layers": 24,
8
+ "num_attention_heads": 32,
9
+ "num_key_value_heads": 32,
10
+ "layer_norm_eps": 1e-05,
11
+ "partial_rotary_factor": 0.25,
12
+ "rope_theta": 10000,
13
+ "intermediate_size": 5632,
14
+ "use_qkv_bias": true,
15
+ "head_dim": 64,
16
+ "context_window_size": 4096,
17
+ "prefill_chunk_size": 2048,
18
+ "tensor_parallel_shards": 1,
19
+ "max_batch_size": 80
20
+ },
21
+ "vocab_size": 100352,
22
+ "context_window_size": 4096,
23
+ "sliding_window_size": -1,
24
+ "prefill_chunk_size": 2048,
25
+ "attention_sink_size": -1,
26
+ "tensor_parallel_shards": 1,
27
+ "mean_gen_len": 128,
28
+ "max_gen_len": 512,
29
+ "shift_fill_factor": 0.3,
30
+ "temperature": 0.7,
31
+ "presence_penalty": 0.0,
32
+ "frequency_penalty": 0.0,
33
+ "repetition_penalty": 1.0,
34
+ "top_p": 0.95,
35
+ "conv_template": {
36
+ "name": "stablelm-2",
37
+ "system_template": "{system_message}",
38
+ "system_message": "",
39
+ "add_role_after_system_message": true,
40
+ "roles": {
41
+ "user": "<|user|>",
42
+ "assistant": "<|assistant|>"
43
+ },
44
+ "role_templates": {
45
+ "user": "{user_message}",
46
+ "assistant": "{assistant_message}",
47
+ "tool": "{tool_message}"
48
+ },
49
+ "messages": [],
50
+ "seps": [
51
+ "<|endoftext|>",
52
+ "<|endoftext|>"
53
+ ],
54
+ "role_content_sep": "\n",
55
+ "role_empty_sep": "\n",
56
+ "stop_str": [
57
+ "<|endoftext|>"
58
+ ],
59
+ "stop_token_ids": [
60
+ 100257
61
+ ],
62
+ "function_string": "",
63
+ "use_function_calling": false
64
+ },
65
+ "pad_token_id": 0,
66
+ "bos_token_id": 100257,
67
+ "eos_token_id": 100257,
68
+ "tokenizer_files": [
69
+ "tokenizer.json",
70
+ "vocab.json",
71
+ "merges.txt",
72
+ "tokenizer_config.json"
73
+ ],
74
+ "token_table_postproc_method": "byte_level",
75
+ "version": "0.1.0"
76
+ }
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 sha256:8e278ca255fea036b8fe4479cd46b5911c070bbd5609de08177335f2367a1b81
3
+ size 411041792
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53f318f494937404207e49eaf77a0451710aff6bc9e0e3a60affa6767339dde
3
+ size 411041792
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d6928a8167190e3bc7658ed34a8c6a2dad7ff7a9dce20de8c1e3478cb6cc47
3
+ size 31485952
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40841b4574ce5ac98f5355a852f5b2369ce9c0bf2aa96a66bf594e8927173a8
3
+ size 46137344
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5b20cf7fc974667cf8a62a933f32b266f6961f8428c1fac880a3660bd8bc7f
3
+ size 25165824
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4eac1b1884e05b50237ef9cc52fe44fba673bca242b1e840d1fdcb66cc36ecd
3
+ size 31485952
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172cd02c3fc607a7651600bddf3449c7215ae405875b42500cd1a6f4cda027e2
3
+ size 46137344
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b67234206a33460d7f0974fd95f7a276fb28c2b8384049921f4ae1ffa524302
3
+ size 25165824
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3d1027775a621fa7ca5a5e42084bd98be9593078c9a10aeb2c35eba309b5a
3
+ size 31485952
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d939111cc3eaadbb6545e16fac97bb156d26f47ae553ccf9a32637bdd041a2
3
+ size 46137344
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4559d14dba10959dc81e68ff9f45b6c1a5656d9fda8b761170fcdfe7c4ff6c
3
+ size 25165824
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4d47762a3dd87c8fa5498157651b8d6b68857871b4eb4b7b2ca896080a1ca7
3
+ size 31485952
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fb1519844a886bd1c01f7842950ffa658eca336bcb7cbebe91ae9773594cd9
3
+ size 46137344
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5709d28c15f4f4716411f6eaa11897ffef1c213a2c42f0b10a1ce01a7a29bba
3
+ size 46137344
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cf31b4cc1f16602e3311f1b0a0c080dc414514a3e6d671eea4afcad7624e00
3
+ size 25165824
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab8adb85d7fa188447bd96a34e0aa69ca3f6c0d288a5c9115e1768f64c91b55
3
+ size 31485952
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc40dc3e96a2f0baf3035e0f3c9d116ff864e3e1c41af4811a1feee0df32dfd
3
+ size 46137344
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07789840a4879e0e08a8439887f7abca8fc26b7f31d378405b3b73ef1d13b79
3
+ size 25165824
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84d56edd5c71874e6a68731d08603c46a792c82e3d0efcadef8b86e6d77f254
3
+ size 31485952
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9543e1fb1f0c5436f97d01c1776569cdaf5877c61ee21ad9316d329942441ec7
3
+ size 46137344
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f735a0174aa08413f223ae6f5ae9aec55304eb491dce670d460c91927ff5a
3
+ size 25165824
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d653974f363e3cbb195202e72e67792be2d2c098a8e439678cc1907464b0e4
3
+ size 31485952
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bff6dfede3149f1463495d37fa42a7f04fa0d346f07e154c294f162170199cc
3
+ size 46137344
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51dd5af71d20a9f5ecd76b3c6179457e46f6ac82c10fd9c2f7674ee5394746b4
3
+ size 25165824
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071a8a0ec8a83576815859480ec1c1e99adb43bf92139d8b3919e72c16dd8607
3
+ size 25165824
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d9661db043e742c122c5d5782184cfcea940129ec48b2dceb10f8e3059f34a
3
+ size 31485952
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ab17d974b412f663fa14bc6b6e3a350f9ea0f3a82030738a50ff3fa35a8615
3
+ size 46137344
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f857f0084450e731c8f0fadd56ad134f535fe677a02871464b7b5db5c2b93f8
3
+ size 25165824
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73586342ea5d7ffac0f5658ac7a8046115203db58a51607a71d2c2fdf48b9726
3
+ size 31485952
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d950f4e970899e0aecbdcd7892d3b7e9520dde6a4b4393bf93b8524f5de31cf7
3
+ size 46137344
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ae6879ff12fd3f32ce80e575ca0bc96a83bd8f282f6f2bf7da82d5ec2b082a
3
+ size 25165824
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d85f004c47cd40028df7d4a591dbec7d3c6411f66b7e71168f0e870b5ad174
3
+ size 31485952
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e278cd81c6f4143853787cf884a625bb428135210574fca96dd84ce96cc87384
3
+ size 46137344
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201de6ef0e9c938416942e8ccc3f40c9f09134d7383189bd0fefe27cd97a7af0
3
+ size 25165824
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06188e5d362db53bbe71e596da0335dd16823b1f044edae31f04108d07b69622
3
+ size 23068672
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6414e06bdd440c7e8204085cad47a5e17ce1146b57b06690ecb13b92c7f997bf
3
+ size 31485952
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fc682dc7c4ded464df722e79b5bd126b2857318ecf44341325f1a72688a605
3
+ size 46137344
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1ec336b237d2736b5256b04b42f9c4029206a59a79944000140f6decbeed37
3
+ size 25165824
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb8645ebdd399b556e141274be9ec174dde25a0de2763f6da16ea852ed0ccab
3
+ size 31485952
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e4f2356b1bba2e9b6612a929a94af1e7e59faf68986794c60adf6bab2e83c0
3
+ size 46137344
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1bc1dc651be91bccc554f5c490e6ec86872f65f504079d5695db107ef93c10
3
+ size 25165824
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78080109e5b105aa1e80ea5cd21c821d087d4358948d6455e09844eb78a970ca
3
+ size 31485952
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c39bb9d0259a0491665f2365fd879080aea9ca1c481527a41de5eeee1538be9
3
+ size 46137344
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ecf3bbc48c5d9301fe7f69a01ce2eef544ad1b9f4c9f3ef9825ff1ae95b6ac
3
+ size 25165824
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e36e308e316ea1ea6e0e6dc9d5baa9d516153f96b5ba4d89b736b3763482b5f
3
+ size 31485952
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c2f7a1d8428fb07f7ae0289bdaec8a04d8480e694767179cebb3752f40e237
3
+ size 46137344