Hugging Face's logo

mlc-ai
/
Llama-3-8B-Instruct-q0f16-MLC

MLC-LLM
web-llm
Model card Files Community
riczhou commited on
Commit
dc37d69
·
verified ·
1 Parent(s): d2c2e07

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 +265 -0
  2. mlc-chat-config.json +83 -0
  3. ndarray-cache.json +0 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_10.bin +3 -0
  7. params_shard_100.bin +3 -0
  8. params_shard_101.bin +3 -0
  9. params_shard_102.bin +3 -0
  10. params_shard_103.bin +3 -0
  11. params_shard_104.bin +3 -0
  12. params_shard_105.bin +3 -0
  13. params_shard_106.bin +3 -0
  14. params_shard_107.bin +3 -0
  15. params_shard_108.bin +3 -0
  16. params_shard_109.bin +3 -0
  17. params_shard_11.bin +3 -0
  18. params_shard_110.bin +3 -0
  19. params_shard_111.bin +3 -0
  20. params_shard_112.bin +3 -0
  21. params_shard_113.bin +3 -0
  22. params_shard_114.bin +3 -0
  23. params_shard_115.bin +3 -0
  24. params_shard_116.bin +3 -0
  25. params_shard_117.bin +3 -0
  26. params_shard_118.bin +3 -0
  27. params_shard_119.bin +3 -0
  28. params_shard_12.bin +3 -0
  29. params_shard_120.bin +3 -0
  30. params_shard_121.bin +3 -0
  31. params_shard_122.bin +3 -0
  32. params_shard_123.bin +3 -0
  33. params_shard_124.bin +3 -0
  34. params_shard_125.bin +3 -0
  35. params_shard_126.bin +3 -0
  36. params_shard_127.bin +3 -0
  37. params_shard_128.bin +3 -0
  38. params_shard_129.bin +3 -0
  39. params_shard_13.bin +3 -0
  40. params_shard_130.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
logs.txt ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/195 [00:00<?, ?it/s]
1
 
 
2
  0%| | 0/195 [00:00<?, ?it/s]
3
 
 
4
  0%| | 0/195 [00:03<?, ?it/s]
5
  1%| | 1/195 [00:06<20:46, 6.43s/it]
6
 
 
7
  1%| | 1/195 [00:06<20:46, 6.43s/it]
8
  1%| | 2/195 [00:06<08:44, 2.72s/it]
9
 
 
10
  1%| | 2/195 [00:06<08:44, 2.72s/it]
11
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
12
 
 
13
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
14
 
 
15
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
16
 
 
17
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
18
 
 
19
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
20
 
 
21
  2%|▏ | 3/195 [00:13<05:29, 1.72s/it]
22
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
23
 
 
24
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
25
 
 
26
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
27
  4%|▍ | 8/195 [00:16<05:15, 1.69s/it]
28
 
 
29
  4%|▍ | 8/195 [00:17<05:15, 1.69s/it]
30
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
31
 
 
32
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
33
 
 
34
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
35
  6%|▌ | 11/195 [00:18<03:06, 1.01s/it]
36
 
 
37
  6%|▌ | 11/195 [00:18<03:06, 1.01s/it]
38
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
39
 
 
40
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
41
 
 
42
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
43
  7%|▋ | 14/195 [00:18<01:51, 1.63it/s]
44
 
 
45
  7%|▋ | 14/195 [00:19<01:51, 1.63it/s]
46
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
47
 
 
48
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
49
 
 
50
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
51
  9%|▊ | 17/195 [00:20<01:27, 2.02it/s]
52
 
 
53
  9%|▊ | 17/195 [00:20<01:27, 2.02it/s]
54
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
55
 
 
56
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
57
 
 
58
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
59
  10%|█ | 20/195 [00:20<01:03, 2.77it/s]
60
 
 
61
  10%|█ | 20/195 [00:21<01:03, 2.77it/s]
62
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
63
 
 
64
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
65
 
 
66
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
67
  12%|█▏ | 23/195 [00:22<01:03, 2.70it/s]
68
 
 
69
  12%|█▏ | 23/195 [00:22<01:03, 2.70it/s]
70
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
71
 
 
72
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
73
 
 
74
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
75
  13%|█▎ | 26/195 [00:22<00:50, 3.33it/s]
76
 
 
77
  13%|█▎ | 26/195 [00:23<00:50, 3.33it/s]
78
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
79
 
 
80
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
81
 
 
82
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
83
  15%|���▍ | 29/195 [00:24<00:56, 2.92it/s]
84
 
 
85
  15%|█▍ | 29/195 [00:24<00:56, 2.92it/s]
86
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
87
 
 
88
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
89
 
 
90
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
91
  16%|█▋ | 32/195 [00:24<00:46, 3.49it/s]
92
 
 
93
  16%|█▋ | 32/195 [00:25<00:46, 3.49it/s]
94
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
95
 
 
96
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
97
 
 
98
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
99
  18%|█▊ | 35/195 [00:26<00:53, 2.99it/s]
100
 
 
101
  18%|█▊ | 35/195 [00:26<00:53, 2.99it/s]
102
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
103
 
 
104
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
105
 
 
106
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
107
  19%|█▉ | 38/195 [00:26<00:44, 3.51it/s]
108
 
 
109
  19%|█▉ | 38/195 [00:27<00:44, 3.51it/s]
110
  20%|██ | 39/195 [00:27<01:12, 2.15it/s]
111
 
 
112
  20%|██ | 39/195 [00:27<01:12, 2.15it/s]
113
 
 
114
  20%|██ | 39/195 [00:28<01:12, 2.15it/s]
115
  21%|██ | 41/195 [00:28<00:52, 2.94it/s]
116
 
 
117
  21%|██ | 41/195 [00:28<00:52, 2.94it/s]
118
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
119
 
 
120
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
121
 
 
122
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
123
  23%|██▎ | 44/195 [00:28<00:42, 3.52it/s]
124
 
 
125
  23%|██▎ | 44/195 [00:29<00:42, 3.52it/s]
126
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
127
 
 
128
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
129
 
 
130
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
131
  24%|██▍ | 47/195 [00:30<00:49, 2.99it/s]
132
 
 
133
  24%|██▍ | 47/195 [00:30<00:49, 2.99it/s]
134
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
135
 
 
136
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
137
 
 
138
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
139
  26%|██▌ | 50/195 [00:30<00:41, 3.46it/s]
140
 
 
141
  26%|██▌ | 50/195 [00:31<00:41, 3.46it/s]
142
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
143
 
 
144
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
145
 
 
146
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
147
  27%|██▋ | 53/195 [00:32<00:47, 2.98it/s]
148
 
 
149
  27%|██▋ | 53/195 [00:32<00:47, 2.98it/s]
150
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
151
 
 
152
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
153
 
 
154
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
155
  29%|██▊ | 56/195 [00:33<00:39, 3.53it/s]
156
 
 
157
  29%|██▊ | 56/195 [00:33<00:39, 3.53it/s]
158
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
159
 
 
160
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
161
 
 
162
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
163
  30%|███ | 59/195 [00:34<00:45, 3.02it/s]
164
 
 
165
  30%|███ | 59/195 [00:34<00:45, 3.02it/s]
166
  31%|███ | 60/195 [00:34<00:39, 3.40it/s]
167
 
 
168
  31%|███ | 60/195 [00:34<00:39, 3.40it/s]
169
 
 
170
  31%|███ | 60/195 [00:35<00:39, 3.40it/s]
171
 
 
172
  31%|███ | 60/195 [00:39<00:39, 3.40it/s]
173
  31%|███▏ | 61/195 [00:39<02:58, 1.34s/it]
174
 
 
175
  31%|███▏ | 61/195 [00:39<02:58, 1.34s/it]
176
  32%|███▏ | 62/195 [00:39<02:31, 1.14s/it]
177
 
 
178
  32%|███▏ | 62/195 [00:40<02:31, 1.14s/it]
179
  32%|███▏ | 63/195 [00:40<02:29, 1.13s/it]
180
 
 
181
  32%|███▏ | 63/195 [00:40<02:29, 1.13s/it]
182
 
 
183
  32%|███▏ | 63/195 [00:41<02:29, 1.13s/it]
184
  33%|███▎ | 65/195 [00:41<01:31, 1.42it/s]
185
 
 
186
  33%|███▎ | 65/195 [00:41<01:31, 1.42it/s]
187
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
188
 
 
189
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
190
 
 
191
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
192
  35%|███▍ | 68/195 [00:41<00:56, 2.23it/s]
193
 
 
194
  35%|███▍ | 68/195 [00:42<00:56, 2.23it/s]
195
  35%|███▌ | 69/195 [00:42<01:14, 1.69it/s]
196
 
 
197
  35%|███▌ | 69/195 [00:42<01:14, 1.69it/s]
198
 
 
199
  35%|███▌ | 69/195 [00:43<01:14, 1.69it/s]
200
  36%|███▋ | 71/195 [00:43<00:50, 2.44it/s]
201
 
 
202
  36%|███▋ | 71/195 [00:43<00:50, 2.44it/s]
203
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
204
 
 
205
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
206
 
 
207
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
208
  38%|███▊ | 74/195 [00:43<00:38, 3.16it/s]
209
 
 
210
  38%|███▊ | 74/195 [00:44<00:38, 3.16it/s]
211
  38%|███▊ | 75/195 [00:44<00:57, 2.08it/s]
212
 
 
213
  38%|███▊ | 75/195 [00:44<00:57, 2.08it/s]
214
 
 
215
  38%|███▊ | 75/195 [00:45<00:57, 2.08it/s]
216
  39%|███▉ | 77/195 [00:45<00:40, 2.90it/s]
217
 
 
218
  39%|███▉ | 77/195 [00:45<00:40, 2.90it/s]
219
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
220
 
 
221
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
222
 
 
223
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
224
  41%|████ | 80/195 [00:45<00:32, 3.50it/s]
225
 
 
226
  41%|████ | 80/195 [00:46<00:32, 3.50it/s]
227
  42%|████▏ | 81/195 [00:46<00:51, 2.21it/s]
228
 
 
229
  42%|████▏ | 81/195 [00:46<00:51, 2.21it/s]
230
 
 
231
  42%|████▏ | 81/195 [00:47<00:51, 2.21it/s]
232
  43%|████▎ | 83/195 [00:47<00:36, 3.06it/s]
233
 
 
234
  43%|████▎ | 83/195 [00:47<00:36, 3.06it/s]
235
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
236
 
 
237
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
238
 
 
239
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
240
  44%|████▍ | 86/195 [00:47<00:29, 3.64it/s]
241
 
 
242
  44%|████▍ | 86/195 [00:48<00:29, 3.64it/s]
243
  45%|████▍ | 87/195 [00:48<00:47, 2.26it/s]
244
 
 
245
  45%|████▍ | 87/195 [00:48<00:47, 2.26it/s]
246
 
 
247
  45%|████▍ | 87/195 [00:49<00:47, 2.26it/s]
248
  46%|████▌ | 89/195 [00:49<00:33, 3.12it/s]
249
 
 
250
  46%|████▌ | 89/195 [00:49<00:33, 3.12it/s]
251
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
252
 
 
253
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
254
 
 
255
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
256
  47%|████▋ | 92/195 [00:49<00:27, 3.68it/s]
257
 
 
258
  47%|████▋ | 92/195 [00:50<00:27, 3.68it/s]
259
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
260
 
 
261
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
262
 
 
263
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
264
  49%|████▊ | 95/195 [00:51<00:31, 3.14it/s]
265
 
 
266
  49%|████▊ | 95/195 [00:51<00:31, 3.14it/s]
267
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
268
 
 
269
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
270
 
 
271
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
272
  50%|█████ | 98/195 [00:51<00:26, 3.70it/s]
273
 
 
274
  50%|█████ | 98/195 [00:52<00:26, 3.70it/s]
275
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
276
 
 
277
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
278
 
 
279
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
280
  52%|█████▏ | 101/195 [00:53<00:29, 3.16it/s]
281
 
 
282
  52%|█████▏ | 101/195 [00:53<00:29, 3.16it/s]
283
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
284
 
 
285
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
286
 
 
287
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
288
  53%|█████▎ | 104/195 [00:53<00:24, 3.71it/s]
289
 
 
290
  53%|█████▎ | 104/195 [00:54<00:24, 3.71it/s]
291
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
292
 
 
293
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
294
 
 
295
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
296
  55%|█████▍ | 107/195 [00:54<00:27, 3.15it/s]
297
 
 
298
  55%|█████▍ | 107/195 [00:55<00:27, 3.15it/s]
299
  55%|█████▌ | 108/195 [00:55<00:24, 3.57it/s]
300
 
 
301
  55%|████���▌ | 108/195 [00:55<00:24, 3.57it/s]
302
 
 
303
  55%|█████▌ | 108/195 [00:55<00:24, 3.57it/s]
304
  56%|█████▋ | 110/195 [00:55<00:22, 3.71it/s]
305
 
 
306
  56%|█████▋ | 110/195 [00:56<00:22, 3.71it/s]
307
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
308
 
 
309
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
310
 
 
311
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
312
  58%|█████▊ | 113/195 [00:56<00:26, 3.15it/s]
313
 
 
314
  58%|█████▊ | 113/195 [00:56<00:26, 3.15it/s]
315
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
316
 
 
317
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
318
 
 
319
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
320
  59%|█████▉ | 116/195 [00:57<00:21, 3.71it/s]
321
 
 
322
  59%|█████▉ | 116/195 [00:58<00:21, 3.71it/s]
323
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
324
 
 
325
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
326
 
 
327
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
328
  61%|██████ | 119/195 [00:59<00:30, 2.48it/s]
329
 
 
330
  61%|██████ | 119/195 [00:59<00:30, 2.48it/s]
331
  62%|██████▏ | 120/195 [00:59<00:26, 2.85it/s]
332
 
 
333
  62%|██████▏ | 120/195 [00:59<00:26, 2.85it/s]
334
 
 
335
  62%|██████▏ | 120/195 [01:04<00:26, 2.85it/s]
336
  62%|██████▏ | 121/195 [01:05<01:56, 1.58s/it]
337
 
 
338
  62%|██████▏ | 121/195 [01:05<01:56, 1.58s/it]
339
  63%|██████▎ | 122/195 [01:05<01:31, 1.25s/it]
340
 
 
341
  63%|██████▎ | 122/195 [01:05<01:31, 1.25s/it]
342
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
343
 
 
344
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
345
 
 
346
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
347
  64%|██████▍ | 125/195 [01:06<00:46, 1.51it/s]
348
 
 
349
  64%|██████▍ | 125/195 [01:06<00:46, 1.51it/s]
350
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
351
 
 
352
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
353
 
 
354
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
355
  66%|██████▌ | 128/195 [01:07<00:35, 1.89it/s]
356
 
 
357
  66%|██████▌ | 128/195 [01:07<00:35, 1.89it/s]
358
  66%|██████▌ | 129/195 [01:07<00:29, 2.24it/s]
359
 
 
360
  66%|██████▌ | 129/195 [01:07<00:29, 2.24it/s]
361
 
 
362
  66%|██████▌ | 129/195 [01:08<00:29, 2.24it/s]
363
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
364
 
 
365
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
366
 
 
367
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
368
 
 
369
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
370
  69%|██████▊ | 134/195 [01:08<00:17, 3.48it/s]
371
 
 
372
  69%|██████▊ | 134/195 [01:09<00:17, 3.48it/s]
373
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
374
 
 
375
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
376
 
 
377
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
378
  70%|███████ | 137/195 [01:10<00:19, 3.01it/s]
379
 
 
380
  70%|███████ | 137/195 [01:10<00:19, 3.01it/s]
381
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
382
 
 
383
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
384
 
 
385
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
386
  72%|███████▏ | 140/195 [01:11<00:16, 3.42it/s]
387
 
 
388
  72%|███████▏ | 140/195 [01:11<00:16, 3.42it/s]
389
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
390
 
 
391
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
392
 
 
393
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
394
  73%|███████▎ | 143/195 [01:12<00:17, 2.95it/s]
395
 
 
396
  73%|███████▎ | 143/195 [01:12<00:17, 2.95it/s]
397
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
398
 
 
399
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
400
 
 
401
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
402
  75%|███████▍ | 146/195 [01:13<00:14, 3.48it/s]
403
 
 
404
  75%|███████▍ | 146/195 [01:13<00:14, 3.48it/s]
405
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
406
 
 
407
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
408
 
 
409
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
410
  76%|███████▋ | 149/195 [01:14<00:15, 2.98it/s]
411
 
 
412
  76%|███████▋ | 149/195 [01:14<00:15, 2.98it/s]
413
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
414
 
 
415
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
416
 
 
417
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
418
  78%|███████▊ | 152/195 [01:15<00:12, 3.54it/s]
419
 
 
420
  78%|███████▊ | 152/195 [01:16<00:12, 3.54it/s]
421
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
422
 
 
423
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
424
 
 
425
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
426
  79%|███████▉ | 155/195 [01:17<00:17, 2.31it/s]
427
 
 
428
  79%|███████▉ | 155/195 [01:17<00:17, 2.31it/s]
429
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
430
 
 
431
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
432
 
 
433
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
434
  81%|████████ | 158/195 [01:17<00:12, 2.99it/s]
435
 
 
436
  81%|████████ | 158/195 [01:18<00:12, 2.99it/s]
437
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
438
 
 
439
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
440
 
 
441
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
442
  83%|████████▎ | 161/195 [01:19<00:13, 2.52it/s]
443
 
 
444
  83%|████████▎ | 161/195 [01:19<00:13, 2.52it/s]
445
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
446
 
 
447
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
448
 
 
449
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
450
  84%|████████▍ | 164/195 [01:20<00:09, 3.18it/s]
451
 
 
452
  84%|████████▍ | 164/195 [01:20<00:09, 3.18it/s]
453
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
454
 
 
455
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
456
 
 
457
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
458
  86%|████████▌ | 167/195 [01:21<00:10, 2.66it/s]
459
 
 
460
  86%|████████▌ | 167/195 [01:21<00:10, 2.66it/s]
461
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
462
 
 
463
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
464
 
 
465
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
466
  87%|████████▋ | 170/195 [01:22<00:07, 3.31it/s]
467
 
 
468
  87%|████████▋ | 170/195 [01:23<00:07, 3.31it/s]
469
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
470
 
 
471
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
472
 
 
473
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
474
  89%|████████▊ | 173/195 [01:24<00:09, 2.27it/s]
475
 
 
476
  89%|████████▊ | 173/195 [01:24<00:09, 2.27it/s]
477
  89%|████████▉ | 174/195 [01:24<00:08, 2.60it/s]
478
 
 
479
  89%|████████▉ | 174/195 [01:24<00:08, 2.60it/s]
480
 
 
481
  89%|████████▉ | 174/195 [01:25<00:08, 2.60it/s]
482
  90%|█████████ | 176/195 [01:25<00:06, 2.98it/s]
483
 
 
484
  90%|█████████ | 176/195 [01:27<00:06, 2.98it/s]
485
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
486
 
 
487
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
488
 
 
489
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
490
  92%|█████████▏| 179/195 [01:28<00:08, 1.82it/s]
491
 
 
492
  92%|█████████▏| 179/195 [01:28<00:08, 1.82it/s]
493
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
494
 
 
495
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
496
 
 
497
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
498
  93%|█████████▎| 182/195 [01:28<00:05, 2.55it/s]
499
 
 
500
  93%|█████████▎| 182/195 [01:30<00:05, 2.55it/s]
501
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
502
 
 
503
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
504
 
 
505
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
506
  95%|█████████▍| 185/195 [01:30<00:04, 2.04it/s]
507
 
 
508
  95%|██████���██▍| 185/195 [01:31<00:04, 2.04it/s]
509
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
510
 
 
511
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
512
 
 
513
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
514
  96%|█████████▋| 188/195 [01:31<00:02, 2.78it/s]
515
 
 
516
  96%|█████████▋| 188/195 [01:33<00:02, 2.78it/s]
517
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
518
 
 
519
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
520
 
 
521
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
522
  98%|█████████▊| 191/195 [01:34<00:02, 1.82it/s]
523
 
 
524
  98%|█████████▊| 191/195 [01:34<00:02, 1.82it/s]
525
  98%|█████████▊| 192/195 [01:34<00:01, 2.15it/s]
526
 
 
527
  98%|█████████▊| 192/195 [01:35<00:01, 2.15it/s]
528
  99%|█████████▉| 193/195 [01:35<00:01, 1.45it/s]
529
 
 
530
  99%|█████████▉| 193/195 [01:36<00:01, 1.45it/s]
531
  99%|█████████▉| 194/195 [01:36<00:00, 1.72it/s]
532
 
 
533
  99%|█████████▉| 194/195 [01:36<00:00, 1.72it/s]
 
 
 
 
 
 
 
 
 
 
 
1
+ /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Meta-Llama-3-8B-Instruct --quantization q0f16 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC
2
+ [2024-06-04 03:12:21] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
3
+ [2024-06-04 03:12:21] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
4
+ [2024-06-04 03:12:21] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
5
+ [2024-06-04 03:12:21] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
6
+ [2024-06-04 03:12:21] INFO config.py:107: Overriding max_batch_size from 1 to 80
7
+ [2024-06-04 03:12:21] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
8
+ [2024-06-04 03:12:21] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [128001, 128009]
9
+ [2024-06-04 03:12:21] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.6
10
+ [2024-06-04 03:12:21] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.9
11
+ [2024-06-04 03:12:21] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.model
12
+ [2024-06-04 03:12:21] INFO gen_config.py:155: Found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC/tokenizer.json
13
+ [2024-06-04 03:12:21] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/vocab.json
14
+ [2024-06-04 03:12:21] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/merges.txt
15
+ [2024-06-04 03:12:21] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/added_tokens.json
16
+ [2024-06-04 03:12:21] INFO gen_config.py:155: Found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC/tokenizer_config.json
17
+ [2024-06-04 03:12:21] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
18
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
19
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
20
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
21
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
22
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
23
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
24
+ [2024-06-04 03:12:21] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-06-04 03:12:21] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC/mlc-chat-config.json
26
+ /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Meta-Llama-3-8B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC
27
+ [2024-06-04 03:12:23] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
28
+ [2024-06-04 03:12:24] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-06-04 03:12:26] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-06-04 03:12:27] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-06-04 03:12:29] INFO auto_device.py:79: Found device: vulkan:0
32
+ [2024-06-04 03:12:29] INFO auto_device.py:79: Found device: vulkan:1
33
+ [2024-06-04 03:12:29] INFO auto_device.py:79: Found device: vulkan:2
34
+ [2024-06-04 03:12:29] INFO auto_device.py:79: Found device: vulkan:3
35
+ [2024-06-04 03:12:30] INFO auto_device.py:88: Not found device: opencl:0
36
+ [2024-06-04 03:12:30] INFO auto_device.py:35: Using device: cuda:0
37
+ [2024-06-04 03:12:30] INFO auto_weight.py:71: Finding weights in: /models/Meta-Llama-3-8B-Instruct
38
+ [2024-06-04 03:12:30] INFO auto_weight.py:137: Not found Huggingface PyTorch
39
+ [2024-06-04 03:12:30] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json
40
+ [2024-06-04 03:12:30] INFO auto_weight.py:107: Using source weight configuration: /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json. Use `--source` to override.
41
+ [2024-06-04 03:12:30] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
42
+ [2024-06-04 03:12:30] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
43
+ [2024-06-04 03:12:30] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
44
+ [2024-06-04 03:12:30] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
45
+ Weight conversion with arguments:
46
+ --config /models/Meta-Llama-3-8B-Instruct/config.json
47
+ --quantization NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
48
+ --model-type llama
49
+ --device cuda:0
50
+ --source /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json
51
+ --source-format huggingface-safetensor
52
+ --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC
53
+ Start storing to cache /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC
54
+
55
  0%| | 0/195 [00:00<?, ?it/s]
56
 
57
+
58
  0%| | 0/195 [00:00<?, ?it/s]
59
 
60
+
61
  0%| | 0/195 [00:03<?, ?it/s]
62
  1%| | 1/195 [00:06<20:46, 6.43s/it]
63
 
64
+
65
  1%| | 1/195 [00:06<20:46, 6.43s/it]
66
  1%| | 2/195 [00:06<08:44, 2.72s/it]
67
 
68
+
69
  1%| | 2/195 [00:06<08:44, 2.72s/it]
70
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
71
 
72
+
73
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
74
 
75
+
76
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
77
 
78
+
79
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
80
 
81
+
82
  2%|▏ | 3/195 [00:07<05:29, 1.72s/it]
83
 
84
+
85
  2%|▏ | 3/195 [00:13<05:29, 1.72s/it]
86
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
87
 
88
+
89
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
90
 
91
+
92
  3%|▎ | 6/195 [00:16<08:03, 2.56s/it]
93
  4%|▍ | 8/195 [00:16<05:15, 1.69s/it]
94
 
95
+
96
  4%|▍ | 8/195 [00:17<05:15, 1.69s/it]
97
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
98
 
99
+
100
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
101
 
102
+
103
  5%|▍ | 9/195 [00:17<04:50, 1.56s/it]
104
  6%|▌ | 11/195 [00:18<03:06, 1.01s/it]
105
 
106
+
107
  6%|▌ | 11/195 [00:18<03:06, 1.01s/it]
108
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
109
 
110
+
111
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
112
 
113
+
114
  6%|▌ | 12/195 [00:18<02:31, 1.20it/s]
115
  7%|▋ | 14/195 [00:18<01:51, 1.63it/s]
116
 
117
+
118
  7%|▋ | 14/195 [00:19<01:51, 1.63it/s]
119
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
120
 
121
+
122
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
123
 
124
+
125
  8%|▊ | 15/195 [00:19<02:09, 1.39it/s]
126
  9%|▊ | 17/195 [00:20<01:27, 2.02it/s]
127
 
128
+
129
  9%|▊ | 17/195 [00:20<01:27, 2.02it/s]
130
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
131
 
132
+
133
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
134
 
135
+
136
  9%|▉ | 18/195 [00:20<01:14, 2.37it/s]
137
  10%|█ | 20/195 [00:20<01:03, 2.77it/s]
138
 
139
+
140
  10%|█ | 20/195 [00:21<01:03, 2.77it/s]
141
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
142
 
143
+
144
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
145
 
146
+
147
  11%|█ | 21/195 [00:21<01:30, 1.93it/s]
148
  12%|█▏ | 23/195 [00:22<01:03, 2.70it/s]
149
 
150
+
151
  12%|█▏ | 23/195 [00:22<01:03, 2.70it/s]
152
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
153
 
154
+
155
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
156
 
157
+
158
  12%|█▏ | 24/195 [00:22<00:55, 3.08it/s]
159
  13%|█▎ | 26/195 [00:22<00:50, 3.33it/s]
160
 
161
+
162
  13%|█▎ | 26/195 [00:23<00:50, 3.33it/s]
163
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
164
 
165
+
166
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
167
 
168
+
169
  14%|█▍ | 27/195 [00:23<01:19, 2.12it/s]
170
  15%|���▍ | 29/195 [00:24<00:56, 2.92it/s]
171
 
172
+
173
  15%|█▍ | 29/195 [00:24<00:56, 2.92it/s]
174
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
175
 
176
+
177
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
178
 
179
+
180
  15%|█▌ | 30/195 [00:24<00:49, 3.31it/s]
181
  16%|█▋ | 32/195 [00:24<00:46, 3.49it/s]
182
 
183
+
184
  16%|█▋ | 32/195 [00:25<00:46, 3.49it/s]
185
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
186
 
187
+
188
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
189
 
190
+
191
  17%|█▋ | 33/195 [00:25<01:14, 2.18it/s]
192
  18%|█▊ | 35/195 [00:26<00:53, 2.99it/s]
193
 
194
+
195
  18%|█▊ | 35/195 [00:26<00:53, 2.99it/s]
196
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
197
 
198
+
199
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
200
 
201
+
202
  18%|█▊ | 36/195 [00:26<00:47, 3.37it/s]
203
  19%|█▉ | 38/195 [00:26<00:44, 3.51it/s]
204
 
205
+
206
  19%|█▉ | 38/195 [00:27<00:44, 3.51it/s]
207
  20%|██ | 39/195 [00:27<01:12, 2.15it/s]
208
 
209
+
210
  20%|██ | 39/195 [00:27<01:12, 2.15it/s]
211
 
212
+
213
  20%|██ | 39/195 [00:28<01:12, 2.15it/s]
214
  21%|██ | 41/195 [00:28<00:52, 2.94it/s]
215
 
216
+
217
  21%|██ | 41/195 [00:28<00:52, 2.94it/s]
218
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
219
 
220
+
221
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
222
 
223
+
224
  22%|██▏ | 42/195 [00:28<00:45, 3.33it/s]
225
  23%|██▎ | 44/195 [00:28<00:42, 3.52it/s]
226
 
227
+
228
  23%|██▎ | 44/195 [00:29<00:42, 3.52it/s]
229
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
230
 
231
+
232
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
233
 
234
+
235
  23%|██▎ | 45/195 [00:30<01:09, 2.17it/s]
236
  24%|██▍ | 47/195 [00:30<00:49, 2.99it/s]
237
 
238
+
239
  24%|██▍ | 47/195 [00:30<00:49, 2.99it/s]
240
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
241
 
242
+
243
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
244
 
245
+
246
  25%|██▍ | 48/195 [00:30<00:43, 3.36it/s]
247
  26%|██▌ | 50/195 [00:30<00:41, 3.46it/s]
248
 
249
+
250
  26%|██▌ | 50/195 [00:31<00:41, 3.46it/s]
251
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
252
 
253
+
254
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
255
 
256
+
257
  26%|██▌ | 51/195 [00:32<01:06, 2.17it/s]
258
  27%|██▋ | 53/195 [00:32<00:47, 2.98it/s]
259
 
260
+
261
  27%|██▋ | 53/195 [00:32<00:47, 2.98it/s]
262
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
263
 
264
+
265
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
266
 
267
+
268
  28%|██▊ | 54/195 [00:32<00:41, 3.36it/s]
269
  29%|██▊ | 56/195 [00:33<00:39, 3.53it/s]
270
 
271
+
272
  29%|██▊ | 56/195 [00:33<00:39, 3.53it/s]
273
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
274
 
275
+
276
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
277
 
278
+
279
  29%|██▉ | 57/195 [00:34<01:02, 2.20it/s]
280
  30%|███ | 59/195 [00:34<00:45, 3.02it/s]
281
 
282
+
283
  30%|███ | 59/195 [00:34<00:45, 3.02it/s]
284
  31%|███ | 60/195 [00:34<00:39, 3.40it/s]
285
 
286
+
287
  31%|███ | 60/195 [00:34<00:39, 3.40it/s]
288
 
289
+
290
  31%|███ | 60/195 [00:35<00:39, 3.40it/s]
291
 
292
+
293
  31%|███ | 60/195 [00:39<00:39, 3.40it/s]
294
  31%|███▏ | 61/195 [00:39<02:58, 1.34s/it]
295
 
296
+
297
  31%|███▏ | 61/195 [00:39<02:58, 1.34s/it]
298
  32%|███▏ | 62/195 [00:39<02:31, 1.14s/it]
299
 
300
+
301
  32%|███▏ | 62/195 [00:40<02:31, 1.14s/it]
302
  32%|███▏ | 63/195 [00:40<02:29, 1.13s/it]
303
 
304
+
305
  32%|███▏ | 63/195 [00:40<02:29, 1.13s/it]
306
 
307
+
308
  32%|███▏ | 63/195 [00:41<02:29, 1.13s/it]
309
  33%|███▎ | 65/195 [00:41<01:31, 1.42it/s]
310
 
311
+
312
  33%|███▎ | 65/195 [00:41<01:31, 1.42it/s]
313
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
314
 
315
+
316
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
317
 
318
+
319
  34%|███▍ | 66/195 [00:41<01:14, 1.74it/s]
320
  35%|███▍ | 68/195 [00:41<00:56, 2.23it/s]
321
 
322
+
323
  35%|███▍ | 68/195 [00:42<00:56, 2.23it/s]
324
  35%|███▌ | 69/195 [00:42<01:14, 1.69it/s]
325
 
326
+
327
  35%|███▌ | 69/195 [00:42<01:14, 1.69it/s]
328
 
329
+
330
  35%|███▌ | 69/195 [00:43<01:14, 1.69it/s]
331
  36%|███▋ | 71/195 [00:43<00:50, 2.44it/s]
332
 
333
+
334
  36%|███▋ | 71/195 [00:43<00:50, 2.44it/s]
335
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
336
 
337
+
338
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
339
 
340
+
341
  37%|███▋ | 72/195 [00:43<00:43, 2.83it/s]
342
  38%|███▊ | 74/195 [00:43<00:38, 3.16it/s]
343
 
344
+
345
  38%|███▊ | 74/195 [00:44<00:38, 3.16it/s]
346
  38%|███▊ | 75/195 [00:44<00:57, 2.08it/s]
347
 
348
+
349
  38%|███▊ | 75/195 [00:44<00:57, 2.08it/s]
350
 
351
+
352
  38%|███▊ | 75/195 [00:45<00:57, 2.08it/s]
353
  39%|███▉ | 77/195 [00:45<00:40, 2.90it/s]
354
 
355
+
356
  39%|███▉ | 77/195 [00:45<00:40, 2.90it/s]
357
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
358
 
359
+
360
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
361
 
362
+
363
  40%|████ | 78/195 [00:45<00:35, 3.29it/s]
364
  41%|████ | 80/195 [00:45<00:32, 3.50it/s]
365
 
366
+
367
  41%|████ | 80/195 [00:46<00:32, 3.50it/s]
368
  42%|████▏ | 81/195 [00:46<00:51, 2.21it/s]
369
 
370
+
371
  42%|████▏ | 81/195 [00:46<00:51, 2.21it/s]
372
 
373
+
374
  42%|████▏ | 81/195 [00:47<00:51, 2.21it/s]
375
  43%|████▎ | 83/195 [00:47<00:36, 3.06it/s]
376
 
377
+
378
  43%|████▎ | 83/195 [00:47<00:36, 3.06it/s]
379
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
380
 
381
+
382
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
383
 
384
+
385
  43%|████▎ | 84/195 [00:47<00:32, 3.46it/s]
386
  44%|████▍ | 86/195 [00:47<00:29, 3.64it/s]
387
 
388
+
389
  44%|████▍ | 86/195 [00:48<00:29, 3.64it/s]
390
  45%|████▍ | 87/195 [00:48<00:47, 2.26it/s]
391
 
392
+
393
  45%|████▍ | 87/195 [00:48<00:47, 2.26it/s]
394
 
395
+
396
  45%|████▍ | 87/195 [00:49<00:47, 2.26it/s]
397
  46%|████▌ | 89/195 [00:49<00:33, 3.12it/s]
398
 
399
+
400
  46%|████▌ | 89/195 [00:49<00:33, 3.12it/s]
401
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
402
 
403
+
404
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
405
 
406
+
407
  46%|████▌ | 90/195 [00:49<00:29, 3.52it/s]
408
  47%|████▋ | 92/195 [00:49<00:27, 3.68it/s]
409
 
410
+
411
  47%|████▋ | 92/195 [00:50<00:27, 3.68it/s]
412
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
413
 
414
+
415
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
416
 
417
+
418
  48%|████▊ | 93/195 [00:50<00:44, 2.28it/s]
419
  49%|████▊ | 95/195 [00:51<00:31, 3.14it/s]
420
 
421
+
422
  49%|████▊ | 95/195 [00:51<00:31, 3.14it/s]
423
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
424
 
425
+
426
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
427
 
428
+
429
  49%|████▉ | 96/195 [00:51<00:27, 3.54it/s]
430
  50%|█████ | 98/195 [00:51<00:26, 3.70it/s]
431
 
432
+
433
  50%|█████ | 98/195 [00:52<00:26, 3.70it/s]
434
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
435
 
436
+
437
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
438
 
439
+
440
  51%|█████ | 99/195 [00:52<00:41, 2.29it/s]
441
  52%|█████▏ | 101/195 [00:53<00:29, 3.16it/s]
442
 
443
+
444
  52%|█████▏ | 101/195 [00:53<00:29, 3.16it/s]
445
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
446
 
447
+
448
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
449
 
450
+
451
  52%|█████▏ | 102/195 [00:53<00:26, 3.57it/s]
452
  53%|█████▎ | 104/195 [00:53<00:24, 3.71it/s]
453
 
454
+
455
  53%|█████▎ | 104/195 [00:54<00:24, 3.71it/s]
456
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
457
 
458
+
459
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
460
 
461
+
462
  54%|█████▍ | 105/195 [00:54<00:39, 2.29it/s]
463
  55%|█████▍ | 107/195 [00:54<00:27, 3.15it/s]
464
 
465
+
466
  55%|█████▍ | 107/195 [00:55<00:27, 3.15it/s]
467
  55%|█████▌ | 108/195 [00:55<00:24, 3.57it/s]
468
 
469
+
470
  55%|████���▌ | 108/195 [00:55<00:24, 3.57it/s]
471
 
472
+
473
  55%|█████▌ | 108/195 [00:55<00:24, 3.57it/s]
474
  56%|█████▋ | 110/195 [00:55<00:22, 3.71it/s]
475
 
476
+
477
  56%|█████▋ | 110/195 [00:56<00:22, 3.71it/s]
478
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
479
 
480
+
481
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
482
 
483
+
484
  57%|█████▋ | 111/195 [00:56<00:36, 2.29it/s]
485
  58%|█████▊ | 113/195 [00:56<00:26, 3.15it/s]
486
 
487
+
488
  58%|█████▊ | 113/195 [00:56<00:26, 3.15it/s]
489
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
490
 
491
+
492
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
493
 
494
+
495
  58%|█████▊ | 114/195 [00:57<00:22, 3.56it/s]
496
  59%|█████▉ | 116/195 [00:57<00:21, 3.71it/s]
497
 
498
+
499
  59%|█████▉ | 116/195 [00:58<00:21, 3.71it/s]
500
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
501
 
502
+
503
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
504
 
505
+
506
  60%|██████ | 117/195 [00:59<00:44, 1.76it/s]
507
  61%|██████ | 119/195 [00:59<00:30, 2.48it/s]
508
 
509
+
510
  61%|██████ | 119/195 [00:59<00:30, 2.48it/s]
511
  62%|██████▏ | 120/195 [00:59<00:26, 2.85it/s]
512
 
513
+
514
  62%|██████▏ | 120/195 [00:59<00:26, 2.85it/s]
515
 
516
+
517
  62%|██████▏ | 120/195 [01:04<00:26, 2.85it/s]
518
  62%|██████▏ | 121/195 [01:05<01:56, 1.58s/it]
519
 
520
+
521
  62%|██████▏ | 121/195 [01:05<01:56, 1.58s/it]
522
  63%|██████▎ | 122/195 [01:05<01:31, 1.25s/it]
523
 
524
+
525
  63%|██████▎ | 122/195 [01:05<01:31, 1.25s/it]
526
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
527
 
528
+
529
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
530
 
531
+
532
  63%|██████▎ | 123/195 [01:05<01:09, 1.04it/s]
533
  64%|██████▍ | 125/195 [01:06<00:46, 1.51it/s]
534
 
535
+
536
  64%|██████▍ | 125/195 [01:06<00:46, 1.51it/s]
537
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
538
 
539
+
540
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
541
 
542
+
543
  65%|██████▍ | 126/195 [01:07<00:54, 1.26it/s]
544
  66%|██████▌ | 128/195 [01:07<00:35, 1.89it/s]
545
 
546
+
547
  66%|██████▌ | 128/195 [01:07<00:35, 1.89it/s]
548
  66%|██████▌ | 129/195 [01:07<00:29, 2.24it/s]
549
 
550
+
551
  66%|██████▌ | 129/195 [01:07<00:29, 2.24it/s]
552
 
553
+
554
  66%|██████▌ | 129/195 [01:08<00:29, 2.24it/s]
555
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
556
 
557
+
558
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
559
 
560
+
561
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
562
 
563
+
564
  67%|██████▋ | 131/195 [01:08<00:24, 2.65it/s]
565
  69%|██████▊ | 134/195 [01:08<00:17, 3.48it/s]
566
 
567
+
568
  69%|██████▊ | 134/195 [01:09<00:17, 3.48it/s]
569
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
570
 
571
+
572
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
573
 
574
+
575
  69%|██████▉ | 135/195 [01:10<00:26, 2.30it/s]
576
  70%|███████ | 137/195 [01:10<00:19, 3.01it/s]
577
 
578
+
579
  70%|███████ | 137/195 [01:10<00:19, 3.01it/s]
580
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
581
 
582
+
583
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
584
 
585
+
586
  71%|███████ | 138/195 [01:10<00:17, 3.35it/s]
587
  72%|███████▏ | 140/195 [01:11<00:16, 3.42it/s]
588
 
589
+
590
  72%|███████▏ | 140/195 [01:11<00:16, 3.42it/s]
591
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
592
 
593
+
594
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
595
 
596
+
597
  72%|███████▏ | 141/195 [01:12<00:24, 2.17it/s]
598
  73%|███████▎ | 143/195 [01:12<00:17, 2.95it/s]
599
 
600
+
601
  73%|███████▎ | 143/195 [01:12<00:17, 2.95it/s]
602
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
603
 
604
+
605
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
606
 
607
+
608
  74%|███████▍ | 144/195 [01:12<00:15, 3.32it/s]
609
  75%|███████▍ | 146/195 [01:13<00:14, 3.48it/s]
610
 
611
+
612
  75%|███████▍ | 146/195 [01:13<00:14, 3.48it/s]
613
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
614
 
615
+
616
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
617
 
618
+
619
  75%|███████▌ | 147/195 [01:14<00:22, 2.17it/s]
620
  76%|███████▋ | 149/195 [01:14<00:15, 2.98it/s]
621
 
622
+
623
  76%|███████▋ | 149/195 [01:14<00:15, 2.98it/s]
624
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
625
 
626
+
627
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
628
 
629
+
630
  77%|███████▋ | 150/195 [01:14<00:13, 3.36it/s]
631
  78%|███████▊ | 152/195 [01:15<00:12, 3.54it/s]
632
 
633
+
634
  78%|███████▊ | 152/195 [01:16<00:12, 3.54it/s]
635
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
636
 
637
+
638
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
639
 
640
+
641
  78%|███████▊ | 153/195 [01:17<00:25, 1.62it/s]
642
  79%|███████▉ | 155/195 [01:17<00:17, 2.31it/s]
643
 
644
+
645
  79%|███████▉ | 155/195 [01:17<00:17, 2.31it/s]
646
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
647
 
648
+
649
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
650
 
651
+
652
  80%|████████ | 156/195 [01:17<00:14, 2.67it/s]
653
  81%|████████ | 158/195 [01:17<00:12, 2.99it/s]
654
 
655
+
656
  81%|████████ | 158/195 [01:18<00:12, 2.99it/s]
657
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
658
 
659
+
660
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
661
 
662
+
663
  82%|████████▏ | 159/195 [01:19<00:20, 1.80it/s]
664
  83%|████████▎ | 161/195 [01:19<00:13, 2.52it/s]
665
 
666
+
667
  83%|████████▎ | 161/195 [01:19<00:13, 2.52it/s]
668
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
669
 
670
+
671
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
672
 
673
+
674
  83%|████████▎ | 162/195 [01:19<00:11, 2.90it/s]
675
  84%|████████▍ | 164/195 [01:20<00:09, 3.18it/s]
676
 
677
+
678
  84%|████████▍ | 164/195 [01:20<00:09, 3.18it/s]
679
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
680
 
681
+
682
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
683
 
684
+
685
  85%|████████▍ | 165/195 [01:21<00:15, 1.91it/s]
686
  86%|████████▌ | 167/195 [01:21<00:10, 2.66it/s]
687
 
688
+
689
  86%|████████▌ | 167/195 [01:21<00:10, 2.66it/s]
690
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
691
 
692
+
693
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
694
 
695
+
696
  86%|████████▌ | 168/195 [01:22<00:08, 3.04it/s]
697
  87%|████████▋ | 170/195 [01:22<00:07, 3.31it/s]
698
 
699
+
700
  87%|████████▋ | 170/195 [01:23<00:07, 3.31it/s]
701
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
702
 
703
+
704
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
705
 
706
+
707
  88%|████████▊ | 171/195 [01:24<00:15, 1.59it/s]
708
  89%|████████▊ | 173/195 [01:24<00:09, 2.27it/s]
709
 
710
+
711
  89%|████████▊ | 173/195 [01:24<00:09, 2.27it/s]
712
  89%|████████▉ | 174/195 [01:24<00:08, 2.60it/s]
713
 
714
+
715
  89%|████████▉ | 174/195 [01:24<00:08, 2.60it/s]
716
 
717
+
718
  89%|████████▉ | 174/195 [01:25<00:08, 2.60it/s]
719
  90%|█████████ | 176/195 [01:25<00:06, 2.98it/s]
720
 
721
+
722
  90%|█████████ | 176/195 [01:27<00:06, 2.98it/s]
723
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
724
 
725
+
726
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
727
 
728
+
729
  91%|█████████ | 177/195 [01:27<00:14, 1.24it/s]
730
  92%|█████████▏| 179/195 [01:28<00:08, 1.82it/s]
731
 
732
+
733
  92%|█████████▏| 179/195 [01:28<00:08, 1.82it/s]
734
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
735
 
736
+
737
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
738
 
739
+
740
  92%|█████████▏| 180/195 [01:28<00:07, 2.14it/s]
741
  93%|█████████▎| 182/195 [01:28<00:05, 2.55it/s]
742
 
743
+
744
  93%|█████████▎| 182/195 [01:30<00:05, 2.55it/s]
745
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
746
 
747
+
748
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
749
 
750
+
751
  94%|█████████▍| 183/195 [01:30<00:08, 1.42it/s]
752
  95%|█████████▍| 185/195 [01:30<00:04, 2.04it/s]
753
 
754
+
755
  95%|██████���██▍| 185/195 [01:31<00:04, 2.04it/s]
756
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
757
 
758
+
759
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
760
 
761
+
762
  95%|█████████▌| 186/195 [01:31<00:03, 2.38it/s]
763
  96%|█████████▋| 188/195 [01:31<00:02, 2.78it/s]
764
 
765
+
766
  96%|█████████▋| 188/195 [01:33<00:02, 2.78it/s]
767
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
768
 
769
+
770
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
771
 
772
+
773
  97%|█████████▋| 189/195 [01:34<00:04, 1.25it/s]
774
  98%|█████████▊| 191/195 [01:34<00:02, 1.82it/s]
775
 
776
+
777
  98%|█████████▊| 191/195 [01:34<00:02, 1.82it/s]
778
  98%|█████████▊| 192/195 [01:34<00:01, 2.15it/s]
779
 
780
+
781
  98%|█████████▊| 192/195 [01:35<00:01, 2.15it/s]
782
  99%|█████████▉| 193/195 [01:35<00:01, 1.45it/s]
783
 
784
+
785
  99%|█████████▉| 193/195 [01:36<00:01, 1.45it/s]
786
  99%|█████████▉| 194/195 [01:36<00:00, 1.72it/s]
787
 
788
+
789
  99%|█████████▉| 194/195 [01:36<00:00, 1.72it/s]
790
+ [2024-06-04 03:14:09] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors
791
+ [2024-06-04 03:14:09] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors
792
+ [2024-06-04 03:14:10] INFO stats.py:77: Time usage: HF loading: 15.816 sec; Pre-quantization mapping: 36.574 sec; Quantization: 0.000 sec
793
+ [2024-06-04 03:14:10] INFO stats.py:91: RAM usage: Peak RAM: 18.469 GB. Total bytes loaded from disk: 29.915 GB
794
+ [2024-06-04 03:14:10] INFO convert_weight.py:155: Parameter size after quantization: 14.958 GB
795
+ [2024-06-04 03:14:10] INFO convert_weight.py:160: Total parameters: 8,030,261,248
796
+ [2024-06-04 03:14:10] INFO convert_weight.py:161: Bits per parameter: 16.000
797
+ [2024-06-04 03:14:10] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC
798
+
799
+ All finished, 131 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q0f16-MLC/ndarray-cache.json
mlc-chat-config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q0f16",
5
+ "model_config": {
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 14336,
8
+ "num_attention_heads": 32,
9
+ "num_hidden_layers": 32,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 128256,
12
+ "position_embedding_base": 500000.0,
13
+ "context_window_size": 8192,
14
+ "prefill_chunk_size": 2048,
15
+ "num_key_value_heads": 8,
16
+ "head_dim": 128,
17
+ "tensor_parallel_shards": 1,
18
+ "max_batch_size": 80
19
+ },
20
+ "vocab_size": 128256,
21
+ "context_window_size": 8192,
22
+ "sliding_window_size": -1,
23
+ "prefill_chunk_size": 2048,
24
+ "attention_sink_size": -1,
25
+ "tensor_parallel_shards": 1,
26
+ "temperature": 0.6,
27
+ "presence_penalty": 0.0,
28
+ "frequency_penalty": 0.0,
29
+ "repetition_penalty": 1.0,
30
+ "top_p": 0.9,
31
+ "tokenizer_files": [
32
+ "tokenizer.json",
33
+ "tokenizer_config.json"
34
+ ],
35
+ "tokenizer_info": {
36
+ "token_postproc_method": "byte_level",
37
+ "prepend_space_in_encode": false,
38
+ "strip_space_in_decode": false
39
+ },
40
+ "conv_template": {
41
+ "name": "llama-3",
42
+ "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>\n",
43
+ "system_message": "You are a helpful, respectful and honest assistant.",
44
+ "system_prefix_token_ids": [
45
+ 128000
46
+ ],
47
+ "add_role_after_system_message": true,
48
+ "roles": {
49
+ "user": "<|start_header_id|>user",
50
+ "assistant": "<|start_header_id|>assistant"
51
+ },
52
+ "role_templates": {
53
+ "user": "{user_message}",
54
+ "assistant": "{assistant_message}",
55
+ "tool": "{tool_message}"
56
+ },
57
+ "messages": [],
58
+ "seps": [
59
+ "<|eot_id|>"
60
+ ],
61
+ "role_content_sep": "<|end_header_id|>\n\n",
62
+ "role_empty_sep": "<|end_header_id|>\n\n",
63
+ "stop_str": [
64
+ "<|end_of_text|>",
65
+ "<|eot_id|>"
66
+ ],
67
+ "stop_token_ids": [
68
+ 128001,
69
+ 128009
70
+ ],
71
+ "function_string": "",
72
+ "use_function_calling": false
73
+ },
74
+ "pad_token_id": 0,
75
+ "bos_token_id": 128000,
76
+ "eos_token_id": [
77
+ 128001,
78
+ 128009
79
+ ],
80
+ "mean_gen_len": 128,
81
+ "max_gen_len": 512,
82
+ "shift_fill_factor": 0.3
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 sha256:768615f077fb797967844571c58b94d7c399d884d115be3ab4b0154504cae892
3
+ size 1050673152
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a00cd3ecd5e91624a27f9e239b1de425d5ba3cfff82c256a11a4ad434abf3c2
3
+ size 117440512
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b237c9763fa3f75166a6f70b70f1566e77d0d89dfa164ed1b3137393e90575c3
3
+ size 33554432
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8756eac43c926211f1b9e7269f5afdc344d2d3f6e9484707b26b53c2628a5a5
3
+ size 234881024
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d81e195387d6e6fec4863cee2e7e9359ab110dcaac86ec9ceb216a2516b80ee
3
+ size 50331648
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a1363b3ccc87312094c2195022687c16b0dad7fafb9e80bb4ec474d53c29ac
3
+ size 33554432
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd477d6c50aed5f424a878dd284343379cffbee8a34c0b6e55100c8305fa13f
3
+ size 117440512
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ded5db8acb8269503e97e23d7b89fc41f5e163b6c09687d58bed8220867c214
3
+ size 234881024
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b176d164b460856996f78dc64b2040cf0389a8fa5c707325e31fecba3ea738
3
+ size 50331648
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798aaf702e53b657265ac3b5e6caf3a0ab515bdadfeb1a3a156b4f3bfba76666
3
+ size 33554432
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944a60a409d0d5b6a851e33c69aca152454b691711a8b96f5bcc488772ab2833
3
+ size 117440512
params_shard_108.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde8f8e8b6ad3734d95136cb532e8610789c6bd62fd97942d29e0c0f79cce4dc
3
+ size 234881024
params_shard_109.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21dba75de953ef1de743c943138bbeba5a4e3f6afd90e1b85f4db644360bfa8e
3
+ size 50331648
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73823eef46632aedcc8c1cb08a736b6aa97ca97842cd1fdfc5567d8dec459662
3
+ size 117440512
params_shard_110.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39532c7e836baad164a655fb97ec5114ea4da37ffba9fdea2684f6e4450e6f84
3
+ size 33554432
params_shard_111.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2823272bec3a1c12f02cc4cb24aa4031abd7e9dbe0b02676e2305b21671818f0
3
+ size 117440512
params_shard_112.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5625690c816a2ad6d5b13a9c1b3804048c349593813791905b6ffc189e5f2b7
3
+ size 234881024
params_shard_113.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2332a706f61e128aeefd094430ecbf8142a6556d5a26a6a02697c5032a6d548
3
+ size 50331648
params_shard_114.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac407ad02361d53207b3c7e25ceab84dcb4347b8087055162e2efe14d11d84a
3
+ size 33554432
params_shard_115.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f29ed51055d1c1adb8f0660bbe538a27e016c65650f2d67efc6f1c84fa1b45
3
+ size 117440512
params_shard_116.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2347ac7c2b83bcfb2810c0fb599a6125d17b165b072b9e5413006e77e0c3502
3
+ size 234881024
params_shard_117.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1f95b27d99a455ee05cfed5f95c3dbbd86006a3461bc18cc66ec106de06c70
3
+ size 50331648
params_shard_118.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155101c03ddbf18f4fd0694bfc982f33c7bae25c9b087d6f5273c2bfbffcf2c9
3
+ size 33554432
params_shard_119.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594bb692ec2779938721ff4748666ca8370e0e4fe85229503f616438b8884f5f
3
+ size 117440512
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489a5da618768bdaf25fbbc2d9d816ba015c74878a94363d08e3f40e1f5bf04a
3
+ size 234881024
params_shard_120.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebdc706ea33c279bd1a72e781ce75a6ab5ea6e099e179929b751f41a512231c6
3
+ size 234881024
params_shard_121.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936b84e379732bda39a1f141d50a04106ff9f54426d744676a1eb270c32685f8
3
+ size 50331648
params_shard_122.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c944ed44b124b014906fc240afd3b90aed56bbd9567f2eddfd5b7a685b3cb48
3
+ size 33554432
params_shard_123.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417959da77ceb33ead4271cbb9428b195196173a893c44e52880a7ec61b4856b
3
+ size 117440512
params_shard_124.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1d553bd6a2359c52a0dad79a45d4c2d672b1fb748590ee8bf9ed68aa7fc6ca
3
+ size 234881024
params_shard_125.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec106ce0dbfa92b2e0be4aa1e0b7d2229068f682808d40bac723a8d77541a34e
3
+ size 50331648
params_shard_126.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca541fb2e57e2257118c35784845b0c731278af8db3036ac53d71aa1681fdbdc
3
+ size 33554432
params_shard_127.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327eacd934083bbd7ff3b180af3ea3ea0b37864a8901647b60236476dc5fd0c7
3
+ size 234881024
params_shard_128.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ae046d19b31bcb6c1b8d7a50de0fcb493d57106c6bec10683739686ccbf7d3
3
+ size 50331648
params_shard_129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215617f50a1f5d9b2250b82f3652b35a9e9aa0ad9ef2b485d73965a14b2b872a
3
+ size 33554432
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3564e941913f160a42ed1a1772874056331cdf6cd4f734b95aa7edcb8cc2cb70
3
+ size 50331648
params_shard_130.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c501bdd49d7071e8e305d7ff6063e5cb223806a1dde616408512682b427030
3
+ size 532480
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9f66c32cff51154fea92933c2cd62549236f8cb1a767f9ef28d3f99809b343
3
+ size 33554432
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb332bc05e4821962fdc9dcbcc7cc12630f32117711b687d18fb53c0bc4fbf4
3
+ size 117440512
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10a3eb55a856a0eb7c64586f76c349c24543386863fffd35563af1244dfe3d7
3
+ size 234881024
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a07959289aa8b3113c115aef186a3affa2cd1d8f5b8e25e7e600dddbf393f03
3
+ size 50331648
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beaff0810687923585642ee11d929cbf3b43dc6f87f30ddb552c222ab57bdbb3
3
+ size 33554432
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620f34ee75cdc73aecb8949af5fbb0d2437fd81422b6d8eb7acfc52addb9fc68
3
+ size 117440512
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53102a11d9064bbd404833e3464b1b13e08ce73300b442312cccde2f19b2698
3
+ size 1050673152
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a959035c18de0c79d090c7aa0c92916566fb1d3ebd51830ec58404577c0127dc
3
+ size 234881024
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb962c5f3f8d6158c7bc60b8bac81c54bf91381da958a802687d34e0cbe2861
3
+ size 50331648
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1547e2497c423b0aff0eee71d9300d6fdf4e4986679418b6e637b69a9a6720b
3
+ size 33554432