Hugging Face's logo

mlc-ai
/
Qwen1.5-1.8B-Chat-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
riczhou commited on
Commit
423c362
·
verified ·
1 Parent(s): 7bae20c

Initial commit

Browse files
Files changed (35) hide show
  1. logs.txt +338 -0
  2. merges.txt +0 -0
  3. mlc-chat-config.json +83 -0
  4. ndarray-cache.json +0 -0
  5. params_shard_0.bin +3 -0
  6. params_shard_1.bin +3 -0
  7. params_shard_10.bin +3 -0
  8. params_shard_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_3.bin +3 -0
  27. params_shard_4.bin +3 -0
  28. params_shard_5.bin +3 -0
  29. params_shard_6.bin +3 -0
  30. params_shard_7.bin +3 -0
  31. params_shard_8.bin +3 -0
  32. params_shard_9.bin +3 -0
  33. tokenizer.json +0 -0
  34. tokenizer_config.json +40 -0
  35. vocab.json +0 -0
logs.txt ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/171 [00:00<?, ?it/s]
1
 
 
2
  0%| | 0/171 [00:00<?, ?it/s]
3
 
 
4
  0%| | 0/171 [00:05<?, ?it/s]
5
 
 
6
  0%| | 0/171 [00:06<?, ?it/s]
7
 
 
8
  0%| | 0/171 [00:06<?, ?it/s]
9
  1%| | 1/171 [00:06<18:30, 6.53s/it]
10
 
 
11
  1%| | 1/171 [00:08<18:30, 6.53s/it]
12
 
 
13
  1%| | 1/171 [00:08<18:30, 6.53s/it]
14
  1%| | 2/171 [00:08<10:46, 3.83s/it]
15
 
 
16
  1%| | 2/171 [00:08<10:46, 3.83s/it]
17
 
 
18
  1%| | 2/171 [00:08<10:46, 3.83s/it]
19
 
 
20
  1%| | 2/171 [00:08<10:46, 3.83s/it]
21
 
 
22
  1%| | 2/171 [00:08<10:46, 3.83s/it]
23
  2%|▏ | 4/171 [00:08<04:25, 1.59s/it]
24
 
 
25
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
26
 
 
27
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
28
 
 
29
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
30
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
31
 
 
32
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
33
 
 
34
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
35
 
 
36
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
37
 
 
38
  3%|▎ | 5/171 [00:10<03:33, 1.28s/it]
39
 
 
40
  3%|▎ | 5/171 [00:10<03:33, 1.28s/it]
41
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
42
 
 
43
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
44
 
 
45
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
46
 
 
47
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
48
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
49
 
 
50
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
51
 
 
52
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
53
 
 
54
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
55
 
 
56
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
57
 
 
58
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
59
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
60
 
 
61
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
62
 
 
63
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
64
 
 
65
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
66
 
 
67
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
68
 
 
69
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
70
 
 
71
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
72
 
 
73
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
74
 
 
75
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
76
 
 
77
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
78
  11%|█ | 18/171 [00:10<00:24, 6.26it/s]
79
 
 
80
  11%|█ | 18/171 [00:10<00:24, 6.26it/s]
81
 
 
82
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
83
 
 
84
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
85
 
 
86
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
87
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
88
 
 
89
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
90
 
 
91
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
92
 
 
93
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
94
 
 
95
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
96
 
 
97
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
98
 
 
99
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
100
 
 
101
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
102
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
103
 
 
104
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
105
 
 
106
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
107
 
 
108
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
109
 
 
110
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
111
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
112
 
 
113
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
114
 
 
115
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
116
 
 
117
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
118
 
 
119
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
120
 
 
121
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
122
 
 
123
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
124
 
 
125
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
126
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
127
 
 
128
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
129
 
 
130
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
131
 
 
132
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
133
 
 
134
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
135
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
136
 
 
137
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
138
 
 
139
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
140
 
 
141
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
142
 
 
143
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
144
 
 
145
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
146
 
 
147
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
148
 
 
149
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
150
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
151
 
 
152
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
153
 
 
154
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
155
 
 
156
  23%|█��▎ | 39/171 [00:11<00:06, 20.62it/s]
157
 
 
158
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
159
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
160
 
 
161
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
162
 
 
163
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
164
 
 
165
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
166
 
 
167
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
168
 
 
169
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
170
 
 
171
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
172
 
 
173
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
174
  27%|██▋ | 46/171 [00:11<00:05, 23.87it/s]
175
 
 
176
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
177
 
 
178
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
179
 
 
180
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
181
 
 
182
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
183
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
184
 
 
185
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
186
 
 
187
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
188
 
 
189
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
190
 
 
191
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
192
 
 
193
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
194
 
 
195
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
196
 
 
197
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
198
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
199
 
 
200
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
201
 
 
202
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
203
 
 
204
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
205
 
 
206
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
207
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
208
 
 
209
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
210
 
 
211
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
212
 
 
213
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
214
 
 
215
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
216
 
 
217
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
218
 
 
219
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
220
 
 
221
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
222
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
223
 
 
224
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
225
 
 
226
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
227
 
 
228
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
229
 
 
230
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
231
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
232
 
 
233
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
234
 
 
235
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
236
 
 
237
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
238
 
 
239
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
240
 
 
241
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
242
 
 
243
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
244
 
 
245
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
246
  39%|███▉ | 67/171 [00:12<00:04, 23.76it/s]
247
 
 
248
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
249
 
 
250
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
251
 
 
252
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
253
 
 
254
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
255
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
256
 
 
257
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
258
 
 
259
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
260
 
 
261
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
262
 
 
263
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
264
 
 
265
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
266
 
 
267
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
268
 
 
269
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
270
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
271
 
 
272
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
273
 
 
274
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
275
 
 
276
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
277
 
 
278
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
279
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
280
 
 
281
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
282
 
 
283
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
284
 
 
285
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
286
 
 
287
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
288
 
 
289
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
290
 
 
291
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
292
 
 
293
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
294
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
295
 
 
296
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
297
 
 
298
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
299
 
 
300
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
301
 
 
302
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
303
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
304
 
 
305
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
306
 
 
307
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
308
 
 
309
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
310
 
 
311
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
312
 
 
313
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
314
 
 
315
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
316
 
 
317
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
318
  51%|█████▏ | 88/171 [00:13<00:03, 22.66it/s]
319
 
 
320
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
321
 
 
322
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
323
 
 
324
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
325
 
 
326
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
327
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
328
 
 
329
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
330
 
 
331
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
332
 
 
333
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
334
 
 
335
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
336
 
 
337
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
338
 
 
339
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
340
 
 
341
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
342
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
343
 
 
344
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
345
 
 
346
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
347
 
 
348
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
349
 
 
350
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
351
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
352
 
 
353
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
354
 
 
355
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
356
 
 
357
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
358
 
 
359
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
360
 
 
361
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
362
 
 
363
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
364
 
 
365
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
366
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
367
 
 
368
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
369
 
 
370
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
371
 
 
372
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
373
 
 
374
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
375
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
376
 
 
377
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
378
 
 
379
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
380
 
 
381
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
382
 
 
383
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
384
 
 
385
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
386
 
 
387
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
388
 
 
389
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
390
  64%|██████▎ | 109/171 [00:14<00:02, 21.40it/s]
391
 
 
392
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
393
 
 
394
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
395
 
 
396
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
397
 
 
398
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
399
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
400
 
 
401
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
402
 
 
403
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
404
 
 
405
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
406
 
 
407
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
408
 
 
409
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
410
 
 
411
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
412
 
 
413
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
414
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
415
 
 
416
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
417
 
 
418
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
419
 
 
420
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
421
 
 
422
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
423
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
424
 
 
425
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
426
 
 
427
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
428
 
 
429
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
430
 
 
431
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
432
 
 
433
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
434
 
 
435
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
436
 
 
437
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
438
  72%|███████▏ | 123/171 [00:15<00:02, 19.27it/s]
439
 
 
440
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
441
 
 
442
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
443
 
 
444
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
445
 
 
446
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
447
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
448
 
 
449
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
450
 
 
451
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
452
 
 
453
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
454
 
 
455
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
456
 
 
457
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
458
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
459
 
 
460
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
461
 
 
462
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
463
 
 
464
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
465
 
 
466
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
467
 
 
468
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
469
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
470
 
 
471
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
472
 
 
473
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
474
 
 
475
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
476
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
477
 
 
478
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
479
 
 
480
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
481
 
 
482
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
483
 
 
484
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
485
 
 
486
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
487
 
 
488
  78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s]
489
 
 
490
  78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s]
491
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
492
 
 
493
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
494
 
 
495
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
496
 
 
497
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
498
 
 
499
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
500
 
 
501
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
502
 
 
503
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
504
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
505
 
 
506
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
507
 
 
508
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
509
 
 
510
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
511
 
 
512
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
513
 
 
514
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
515
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
516
 
 
517
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
518
 
 
519
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
520
 
 
521
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
522
 
 
523
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
524
 
 
525
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
526
 
 
527
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
528
 
 
529
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
530
 
 
531
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
532
 
 
533
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
534
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
535
 
 
536
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
537
 
 
538
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
539
 
 
540
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
541
 
 
542
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
543
  90%|█████████ | 154/171 [00:17<00:01, 14.89it/s]
544
 
 
545
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
546
 
 
547
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
548
 
 
549
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
550
 
 
551
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
552
 
 
553
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
554
 
 
555
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
556
 
 
557
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
558
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
559
 
 
560
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
561
 
 
562
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
563
 
 
564
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
565
 
 
566
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
567
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
568
 
 
569
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
570
 
 
571
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
572
 
 
573
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
574
 
 
575
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
576
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
577
 
 
578
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
579
 
 
580
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
581
 
 
582
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
583
 
 
584
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
585
 
 
586
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
587
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
588
 
 
589
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
590
 
 
591
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
592
 
 
593
  97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s]
594
 
 
595
  97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s]
596
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
597
 
 
598
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
599
 
 
600
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
601
 
 
602
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
 
 
 
 
 
 
 
 
 
 
1
+ /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-1.8B-Chat --quantization q4f16_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
2
+ [2024-06-04 03:33:26] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
3
+ [2024-06-04 03:33:26] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
4
+ [2024-06-04 03:33:26] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
5
+ [2024-06-04 03:33:26] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
6
+ [2024-06-04 03:33:26] INFO config.py:107: Overriding max_batch_size from 1 to 80
7
+ [2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
8
+ [2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
9
+ [2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
10
+ [2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
11
+ [2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
12
+ [2024-06-04 03:33:26] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.model
13
+ [2024-06-04 03:33:26] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/tokenizer.json
14
+ [2024-06-04 03:33:26] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/vocab.json
15
+ [2024-06-04 03:33:26] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/merges.txt
16
+ [2024-06-04 03:33:26] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/added_tokens.json
17
+ [2024-06-04 03:33:26] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/tokenizer_config.json
18
+ [2024-06-04 03:33:26] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
19
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting temperature: 1.0
20
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
21
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
22
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
23
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
24
+ [2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-06-04 03:33:26] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/mlc-chat-config.json
26
+ /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-1.8B-Chat --quantization q4f16_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
27
+ [2024-06-04 03:33:28] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
28
+ [2024-06-04 03:33:29] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-06-04 03:33:30] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-06-04 03:33:32] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:0
32
+ [2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:1
33
+ [2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:2
34
+ [2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:3
35
+ [2024-06-04 03:33:35] INFO auto_device.py:88: Not found device: opencl:0
36
+ [2024-06-04 03:33:35] INFO auto_device.py:35: Using device: cuda:0
37
+ [2024-06-04 03:33:35] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-1.8B-Chat
38
+ [2024-06-04 03:33:35] INFO auto_weight.py:137: Not found Huggingface PyTorch
39
+ [2024-06-04 03:33:35] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json
40
+ [2024-06-04 03:33:35] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json. Use `--source` to override.
41
+ [2024-06-04 03:33:35] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
42
+ [2024-06-04 03:33:35] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
43
+ [2024-06-04 03:33:35] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
44
+ [2024-06-04 03:33:35] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
45
+ Weight conversion with arguments:
46
+ --config /models/Qwen1.5-1.8B-Chat/config.json
47
+ --quantization GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
48
+ --model-type qwen2
49
+ --device cuda:0
50
+ --source /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json
51
+ --source-format huggingface-safetensor
52
+ --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
53
+ Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
54
+
55
  0%| | 0/171 [00:00<?, ?it/s]
56
 
57
+
58
  0%| | 0/171 [00:00<?, ?it/s]
59
 
60
+
61
  0%| | 0/171 [00:05<?, ?it/s]
62
 
63
+
64
  0%| | 0/171 [00:06<?, ?it/s]
65
 
66
+
67
  0%| | 0/171 [00:06<?, ?it/s]
68
  1%| | 1/171 [00:06<18:30, 6.53s/it]
69
 
70
+
71
  1%| | 1/171 [00:08<18:30, 6.53s/it]
72
 
73
+
74
  1%| | 1/171 [00:08<18:30, 6.53s/it]
75
  1%| | 2/171 [00:08<10:46, 3.83s/it]
76
 
77
+
78
  1%| | 2/171 [00:08<10:46, 3.83s/it]
79
 
80
+
81
  1%| | 2/171 [00:08<10:46, 3.83s/it]
82
 
83
+
84
  1%| | 2/171 [00:08<10:46, 3.83s/it]
85
 
86
+
87
  1%| | 2/171 [00:08<10:46, 3.83s/it]
88
  2%|▏ | 4/171 [00:08<04:25, 1.59s/it]
89
 
90
+
91
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
92
 
93
+
94
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
95
 
96
+
97
  2%|▏ | 4/171 [00:09<04:25, 1.59s/it]
98
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
99
 
100
+
101
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
102
 
103
+
104
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
105
 
106
+
107
  3%|▎ | 5/171 [00:09<03:33, 1.28s/it]
108
 
109
+
110
  3%|▎ | 5/171 [00:10<03:33, 1.28s/it]
111
 
112
+
113
  3%|▎ | 5/171 [00:10<03:33, 1.28s/it]
114
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
115
 
116
+
117
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
118
 
119
+
120
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
121
 
122
+
123
  5%|▍ | 8/171 [00:10<01:46, 1.54it/s]
124
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
125
 
126
+
127
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
128
 
129
+
130
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
131
 
132
+
133
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
134
 
135
+
136
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
137
 
138
+
139
  5%|▌ | 9/171 [00:10<01:39, 1.63it/s]
140
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
141
 
142
+
143
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
144
 
145
+
146
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
147
 
148
+
149
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
150
 
151
+
152
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
153
 
154
+
155
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
156
 
157
+
158
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
159
 
160
+
161
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
162
 
163
+
164
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
165
 
166
+
167
  7%|▋ | 12/171 [00:10<00:55, 2.85it/s]
168
  11%|█ | 18/171 [00:10<00:24, 6.26it/s]
169
 
170
+
171
  11%|█ | 18/171 [00:10<00:24, 6.26it/s]
172
 
173
+
174
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
175
 
176
+
177
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
178
 
179
+
180
  11%|█ | 18/171 [00:11<00:24, 6.26it/s]
181
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
182
 
183
+
184
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
185
 
186
+
187
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
188
 
189
+
190
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
191
 
192
+
193
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
194
 
195
+
196
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
197
 
198
+
199
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
200
 
201
+
202
  12%|█▏ | 21/171 [00:11<00:19, 7.84it/s]
203
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
204
 
205
+
206
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
207
 
208
+
209
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
210
 
211
+
212
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
213
 
214
+
215
  15%|█▍ | 25/171 [00:11<00:13, 10.86it/s]
216
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
217
 
218
+
219
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
220
 
221
+
222
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
223
 
224
+
225
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
226
 
227
+
228
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
229
 
230
+
231
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
232
 
233
+
234
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
235
 
236
+
237
  16%|█▋ | 28/171 [00:11<00:11, 12.43it/s]
238
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
239
 
240
+
241
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
242
 
243
+
244
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
245
 
246
+
247
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
248
 
249
+
250
  19%|█▊ | 32/171 [00:11<00:08, 16.03it/s]
251
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
252
 
253
+
254
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
255
 
256
+
257
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
258
 
259
+
260
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
261
 
262
+
263
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
264
 
265
+
266
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
267
 
268
+
269
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
270
 
271
+
272
  20%|██ | 35/171 [00:11<00:08, 16.95it/s]
273
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
274
 
275
+
276
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
277
 
278
+
279
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
280
 
281
+
282
  23%|█��▎ | 39/171 [00:11<00:06, 20.62it/s]
283
 
284
+
285
  23%|██▎ | 39/171 [00:11<00:06, 20.62it/s]
286
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
287
 
288
+
289
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
290
 
291
+
292
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
293
 
294
+
295
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
296
 
297
+
298
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
299
 
300
+
301
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
302
 
303
+
304
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
305
 
306
+
307
  25%|██▍ | 42/171 [00:11<00:06, 20.46it/s]
308
  27%|██▋ | 46/171 [00:11<00:05, 23.87it/s]
309
 
310
+
311
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
312
 
313
+
314
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
315
 
316
+
317
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
318
 
319
+
320
  27%|██▋ | 46/171 [00:12<00:05, 23.87it/s]
321
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
322
 
323
+
324
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
325
 
326
+
327
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
328
 
329
+
330
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
331
 
332
+
333
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
334
 
335
+
336
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
337
 
338
+
339
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
340
 
341
+
342
  29%|██▊ | 49/171 [00:12<00:05, 22.71it/s]
343
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
344
 
345
+
346
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
347
 
348
+
349
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
350
 
351
+
352
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
353
 
354
+
355
  31%|███ | 53/171 [00:12<00:04, 25.82it/s]
356
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
357
 
358
+
359
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
360
 
361
+
362
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
363
 
364
+
365
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
366
 
367
+
368
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
369
 
370
+
371
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
372
 
373
+
374
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
375
 
376
+
377
  33%|███▎ | 56/171 [00:12<00:04, 23.63it/s]
378
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
379
 
380
+
381
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
382
 
383
+
384
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
385
 
386
+
387
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
388
 
389
+
390
  35%|███▌ | 60/171 [00:12<00:04, 26.61it/s]
391
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
392
 
393
+
394
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
395
 
396
+
397
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
398
 
399
+
400
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
401
 
402
+
403
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
404
 
405
+
406
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
407
 
408
+
409
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
410
 
411
+
412
  37%|███▋ | 63/171 [00:12<00:05, 20.36it/s]
413
  39%|███▉ | 67/171 [00:12<00:04, 23.76it/s]
414
 
415
+
416
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
417
 
418
+
419
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
420
 
421
+
422
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
423
 
424
+
425
  39%|███▉ | 67/171 [00:13<00:04, 23.76it/s]
426
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
427
 
428
+
429
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
430
 
431
+
432
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
433
 
434
+
435
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
436
 
437
+
438
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
439
 
440
+
441
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
442
 
443
+
444
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
445
 
446
+
447
  41%|████ | 70/171 [00:13<00:05, 19.28it/s]
448
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
449
 
450
+
451
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
452
 
453
+
454
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
455
 
456
+
457
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
458
 
459
+
460
  43%|████▎ | 74/171 [00:13<00:04, 22.77it/s]
461
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
462
 
463
+
464
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
465
 
466
+
467
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
468
 
469
+
470
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
471
 
472
+
473
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
474
 
475
+
476
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
477
 
478
+
479
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
480
 
481
+
482
  45%|████▌ | 77/171 [00:13<00:05, 17.28it/s]
483
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
484
 
485
+
486
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
487
 
488
+
489
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
490
 
491
+
492
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
493
 
494
+
495
  47%|████▋ | 81/171 [00:13<00:04, 20.87it/s]
496
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
497
 
498
+
499
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
500
 
501
+
502
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
503
 
504
+
505
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
506
 
507
+
508
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
509
 
510
+
511
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
512
 
513
+
514
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
515
 
516
+
517
  49%|████▉ | 84/171 [00:13<00:04, 19.15it/s]
518
  51%|█████▏ | 88/171 [00:13<00:03, 22.66it/s]
519
 
520
+
521
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
522
 
523
+
524
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
525
 
526
+
527
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
528
 
529
+
530
  51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s]
531
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
532
 
533
+
534
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
535
 
536
+
537
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
538
 
539
+
540
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
541
 
542
+
543
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
544
 
545
+
546
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
547
 
548
+
549
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
550
 
551
+
552
  53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s]
553
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
554
 
555
+
556
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
557
 
558
+
559
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
560
 
561
+
562
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
563
 
564
+
565
  56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s]
566
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
567
 
568
+
569
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
570
 
571
+
572
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
573
 
574
+
575
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
576
 
577
+
578
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
579
 
580
+
581
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
582
 
583
+
584
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
585
 
586
+
587
  57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s]
588
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
589
 
590
+
591
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
592
 
593
+
594
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
595
 
596
+
597
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
598
 
599
+
600
  60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s]
601
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
602
 
603
+
604
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
605
 
606
+
607
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
608
 
609
+
610
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
611
 
612
+
613
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
614
 
615
+
616
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
617
 
618
+
619
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
620
 
621
+
622
  61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s]
623
  64%|██████▎ | 109/171 [00:14<00:02, 21.40it/s]
624
 
625
+
626
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
627
 
628
+
629
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
630
 
631
+
632
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
633
 
634
+
635
  64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s]
636
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
637
 
638
+
639
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
640
 
641
+
642
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
643
 
644
+
645
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
646
 
647
+
648
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
649
 
650
+
651
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
652
 
653
+
654
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
655
 
656
+
657
  65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s]
658
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
659
 
660
+
661
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
662
 
663
+
664
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
665
 
666
+
667
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
668
 
669
+
670
  68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s]
671
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
672
 
673
+
674
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
675
 
676
+
677
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
678
 
679
+
680
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
681
 
682
+
683
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
684
 
685
+
686
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
687
 
688
+
689
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
690
 
691
+
692
  70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s]
693
  72%|███████▏ | 123/171 [00:15<00:02, 19.27it/s]
694
 
695
+
696
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
697
 
698
+
699
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
700
 
701
+
702
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
703
 
704
+
705
  72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s]
706
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
707
 
708
+
709
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
710
 
711
+
712
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
713
 
714
+
715
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
716
 
717
+
718
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
719
 
720
+
721
  74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s]
722
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
723
 
724
+
725
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
726
 
727
+
728
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
729
 
730
+
731
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
732
 
733
+
734
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
735
 
736
+
737
  75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s]
738
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
739
 
740
+
741
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
742
 
743
+
744
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
745
 
746
+
747
  77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s]
748
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
749
 
750
+
751
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
752
 
753
+
754
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
755
 
756
+
757
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
758
 
759
+
760
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
761
 
762
+
763
  78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s]
764
 
765
+
766
  78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s]
767
 
768
+
769
  78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s]
770
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
771
 
772
+
773
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
774
 
775
+
776
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
777
 
778
+
779
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
780
 
781
+
782
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
783
 
784
+
785
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
786
 
787
+
788
  81%|████████ | 138/171 [00:17<00:02, 13.00it/s]
789
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
790
 
791
+
792
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
793
 
794
+
795
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
796
 
797
+
798
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
799
 
800
+
801
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
802
 
803
+
804
  83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s]
805
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
806
 
807
+
808
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
809
 
810
+
811
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
812
 
813
+
814
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
815
 
816
+
817
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
818
 
819
+
820
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
821
 
822
+
823
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
824
 
825
+
826
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
827
 
828
+
829
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
830
 
831
+
832
  85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s]
833
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
834
 
835
+
836
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
837
 
838
+
839
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
840
 
841
+
842
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
843
 
844
+
845
  88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s]
846
  90%|█████████ | 154/171 [00:17<00:01, 14.89it/s]
847
 
848
+
849
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
850
 
851
+
852
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
853
 
854
+
855
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
856
 
857
+
858
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
859
 
860
+
861
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
862
 
863
+
864
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
865
 
866
+
867
  90%|█████████ | 154/171 [00:18<00:01, 14.89it/s]
868
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
869
 
870
+
871
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
872
 
873
+
874
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
875
 
876
+
877
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
878
 
879
+
880
  92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s]
881
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
882
 
883
+
884
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
885
 
886
+
887
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
888
 
889
+
890
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
891
 
892
+
893
  94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s]
894
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
895
 
896
+
897
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
898
 
899
+
900
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
901
 
902
+
903
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
904
 
905
+
906
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
907
 
908
+
909
  95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s]
910
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
911
 
912
+
913
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
914
 
915
+
916
  97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s]
917
 
918
+
919
  97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s]
920
 
921
+
922
  97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s]
923
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
924
 
925
+
926
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
927
 
928
+
929
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
930
 
931
+
932
  99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s]
933
+ [2024-06-04 03:33:56] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-1.8B-Chat/model.safetensors
934
+ [2024-06-04 03:33:56] INFO stats.py:77: Time usage: HF loading: 4.272 sec; Pre-quantization mapping: 9.413 sec; Quantization: 2.770 sec
935
+ [2024-06-04 03:33:56] INFO stats.py:91: RAM usage: Peak RAM: 6.843 GB. Total bytes loaded from disk: 6.843 GB
936
+ [2024-06-04 03:33:56] INFO convert_weight.py:155: Parameter size after quantization: 0.963 GB
937
+ [2024-06-04 03:33:56] INFO convert_weight.py:160: Total parameters: 1,836,828,672
938
+ [2024-06-04 03:33:56] INFO convert_weight.py:161: Bits per parameter: 4.502
939
+ [2024-06-04 03:33:56] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
940
+
941
+ All finished, 28 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "qwen2",
4
+ "quantization": "q4f16_1",
5
+ "model_config": {
6
+ "hidden_act": "silu",
7
+ "hidden_size": 2048,
8
+ "intermediate_size": 5504,
9
+ "num_attention_heads": 16,
10
+ "num_hidden_layers": 24,
11
+ "num_key_value_heads": 16,
12
+ "rms_norm_eps": 1e-06,
13
+ "rope_theta": 1000000.0,
14
+ "vocab_size": 151936,
15
+ "context_window_size": 32768,
16
+ "prefill_chunk_size": 2048,
17
+ "tensor_parallel_shards": 1,
18
+ "head_dim": 128,
19
+ "dtype": "float32",
20
+ "max_batch_size": 80
21
+ },
22
+ "vocab_size": 151936,
23
+ "context_window_size": 32768,
24
+ "sliding_window_size": -1,
25
+ "prefill_chunk_size": 2048,
26
+ "attention_sink_size": -1,
27
+ "tensor_parallel_shards": 1,
28
+ "temperature": 1.0,
29
+ "presence_penalty": 0.0,
30
+ "frequency_penalty": 0.0,
31
+ "repetition_penalty": 1.1,
32
+ "top_p": 0.8,
33
+ "tokenizer_files": [
34
+ "tokenizer.json",
35
+ "vocab.json",
36
+ "merges.txt",
37
+ "tokenizer_config.json"
38
+ ],
39
+ "tokenizer_info": {
40
+ "token_postproc_method": "byte_level",
41
+ "prepend_space_in_encode": false,
42
+ "strip_space_in_decode": false
43
+ },
44
+ "conv_template": {
45
+ "name": "chatml",
46
+ "system_template": "<|im_start|>system\n{system_message}",
47
+ "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
48
+ "system_prefix_token_ids": null,
49
+ "add_role_after_system_message": true,
50
+ "roles": {
51
+ "user": "<|im_start|>user",
52
+ "assistant": "<|im_start|>assistant"
53
+ },
54
+ "role_templates": {
55
+ "user": "{user_message}",
56
+ "assistant": "{assistant_message}",
57
+ "tool": "{tool_message}"
58
+ },
59
+ "messages": [],
60
+ "seps": [
61
+ "<|im_end|>\n"
62
+ ],
63
+ "role_content_sep": "\n",
64
+ "role_empty_sep": "\n",
65
+ "stop_str": [
66
+ "<|im_end|>"
67
+ ],
68
+ "stop_token_ids": [
69
+ 2
70
+ ],
71
+ "function_string": "",
72
+ "use_function_calling": false
73
+ },
74
+ "pad_token_id": 151643,
75
+ "bos_token_id": 151643,
76
+ "eos_token_id": [
77
+ 151645,
78
+ 151643
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:fd1b492861cd32161e45b42c370bc202604ad3d4914de99b74ae0c5b5bdd73b9
3
+ size 155582464
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba71642f404e31c7821bb935142fb3b101295fcfdffd947f0d8f1a2c136bc41
3
+ size 155582464
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c51b727b89b74457e87a841cb5abd0d76a7bb212f334a71f52ed284f5bfec92
3
+ size 28479488
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c575e577339dc86e3af82eecfeee32febf6ef8badf0436a9db3edc4c9ee5090
3
+ size 28479488
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a45e11f9e8d29becd96b6e0ad2e270248da6ac029e8af14e7360d697a257d1
3
+ size 28479488
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5ca17b12e6b1ef4e51eca8e3dc311a275550cfe2d9a4f03a17f40ee2ab2bcf
3
+ size 28479488
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f3e314224f0a88726a25d0265928552141f9a3a8021da0f98a524377a72a49
3
+ size 28479488
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44eeacaed25dd74c3e400c4ff3af25d01f8c1bd0b9e8853eb6e74d41203730bc
3
+ size 28479488
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dffcdd86bdd1c124f722c36dd9b5816def620221ba7584b2f63140e12aa7987
3
+ size 28479488
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ea9861c09fb61b62cc8d4a4e874a61faec76e32db4bec16a3decb8ddea535f
3
+ size 28479488
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f11754616b0e94503129911760033d4ea9353c06dcf1d926b64d9e273356f31
3
+ size 28479488
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45c304b41bdb2531740b05a60e3eaa907b15b6bb94f9690692b7f131316571c
3
+ size 28479488
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d28e00d872e03fdca57076746f2440a921e43d383f0174808cb2319cfe5c8f
3
+ size 19447808
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1732ec8dc2adb1b497e3af25e72a7f2956a2b29d598980436948455b5135b0ea
3
+ size 28479488
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b147f82475b45297f198c829098cddf9e81b9d96d73effd295f4573ef3f007
3
+ size 28479488
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455feea485a81cec70f0434a5f0277ab97ff225c06312394da5764b369fa8092
3
+ size 28479488
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587e663ca36237024e933c92b70c06f690f22733134976d79776a5b33602b589
3
+ size 28479488
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019209b6fbed3e7824842ee6d83932fa6d5b8ca077716bfaf9c9a8e290869371
3
+ size 28479488
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68afdcd0c2e1d82c2afef26775f40b8913ac4aa6d4b2de3b8ac4fd2b7328d67
3
+ size 28479488
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbc1ceaa106f186fcb6496da875fd1c68dcf7b10d7caa0bb0612841387ccc2d
3
+ size 28479488
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f17bbe1bb5469f3aa0be308a4cb82387503794a07a1a6e8edec6494c9fab0fc
3
+ size 22138880
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832107ad5e073acb71104edefa71ab794e0e98be3a616d335f49629008129d15
3
+ size 25792512
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3141431b8d9700a9ede0d1a2a35e90d62665caf8e4c442473b9f194c71ae5f
3
+ size 28479488
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7980c3fe56d552213edfd64a8535addfa44cdbe4d4b5aebc24c543bda0da5111
3
+ size 28479488
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9412d22a2ab7486606867b3cb0fc4c98ff76a0f1e1e20efd426da9e11f6994
3
+ size 28479488
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba65b22109ad65b40c7b328ce9eb5c60c5ef572392a8fbce7b63f2358bd4598
3
+ size 28479488
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69460f5a8608038712a9a5b72130b8a18179ffc4229e461b04c05cf1300981d
3
+ size 28479488
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0421fd7114e31ab89b781243f495c8fd53384f26efa014809ad4b02fa4f4dfb6
3
+ size 28479488
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
30
+ "bos_token": null,
31
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
+ "errors": "replace",
35
+ "model_max_length": 32768,
36
+ "pad_token": "<|endoftext|>",
37
+ "split_special_tokens": false,
38
+ "tokenizer_class": "Qwen2Tokenizer",
39
+ "unk_token": null
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff