Hugging Face's logo

mlc-ai
/
Qwen1.5-0.5B-Chat-q3f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Tlopex commited on
Commit
ce9efa6
·
verified ·
1 Parent(s): c3746c7

Initial commit

Browse files
Files changed (14) hide show
  1. logs.txt +335 -0
  2. merges.txt +0 -0
  3. mlc-chat-config.json +77 -0
  4. ndarray-cache.json +0 -0
  5. params_shard_0.bin +3 -0
  6. params_shard_1.bin +3 -0
  7. params_shard_2.bin +3 -0
  8. params_shard_3.bin +3 -0
  9. params_shard_4.bin +3 -0
  10. params_shard_5.bin +3 -0
  11. params_shard_6.bin +3 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +40 -0
  14. vocab.json +0 -0
logs.txt ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/171 [00:00<?, ?it/s]
1
 
 
2
  0%| | 0/171 [00:00<?, ?it/s]
3
 
 
4
  0%| | 0/171 [00:02<?, ?it/s]
5
 
 
6
  0%| | 0/171 [00:03<?, ?it/s]
7
 
 
8
  0%| | 0/171 [00:03<?, ?it/s]
9
  1%| | 1/171 [00:03<10:28, 3.70s/it]
10
 
 
11
  1%| | 1/171 [00:04<10:28, 3.70s/it]
12
 
 
13
  1%| | 1/171 [00:04<10:28, 3.70s/it]
14
  1%| | 2/171 [00:04<05:59, 2.13s/it]
15
 
 
16
  1%| | 2/171 [00:04<05:59, 2.13s/it]
17
 
 
18
  1%| | 2/171 [00:04<05:59, 2.13s/it]
19
 
 
20
  1%| | 2/171 [00:05<05:59, 2.13s/it]
21
 
 
22
  1%| | 2/171 [00:05<05:59, 2.13s/it]
23
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
24
 
 
25
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
26
 
 
27
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
28
 
 
29
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
30
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
31
 
 
32
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
33
 
 
34
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
35
 
 
36
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
37
 
 
38
  3%|▎ | 5/171 [00:06<02:10, 1.27it/s]
39
 
 
40
  3%|▎ | 5/171 [00:06<02:10, 1.27it/s]
41
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
42
 
 
43
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
44
 
 
45
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
46
 
 
47
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
48
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
49
 
 
50
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
51
 
 
52
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
53
 
 
54
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
55
 
 
56
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
57
 
 
58
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
59
 
 
60
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
61
 
 
62
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
63
 
 
64
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
65
 
 
66
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
67
 
 
68
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
69
 
 
70
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
71
 
 
72
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
73
 
 
74
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
75
 
 
76
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
77
 
 
78
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
79
 
 
80
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
81
 
 
82
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
83
 
 
84
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
85
 
 
86
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
87
 
 
88
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
89
 
 
90
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
91
 
 
92
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
93
 
 
94
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
95
 
 
96
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
97
 
 
98
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
99
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
100
 
 
101
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
102
 
 
103
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
104
 
 
105
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
106
 
 
107
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
108
 
 
109
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
110
 
 
111
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
112
 
 
113
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
114
 
 
115
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
116
 
 
117
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
118
 
 
119
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
120
 
 
121
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
122
 
 
123
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
124
 
 
125
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
126
 
 
127
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
128
 
 
129
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
130
 
 
131
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
132
 
 
133
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
134
 
 
135
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
136
 
 
137
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
138
 
 
139
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
140
 
 
141
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
142
 
 
143
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
144
 
 
145
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
146
 
 
147
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
148
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
149
 
 
150
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
151
 
 
152
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
153
 
 
154
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
155
 
 
156
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
157
 
 
158
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
159
 
 
160
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
161
 
 
162
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
163
 
 
164
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
165
 
 
166
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
167
 
 
168
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
169
 
 
170
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
171
 
 
172
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
173
 
 
174
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
175
 
 
176
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
177
 
 
178
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
179
 
 
180
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
181
 
 
182
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
183
 
 
184
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
185
 
 
186
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
187
 
 
188
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
189
 
 
190
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
191
 
 
192
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
193
 
 
194
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
195
 
 
196
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
197
 
 
198
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
199
 
 
200
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
201
 
 
202
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
203
 
 
204
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
205
 
 
206
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
207
 
 
208
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
209
 
 
210
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
211
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
212
 
 
213
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
214
 
 
215
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
216
 
 
217
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
218
 
 
219
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
220
 
 
221
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
222
 
 
223
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
224
 
 
225
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
226
 
 
227
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
228
 
 
229
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
230
 
 
231
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
232
 
 
233
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
234
 
 
235
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
236
 
 
237
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
238
 
 
239
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
240
 
 
241
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
242
 
 
243
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
244
 
 
245
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
246
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
247
 
 
248
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
249
 
 
250
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
251
 
 
252
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
253
 
 
254
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
255
 
 
256
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
257
 
 
258
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
259
 
 
260
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
261
 
 
262
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
263
 
 
264
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
265
 
 
266
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
267
 
 
268
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
269
 
 
270
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
271
 
 
272
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
273
 
 
274
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
275
 
 
276
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
277
 
 
278
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
279
 
 
280
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
281
 
 
282
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
283
 
 
284
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
285
 
 
286
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
287
 
 
288
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
289
 
 
290
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
291
 
 
292
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
293
 
 
294
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
295
 
 
296
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
297
 
 
298
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
299
 
 
300
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
301
 
 
302
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
303
 
 
304
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
305
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
306
 
 
307
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
308
 
 
309
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
310
 
 
311
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
312
 
 
313
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
314
 
 
315
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
316
 
 
317
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
318
 
 
319
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
320
 
 
321
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
322
 
 
323
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
324
 
 
325
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
326
 
 
327
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
328
 
 
329
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
330
 
 
331
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
332
 
 
333
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
334
 
 
335
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
336
 
 
337
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
338
 
 
339
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
340
 
 
341
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
342
 
 
343
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
344
 
 
345
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
346
 
 
347
  52%|█��███▏ | 89/171 [00:07<00:01, 68.94it/s]
348
 
 
349
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
350
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
351
 
 
352
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
353
 
 
354
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
355
 
 
356
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
357
 
 
358
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
359
 
 
360
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
361
 
 
362
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
363
 
 
364
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
365
 
 
366
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
367
 
 
368
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
369
 
 
370
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
371
 
 
372
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
373
 
 
374
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
375
 
 
376
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
377
 
 
378
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
379
 
 
380
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
381
 
 
382
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
383
 
 
384
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
385
 
 
386
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
387
 
 
388
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
389
 
 
390
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
391
 
 
392
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
393
 
 
394
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
395
 
 
396
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
397
 
 
398
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
399
 
 
400
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
401
 
 
402
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
403
 
 
404
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
405
 
 
406
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
407
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
408
 
 
409
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
410
 
 
411
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
412
 
 
413
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
414
 
 
415
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
416
 
 
417
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
418
 
 
419
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
420
 
 
421
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
422
 
 
423
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
424
 
 
425
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
426
 
 
427
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
428
 
 
429
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
430
 
 
431
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
432
 
 
433
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
434
 
 
435
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
436
 
 
437
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
438
 
 
439
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
440
 
 
441
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
442
 
 
443
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
444
 
 
445
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
446
 
 
447
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
448
 
 
449
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
450
 
 
451
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
452
 
 
453
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
454
 
 
455
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
456
 
 
457
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
458
 
 
459
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
460
 
 
461
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
462
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
463
 
 
464
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
465
 
 
466
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
467
 
 
468
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
469
 
 
470
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
471
 
 
472
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
473
 
 
474
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
475
 
 
476
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
477
 
 
478
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
479
 
 
480
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
481
 
 
482
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
483
 
 
484
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
485
 
 
486
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
487
 
 
488
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
489
 
 
490
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
491
 
 
492
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
493
 
 
494
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
495
 
 
496
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
497
 
 
498
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
499
 
 
500
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
501
 
 
502
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
503
 
 
504
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
505
 
 
506
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
507
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
508
 
 
509
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
510
 
 
511
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
512
 
 
513
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
514
 
 
515
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
516
 
 
517
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
518
 
 
519
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
520
 
 
521
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
522
 
 
523
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
524
 
 
525
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
526
 
 
527
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
528
 
 
529
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
530
 
 
531
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
532
 
 
533
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
534
 
 
535
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
536
 
 
537
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
538
 
 
539
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
540
 
 
541
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
542
 
 
543
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
544
 
 
545
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
546
 
 
547
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
548
 
 
549
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
550
 
 
551
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
552
 
 
553
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
554
 
 
555
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
556
 
 
557
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
558
 
 
559
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
560
 
 
561
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
562
 
 
563
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
564
 
 
565
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
 
 
 
 
 
 
 
 
 
 
1
+ /usr/bin/python3 -m mlc_llm gen_config dist/models/Qwen1.5-0.5B-Chat --quantization q3f16_1 --conv-template chatml --output /tmp/tmpycunqk51 --context-window-size 32768
2
+ [2024-05-30 00:06:46] INFO auto_config.py:115: Found model configuration: dist/models/Qwen1.5-0.5B-Chat/config.json
3
+ [2024-05-30 00:06:46] INFO auto_config.py:153: Found model type: qwen2. Use `--model-type` to override.
4
+ [2024-05-30 00:06:46] INFO qwen2_model.py:48: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
5
+ [2024-05-30 00:06:46] INFO qwen2_model.py:65: prefill_chunk_size defaults to 2048
6
+ [2024-05-30 00:06:46] INFO config.py:106: Overriding context_window_size from 32768 to 32768
7
+ [2024-05-30 00:06:46] WARNING config.py:99: Warning: Cannot override max_batch_size, because QWen2Config does not have this field
8
+ [2024-05-30 00:06:46] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 151643
9
+ [2024-05-30 00:06:46] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 151643
10
+ [2024-05-30 00:06:46] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [151645, 151643]
11
+ [2024-05-30 00:06:46] INFO gen_config.py:255: [generation_config.json] Setting repetition_penalty: 1.1
12
+ [2024-05-30 00:06:46] INFO gen_config.py:255: [generation_config.json] Setting top_p: 0.8
13
+ [2024-05-30 00:06:46] INFO gen_config.py:269: Not found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer.model
14
+ [2024-05-30 00:06:46] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer.json. Copying to /tmp/tmpycunqk51/tokenizer.json
15
+ [2024-05-30 00:06:46] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/vocab.json. Copying to /tmp/tmpycunqk51/vocab.json
16
+ [2024-05-30 00:06:46] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/merges.txt. Copying to /tmp/tmpycunqk51/merges.txt
17
+ [2024-05-30 00:06:46] INFO gen_config.py:269: Not found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/added_tokens.json
18
+ [2024-05-30 00:06:46] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer_config.json. Copying to /tmp/tmpycunqk51/tokenizer_config.json
19
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting temperature: 0.7
20
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
21
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
22
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
23
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
24
+ [2024-05-30 00:06:46] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-05-30 00:06:46] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpycunqk51/mlc-chat-config.json
26
+ /usr/bin/python3 -m mlc_llm convert_weight dist/models/Qwen1.5-0.5B-Chat --quantization q3f16_1 --source-format auto --output /tmp/tmpycunqk51
27
+ [2024-05-30 00:06:47] INFO auto_config.py:115: Found model configuration: dist/models/Qwen1.5-0.5B-Chat/config.json
28
+ [2024-05-30 00:06:49] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-05-30 00:06:51] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-05-30 00:06:52] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-05-30 00:06:52] INFO auto_device.py:88: Not found device: vulkan:0
32
+ [2024-05-30 00:06:53] INFO auto_device.py:88: Not found device: opencl:0
33
+ [2024-05-30 00:06:53] INFO auto_device.py:35: Using device: cuda:0
34
+ [2024-05-30 00:06:53] INFO auto_weight.py:70: Finding weights in: dist/models/Qwen1.5-0.5B-Chat
35
+ [2024-05-30 00:06:53] INFO auto_weight.py:136: Not found Huggingface PyTorch
36
+ [2024-05-30 00:06:53] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: dist/models/Qwen1.5-0.5B-Chat/model.safetensors.index.json
37
+ [2024-05-30 00:06:53] INFO auto_weight.py:106: Using source weight configuration: dist/models/Qwen1.5-0.5B-Chat/model.safetensors.index.json. Use `--source` to override.
38
+ [2024-05-30 00:06:53] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
39
+ [2024-05-30 00:06:53] INFO auto_config.py:153: Found model type: qwen2. Use `--model-type` to override.
40
+ [2024-05-30 00:06:53] INFO qwen2_model.py:48: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
41
+ [2024-05-30 00:06:53] INFO qwen2_model.py:65: prefill_chunk_size defaults to 2048
42
+ Weight conversion with arguments:
43
+ --config dist/models/Qwen1.5-0.5B-Chat/config.json
44
+ --quantization GroupQuantize(name='q3f16_1', kind='group-quant', group_size=40, quantize_dtype='int3', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=10, num_storage_per_group=4, max_int_value=3)
45
+ --model-type qwen2
46
+ --device cuda:0
47
+ --source dist/models/Qwen1.5-0.5B-Chat/model.safetensors.index.json
48
+ --source-format huggingface-safetensor
49
+ --output /tmp/tmpycunqk51
50
+ Start storing to cache /tmp/tmpycunqk51
51
+
52
  0%| | 0/171 [00:00<?, ?it/s]
53
 
54
+
55
  0%| | 0/171 [00:00<?, ?it/s]
56
 
57
+
58
  0%| | 0/171 [00:02<?, ?it/s]
59
 
60
+
61
  0%| | 0/171 [00:03<?, ?it/s]
62
 
63
+
64
  0%| | 0/171 [00:03<?, ?it/s]
65
  1%| | 1/171 [00:03<10:28, 3.70s/it]
66
 
67
+
68
  1%| | 1/171 [00:04<10:28, 3.70s/it]
69
 
70
+
71
  1%| | 1/171 [00:04<10:28, 3.70s/it]
72
  1%| | 2/171 [00:04<05:59, 2.13s/it]
73
 
74
+
75
  1%| | 2/171 [00:04<05:59, 2.13s/it]
76
 
77
+
78
  1%| | 2/171 [00:04<05:59, 2.13s/it]
79
 
80
+
81
  1%| | 2/171 [00:05<05:59, 2.13s/it]
82
 
83
+
84
  1%| | 2/171 [00:05<05:59, 2.13s/it]
85
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
86
 
87
+
88
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
89
 
90
+
91
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
92
 
93
+
94
  2%|▏ | 4/171 [00:05<02:35, 1.07it/s]
95
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
96
 
97
+
98
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
99
 
100
+
101
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
102
 
103
+
104
  3%|▎ | 5/171 [00:05<02:10, 1.27it/s]
105
 
106
+
107
  3%|▎ | 5/171 [00:06<02:10, 1.27it/s]
108
 
109
+
110
  3%|▎ | 5/171 [00:06<02:10, 1.27it/s]
111
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
112
 
113
+
114
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
115
 
116
+
117
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
118
 
119
+
120
  5%|▍ | 8/171 [00:06<01:08, 2.39it/s]
121
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
122
 
123
+
124
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
125
 
126
+
127
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
128
 
129
+
130
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
131
 
132
+
133
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
134
 
135
+
136
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
137
 
138
+
139
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
140
 
141
+
142
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
143
 
144
+
145
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
146
 
147
+
148
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
149
 
150
+
151
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
152
 
153
+
154
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
155
 
156
+
157
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
158
 
159
+
160
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
161
 
162
+
163
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
164
 
165
+
166
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
167
 
168
+
169
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
170
 
171
+
172
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
173
 
174
+
175
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
176
 
177
+
178
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
179
 
180
+
181
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
182
 
183
+
184
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
185
 
186
+
187
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
188
 
189
+
190
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
191
 
192
+
193
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
194
 
195
+
196
  5%|▌ | 9/171 [00:06<01:05, 2.46it/s]
197
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
198
 
199
+
200
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
201
 
202
+
203
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
204
 
205
+
206
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
207
 
208
+
209
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
210
 
211
+
212
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
213
 
214
+
215
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
216
 
217
+
218
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
219
 
220
+
221
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
222
 
223
+
224
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
225
 
226
+
227
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
228
 
229
+
230
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
231
 
232
+
233
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
234
 
235
+
236
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
237
 
238
+
239
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
240
 
241
+
242
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
243
 
244
+
245
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
246
 
247
+
248
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
249
 
250
+
251
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
252
 
253
+
254
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
255
 
256
+
257
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
258
 
259
+
260
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
261
 
262
+
263
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
264
 
265
+
266
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
267
 
268
+
269
  15%|█▍ | 25/171 [00:06<00:11, 12.92it/s]
270
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
271
 
272
+
273
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
274
 
275
+
276
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
277
 
278
+
279
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
280
 
281
+
282
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
283
 
284
+
285
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
286
 
287
+
288
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
289
 
290
+
291
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
292
 
293
+
294
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
295
 
296
+
297
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
298
 
299
+
300
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
301
 
302
+
303
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
304
 
305
+
306
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
307
 
308
+
309
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
310
 
311
+
312
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
313
 
314
+
315
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
316
 
317
+
318
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
319
 
320
+
321
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
322
 
323
+
324
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
325
 
326
+
327
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
328
 
329
+
330
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
331
 
332
+
333
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
334
 
335
+
336
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
337
 
338
+
339
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
340
 
341
+
342
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
343
 
344
+
345
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
346
 
347
+
348
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
349
 
350
+
351
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
352
 
353
+
354
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
355
 
356
+
357
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
358
 
359
+
360
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
361
 
362
+
363
  23%|██▎ | 40/171 [00:06<00:05, 24.83it/s]
364
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
365
 
366
+
367
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
368
 
369
+
370
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
371
 
372
+
373
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
374
 
375
+
376
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
377
 
378
+
379
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
380
 
381
+
382
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
383
 
384
+
385
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
386
 
387
+
388
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
389
 
390
+
391
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
392
 
393
+
394
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
395
 
396
+
397
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
398
 
399
+
400
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
401
 
402
+
403
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
404
 
405
+
406
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
407
 
408
+
409
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
410
 
411
+
412
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
413
 
414
+
415
  35%|███▌ | 60/171 [00:06<00:02, 43.85it/s]
416
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
417
 
418
+
419
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
420
 
421
+
422
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
423
 
424
+
425
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
426
 
427
+
428
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
429
 
430
+
431
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
432
 
433
+
434
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
435
 
436
+
437
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
438
 
439
+
440
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
441
 
442
+
443
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
444
 
445
+
446
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
447
 
448
+
449
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
450
 
451
+
452
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
453
 
454
+
455
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
456
 
457
+
458
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
459
 
460
+
461
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
462
 
463
+
464
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
465
 
466
+
467
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
468
 
469
+
470
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
471
 
472
+
473
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
474
 
475
+
476
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
477
 
478
+
479
  42%|████▏ | 71/171 [00:06<00:01, 50.36it/s]
480
 
481
+
482
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
483
 
484
+
485
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
486
 
487
+
488
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
489
 
490
+
491
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
492
 
493
+
494
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
495
 
496
+
497
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
498
 
499
+
500
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
501
 
502
+
503
  42%|████▏ | 71/171 [00:07<00:01, 50.36it/s]
504
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
505
 
506
+
507
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
508
 
509
+
510
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
511
 
512
+
513
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
514
 
515
+
516
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
517
 
518
+
519
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
520
 
521
+
522
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
523
 
524
+
525
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
526
 
527
+
528
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
529
 
530
+
531
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
532
 
533
+
534
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
535
 
536
+
537
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
538
 
539
+
540
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
541
 
542
+
543
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
544
 
545
+
546
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
547
 
548
+
549
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
550
 
551
+
552
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
553
 
554
+
555
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
556
 
557
+
558
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
559
 
560
+
561
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
562
 
563
+
564
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
565
 
566
+
567
  52%|█��███▏ | 89/171 [00:07<00:01, 68.94it/s]
568
 
569
+
570
  52%|█████▏ | 89/171 [00:07<00:01, 68.94it/s]
571
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
572
 
573
+
574
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
575
 
576
+
577
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
578
 
579
+
580
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
581
 
582
+
583
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
584
 
585
+
586
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
587
 
588
+
589
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
590
 
591
+
592
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
593
 
594
+
595
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
596
 
597
+
598
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
599
 
600
+
601
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
602
 
603
+
604
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
605
 
606
+
607
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
608
 
609
+
610
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
611
 
612
+
613
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
614
 
615
+
616
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
617
 
618
+
619
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
620
 
621
+
622
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
623
 
624
+
625
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
626
 
627
+
628
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
629
 
630
+
631
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
632
 
633
+
634
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
635
 
636
+
637
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
638
 
639
+
640
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
641
 
642
+
643
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
644
 
645
+
646
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
647
 
648
+
649
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
650
 
651
+
652
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
653
 
654
+
655
  60%|██████ | 103/171 [00:07<00:00, 75.99it/s]
656
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
657
 
658
+
659
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
660
 
661
+
662
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
663
 
664
+
665
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
666
 
667
+
668
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
669
 
670
+
671
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
672
 
673
+
674
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
675
 
676
+
677
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
678
 
679
+
680
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
681
 
682
+
683
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
684
 
685
+
686
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
687
 
688
+
689
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
690
 
691
+
692
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
693
 
694
+
695
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
696
 
697
+
698
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
699
 
700
+
701
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
702
 
703
+
704
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
705
 
706
+
707
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
708
 
709
+
710
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
711
 
712
+
713
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
714
 
715
+
716
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
717
 
718
+
719
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
720
 
721
+
722
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
723
 
724
+
725
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
726
 
727
+
728
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
729
 
730
+
731
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
732
 
733
+
734
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
735
 
736
+
737
  71%|███████ | 121/171 [00:07<00:00, 95.61it/s]
738
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
739
 
740
+
741
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
742
 
743
+
744
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
745
 
746
+
747
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
748
 
749
+
750
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
751
 
752
+
753
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
754
 
755
+
756
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
757
 
758
+
759
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
760
 
761
+
762
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
763
 
764
+
765
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
766
 
767
+
768
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
769
 
770
+
771
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
772
 
773
+
774
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
775
 
776
+
777
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
778
 
779
+
780
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
781
 
782
+
783
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
784
 
785
+
786
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
787
 
788
+
789
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
790
 
791
+
792
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
793
 
794
+
795
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
796
 
797
+
798
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
799
 
800
+
801
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
802
 
803
+
804
  81%|████████ | 138/171 [00:07<00:00, 109.14it/s]
805
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
806
 
807
+
808
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
809
 
810
+
811
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
812
 
813
+
814
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
815
 
816
+
817
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
818
 
819
+
820
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
821
 
822
+
823
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
824
 
825
+
826
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
827
 
828
+
829
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
830
 
831
+
832
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
833
 
834
+
835
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
836
 
837
+
838
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
839
 
840
+
841
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
842
 
843
+
844
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
845
 
846
+
847
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
848
 
849
+
850
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
851
 
852
+
853
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
854
 
855
+
856
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
857
 
858
+
859
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
860
 
861
+
862
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
863
 
864
+
865
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
866
 
867
+
868
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
869
 
870
+
871
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
872
 
873
+
874
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
875
 
876
+
877
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
878
 
879
+
880
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
881
 
882
+
883
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
884
 
885
+
886
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
887
 
888
+
889
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
890
 
891
+
892
  89%|████████▉ | 152/171 [00:07<00:00, 104.82it/s]
893
+ [2024-05-30 00:07:03] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/Qwen1.5-0.5B-Chat/model.safetensors
894
+ [2024-05-30 00:07:04] INFO stats.py:76: Time usage: HF loading: 1.324 sec; Pre-quantization mapping: 2.112 sec; Quantization: 3.070 sec
895
+ [2024-05-30 00:07:04] INFO stats.py:90: RAM usage: Peak RAM: 2.308 GB. Total bytes loaded from disk: 2.308 GB
896
+ [2024-05-30 00:07:04] INFO convert_weight.py:155: Parameter size after quantization: 0.264 GB
897
+ [2024-05-30 00:07:04] INFO convert_weight.py:160: Total parameters: 619,570,176
898
+ [2024-05-30 00:07:04] INFO convert_weight.py:161: Bits per parameter: 3.656
899
+ [2024-05-30 00:07:04] INFO convert_weight.py:166: Saved to directory: /tmp/tmpycunqk51
900
+
901
+ All finished, 7 total shards committed, record saved to /tmp/tmpycunqk51/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 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "qwen2",
3
+ "quantization": "q3f16_1",
4
+ "model_config": {
5
+ "hidden_act": "silu",
6
+ "hidden_size": 1024,
7
+ "intermediate_size": 2816,
8
+ "num_attention_heads": 16,
9
+ "num_hidden_layers": 24,
10
+ "num_key_value_heads": 16,
11
+ "rms_norm_eps": 1e-06,
12
+ "rope_theta": 1000000.0,
13
+ "vocab_size": 151936,
14
+ "context_window_size": 32768,
15
+ "prefill_chunk_size": 2048,
16
+ "tensor_parallel_shards": 1,
17
+ "head_dim": 64,
18
+ "dtype": "float32"
19
+ },
20
+ "vocab_size": 151936,
21
+ "context_window_size": 32768,
22
+ "sliding_window_size": -1,
23
+ "prefill_chunk_size": 2048,
24
+ "attention_sink_size": -1,
25
+ "tensor_parallel_shards": 1,
26
+ "mean_gen_len": 128,
27
+ "max_gen_len": 512,
28
+ "shift_fill_factor": 0.3,
29
+ "temperature": 0.7,
30
+ "presence_penalty": 0.0,
31
+ "frequency_penalty": 0.0,
32
+ "repetition_penalty": 1.1,
33
+ "top_p": 0.8,
34
+ "conv_template": {
35
+ "name": "chatml",
36
+ "system_template": "<|im_start|>system\n{system_message}",
37
+ "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
38
+ "add_role_after_system_message": true,
39
+ "roles": {
40
+ "user": "<|im_start|>user",
41
+ "assistant": "<|im_start|>assistant"
42
+ },
43
+ "role_templates": {
44
+ "user": "{user_message}",
45
+ "assistant": "{assistant_message}",
46
+ "tool": "{tool_message}"
47
+ },
48
+ "messages": [],
49
+ "seps": [
50
+ "<|im_end|>\n"
51
+ ],
52
+ "role_content_sep": "\n",
53
+ "role_empty_sep": "\n",
54
+ "stop_str": [
55
+ "<|im_end|>"
56
+ ],
57
+ "stop_token_ids": [
58
+ 2
59
+ ],
60
+ "function_string": "",
61
+ "use_function_calling": false
62
+ },
63
+ "pad_token_id": 151643,
64
+ "bos_token_id": 151643,
65
+ "eos_token_id": [
66
+ 151645,
67
+ 151643
68
+ ],
69
+ "tokenizer_files": [
70
+ "tokenizer.json",
71
+ "vocab.json",
72
+ "merges.txt",
73
+ "tokenizer_config.json"
74
+ ],
75
+ "token_table_postproc_method": "byte_level",
76
+ "version": "0.1.0"
77
+ }
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 sha256:26db7b2c999c7cd3d5ac651183b640b977f3c0f36fefa10ccbd5ea173ced5027
3
+ size 63205376
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26db7b2c999c7cd3d5ac651183b640b977f3c0f36fefa10ccbd5ea173ced5027
3
+ size 63205376
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081021d6cea24aaa37932a765052db1e6549930fd87f82b11cef6a7bec883c8d
3
+ size 33418240
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242d39f620b0ba6d87988841b31a2bcdc9e1f99a5189d0d5f41b37065a6e7a4f
3
+ size 33310720
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8712d402b12c3a49f04b58c7e68f6a4635bb101e7b276711207df4a4863aabb2
3
+ size 32585728
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cecb856e60906a6af2bf7557e9d5ad507c15cef2fda01f7bf14e65aa8d466215
3
+ size 33439744
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec93f26346a790c0a2c13c931a19481b324a182c824696ccc83659b1634259ef
3
+ size 23967744
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