Hugging Face's logo

mlc-ai
/
Qwen1.5-0.5B-Chat-q4f32_1-MLC

MLC-LLM
web-llm
Model card Files Community
riczhou commited on
Commit
ac8c7ff
·
verified ·
1 Parent(s): d4ee7e6

Initial commit

Browse files
Files changed (16) hide show
  1. logs.txt +339 -0
  2. merges.txt +0 -0
  3. mlc-chat-config.json +83 -0
  4. ndarray-cache-b16.json +0 -0
  5. ndarray-cache.json +0 -0
  6. params_shard_0.bin +3 -0
  7. params_shard_1.bin +3 -0
  8. params_shard_2.bin +3 -0
  9. params_shard_3.bin +3 -0
  10. params_shard_4.bin +3 -0
  11. params_shard_5.bin +3 -0
  12. params_shard_6.bin +3 -0
  13. params_shard_7.bin +3 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +40 -0
  16. vocab.json +0 -0
logs.txt ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 [00:02<?, ?it/s]
7
 
 
8
  0%| | 0/171 [00:03<?, ?it/s]
9
  1%| | 1/171 [00:03<09:04, 3.20s/it]
10
 
 
11
  1%| | 1/171 [00:03<09:04, 3.20s/it]
12
 
 
13
  1%| | 1/171 [00:03<09:04, 3.20s/it]
14
  1%| | 2/171 [00:03<04:24, 1.56s/it]
15
 
 
16
  1%| | 2/171 [00:03<04:24, 1.56s/it]
17
 
 
18
  1%| | 2/171 [00:03<04:24, 1.56s/it]
19
 
 
20
  1%| | 2/171 [00:04<04:24, 1.56s/it]
21
 
 
22
  1%| | 2/171 [00:04<04:24, 1.56s/it]
23
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
24
 
 
25
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
26
 
 
27
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
28
 
 
29
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
30
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
31
 
 
32
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
33
 
 
34
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
35
 
 
36
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
37
 
 
38
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
39
 
 
40
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
41
  5%|▍ | 8/171 [00:04<00:57, 2.84it/s]
42
 
 
43
  5%|▍ | 8/171 [00:04<00:57, 2.84it/s]
44
 
 
45
  5%|▍ | 8/171 [00:05<00:57, 2.84it/s]
46
 
 
47
  5%|▍ | 8/171 [00:05<00:57, 2.84it/s]
48
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
49
 
 
50
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
51
 
 
52
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
53
 
 
54
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
55
 
 
56
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
57
 
 
58
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
59
 
 
60
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
61
 
 
62
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
63
 
 
64
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
65
 
 
66
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
67
 
 
68
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
69
 
 
70
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
71
 
 
72
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
73
 
 
74
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
75
 
 
76
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
77
 
 
78
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
79
 
 
80
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
81
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
82
 
 
83
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
84
 
 
85
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
86
 
 
87
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
88
 
 
89
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
90
 
 
91
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
92
 
 
93
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
94
 
 
95
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
96
 
 
97
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
98
 
 
99
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
100
 
 
101
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
102
 
 
103
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
104
 
 
105
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
106
 
 
107
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
108
 
 
109
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
110
 
 
111
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
112
 
 
113
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
114
 
 
115
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
116
 
 
117
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
118
 
 
119
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
120
 
 
121
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
122
 
 
123
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
124
 
 
125
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
126
 
 
127
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
128
 
 
129
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
130
 
 
131
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
132
 
 
133
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
134
 
 
135
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
136
 
 
137
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
138
 
 
139
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
140
 
 
141
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
142
 
 
143
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
144
 
 
145
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
146
 
 
147
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
148
 
 
149
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
150
 
 
151
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
152
 
 
153
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
154
 
 
155
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
156
 
 
157
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
158
 
 
159
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
160
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
161
 
 
162
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
163
 
 
164
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
165
 
 
166
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
167
 
 
168
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
169
 
 
170
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
171
 
 
172
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
173
 
 
174
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
175
 
 
176
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
177
 
 
178
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
179
 
 
180
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
181
 
 
182
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
183
 
 
184
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
185
 
 
186
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
187
 
 
188
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
189
 
 
190
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
191
 
 
192
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
193
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
194
 
 
195
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
196
 
 
197
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
198
 
 
199
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
200
 
 
201
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
202
 
 
203
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
204
 
 
205
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
206
 
 
207
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
208
 
 
209
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
210
 
 
211
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
212
 
 
213
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
214
 
 
215
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
216
 
 
217
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
218
 
 
219
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
220
 
 
221
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
222
 
 
223
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
224
 
 
225
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
226
 
 
227
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
228
 
 
229
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
230
 
 
231
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
232
 
 
233
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
234
 
 
235
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
236
 
 
237
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
238
 
 
239
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
240
 
 
241
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
242
 
 
243
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
244
 
 
245
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
246
 
 
247
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
248
 
 
249
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
250
 
 
251
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
252
 
 
253
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
254
 
 
255
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
256
 
 
257
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
258
 
 
259
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
260
 
 
261
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
262
 
 
263
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
264
 
 
265
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
266
 
 
267
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
268
  46%|███���▌ | 78/171 [00:05<00:01, 62.38it/s]
269
 
 
270
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
271
 
 
272
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
273
 
 
274
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
275
 
 
276
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
277
 
 
278
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
279
 
 
280
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
281
 
 
282
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
283
 
 
284
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
285
 
 
286
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
287
 
 
288
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
289
 
 
290
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
291
 
 
292
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
293
 
 
294
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
295
 
 
296
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
297
 
 
298
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
299
 
 
300
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
301
 
 
302
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
303
 
 
304
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
305
 
 
306
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
307
 
 
308
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
309
 
 
310
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
311
 
 
312
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
313
 
 
314
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
315
 
 
316
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
317
 
 
318
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
319
 
 
320
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
321
 
 
322
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
323
 
 
324
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
325
 
 
326
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
327
 
 
328
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
329
 
 
330
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
331
 
 
332
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
333
 
 
334
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
335
 
 
336
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
337
 
 
338
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
339
 
 
340
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
341
 
 
342
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
343
 
 
344
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
345
 
 
346
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
347
 
 
348
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
349
 
 
350
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
351
 
 
352
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
353
 
 
354
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
355
 
 
356
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
357
 
 
358
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
359
 
 
360
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
361
 
 
362
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
363
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
364
 
 
365
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
366
 
 
367
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
368
 
 
369
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
370
 
 
371
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
372
 
 
373
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
374
 
 
375
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
376
 
 
377
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
378
 
 
379
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
380
 
 
381
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
382
 
 
383
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
384
 
 
385
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
386
 
 
387
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
388
 
 
389
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
390
 
 
391
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
392
 
 
393
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
394
 
 
395
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
396
 
 
397
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
398
 
 
399
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
400
 
 
401
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
402
 
 
403
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
404
 
 
405
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
406
 
 
407
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
408
 
 
409
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
410
 
 
411
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
412
 
 
413
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
414
 
 
415
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
416
 
 
417
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
418
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
419
 
 
420
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
421
 
 
422
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
423
 
 
424
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
425
 
 
426
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
427
 
 
428
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
429
 
 
430
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
431
 
 
432
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
433
 
 
434
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
435
 
 
436
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
437
 
 
438
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
439
 
 
440
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
441
 
 
442
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
443
 
 
444
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
445
 
 
446
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
447
 
 
448
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
449
 
 
450
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
451
 
 
452
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
453
 
 
454
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
455
 
 
456
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
457
 
 
458
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
459
 
 
460
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
461
 
 
462
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
463
 
 
464
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
465
 
 
466
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
467
 
 
468
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
469
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
470
 
 
471
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
472
 
 
473
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
474
 
 
475
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
476
 
 
477
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
478
 
 
479
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
480
 
 
481
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
482
 
 
483
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
484
 
 
485
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
486
 
 
487
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
488
 
 
489
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
490
 
 
491
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
492
 
 
493
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
494
 
 
495
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
496
 
 
497
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
498
 
 
499
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
500
 
 
501
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
502
 
 
503
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
504
 
 
505
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
506
 
 
507
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
508
 
 
509
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
510
 
 
511
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
512
 
 
513
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
514
 
 
515
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
516
 
 
517
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
518
 
 
519
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
520
 
 
521
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
522
 
 
523
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
524
 
 
525
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
526
 
 
527
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
528
 
 
529
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
530
 
 
531
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
532
 
 
533
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
534
 
 
535
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
536
 
 
537
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
538
 
 
539
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
540
 
 
541
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
542
 
 
543
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
544
 
 
545
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
546
 
 
547
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
548
 
 
549
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
550
 
 
551
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
552
 
 
553
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
554
 
 
555
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
556
 
 
557
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
558
 
 
559
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
560
 
 
561
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
562
  99%|█████████▉| 170/171 [00:06<00:00, 150.62it/s]
563
 
 
564
  99%|█████████▉| 170/171 [00:06<00:00, 150.62it/s]
 
 
 
 
 
 
 
 
 
 
 
1
+ /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-0.5B-Chat --quantization q4f32_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC
2
+ [2024-06-04 03:31:01] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-0.5B-Chat/config.json
3
+ [2024-06-04 03:31:01] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
4
+ [2024-06-04 03:31:01] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
5
+ [2024-06-04 03:31:01] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
6
+ [2024-06-04 03:31:01] INFO config.py:107: Overriding max_batch_size from 1 to 80
7
+ [2024-06-04 03:31:01] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
8
+ [2024-06-04 03:31:01] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
9
+ [2024-06-04 03:31:01] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
10
+ [2024-06-04 03:31:01] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
11
+ [2024-06-04 03:31:01] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
12
+ [2024-06-04 03:31:01] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer.model
13
+ [2024-06-04 03:31:01] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/tokenizer.json
14
+ [2024-06-04 03:31:01] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/vocab.json
15
+ [2024-06-04 03:31:01] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/merges.txt
16
+ [2024-06-04 03:31:01] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-0.5B-Chat/added_tokens.json
17
+ [2024-06-04 03:31:01] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/tokenizer_config.json
18
+ [2024-06-04 03:31:01] 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 03:31:01] INFO gen_config.py:32: [System default] Setting temperature: 1.0
20
+ [2024-06-04 03:31:01] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
21
+ [2024-06-04 03:31:01] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
22
+ [2024-06-04 03:31:01] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
23
+ [2024-06-04 03:31:01] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
24
+ [2024-06-04 03:31:01] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-06-04 03:31:01] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/mlc-chat-config.json
26
+ /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-0.5B-Chat --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC
27
+ [2024-06-04 03:31:03] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-0.5B-Chat/config.json
28
+ [2024-06-04 03:31:04] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-06-04 03:31:06] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-06-04 03:31:07] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-06-04 03:31:09] INFO auto_device.py:79: Found device: vulkan:0
32
+ [2024-06-04 03:31:09] INFO auto_device.py:79: Found device: vulkan:1
33
+ [2024-06-04 03:31:09] INFO auto_device.py:79: Found device: vulkan:2
34
+ [2024-06-04 03:31:09] INFO auto_device.py:79: Found device: vulkan:3
35
+ [2024-06-04 03:31:10] INFO auto_device.py:88: Not found device: opencl:0
36
+ [2024-06-04 03:31:10] INFO auto_device.py:35: Using device: cuda:0
37
+ [2024-06-04 03:31:10] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-0.5B-Chat
38
+ [2024-06-04 03:31:10] INFO auto_weight.py:137: Not found Huggingface PyTorch
39
+ [2024-06-04 03:31:11] INFO auto_weight.py:161: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen1.5-0.5B-Chat/model.safetensors.index.json
40
+ [2024-06-04 03:31:11] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen1.5-0.5B-Chat/model.safetensors.index.json. Use `--source` to override.
41
+ [2024-06-04 03:31:11] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
42
+ [2024-06-04 03:31:11] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
43
+ [2024-06-04 03:31:11] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
44
+ [2024-06-04 03:31:11] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
45
+ Weight conversion with arguments:
46
+ --config /models/Qwen1.5-0.5B-Chat/config.json
47
+ --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', 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/Qwen1.5-0.5B-Chat/model.safetensors.index.json
51
+ --source-format huggingface-safetensor
52
+ --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC
53
+ Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_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 [00:02<?, ?it/s]
62
 
63
+
64
  0%| | 0/171 [00:02<?, ?it/s]
65
 
66
+
67
  0%| | 0/171 [00:03<?, ?it/s]
68
  1%| | 1/171 [00:03<09:04, 3.20s/it]
69
 
70
+
71
  1%| | 1/171 [00:03<09:04, 3.20s/it]
72
 
73
+
74
  1%| | 1/171 [00:03<09:04, 3.20s/it]
75
  1%| | 2/171 [00:03<04:24, 1.56s/it]
76
 
77
+
78
  1%| | 2/171 [00:03<04:24, 1.56s/it]
79
 
80
+
81
  1%| | 2/171 [00:03<04:24, 1.56s/it]
82
 
83
+
84
  1%| | 2/171 [00:04<04:24, 1.56s/it]
85
 
86
+
87
  1%| | 2/171 [00:04<04:24, 1.56s/it]
88
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
89
 
90
+
91
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
92
 
93
+
94
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
95
 
96
+
97
  2%|▏ | 4/171 [00:04<02:01, 1.38it/s]
98
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
99
 
100
+
101
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
102
 
103
+
104
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
105
 
106
+
107
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
108
 
109
+
110
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
111
 
112
+
113
  3%|▎ | 5/171 [00:04<01:44, 1.58it/s]
114
  5%|▍ | 8/171 [00:04<00:57, 2.84it/s]
115
 
116
+
117
  5%|▍ | 8/171 [00:04<00:57, 2.84it/s]
118
 
119
+
120
  5%|▍ | 8/171 [00:05<00:57, 2.84it/s]
121
 
122
+
123
  5%|▍ | 8/171 [00:05<00:57, 2.84it/s]
124
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
125
 
126
+
127
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
128
 
129
+
130
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
131
 
132
+
133
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
134
 
135
+
136
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
137
 
138
+
139
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
140
 
141
+
142
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
143
 
144
+
145
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
146
 
147
+
148
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
149
 
150
+
151
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
152
 
153
+
154
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
155
 
156
+
157
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
158
 
159
+
160
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
161
 
162
+
163
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
164
 
165
+
166
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
167
 
168
+
169
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
170
 
171
+
172
  5%|▌ | 9/171 [00:05<00:59, 2.72it/s]
173
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
174
 
175
+
176
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
177
 
178
+
179
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
180
 
181
+
182
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
183
 
184
+
185
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
186
 
187
+
188
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
189
 
190
+
191
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
192
 
193
+
194
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
195
 
196
+
197
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
198
 
199
+
200
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
201
 
202
+
203
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
204
 
205
+
206
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
207
 
208
+
209
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
210
 
211
+
212
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
213
 
214
+
215
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
216
 
217
+
218
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
219
 
220
+
221
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
222
 
223
+
224
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
225
 
226
+
227
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
228
 
229
+
230
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
231
 
232
+
233
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
234
 
235
+
236
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
237
 
238
+
239
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
240
 
241
+
242
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
243
 
244
+
245
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
246
 
247
+
248
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
249
 
250
+
251
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
252
 
253
+
254
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
255
 
256
+
257
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
258
 
259
+
260
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
261
 
262
+
263
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
264
 
265
+
266
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
267
 
268
+
269
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
270
 
271
+
272
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
273
 
274
+
275
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
276
 
277
+
278
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
279
 
280
+
281
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
282
 
283
+
284
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
285
 
286
+
287
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
288
 
289
+
290
  11%|█ | 19/171 [00:05<00:15, 9.64it/s]
291
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
292
 
293
+
294
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
295
 
296
+
297
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
298
 
299
+
300
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
301
 
302
+
303
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
304
 
305
+
306
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
307
 
308
+
309
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
310
 
311
+
312
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
313
 
314
+
315
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
316
 
317
+
318
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
319
 
320
+
321
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
322
 
323
+
324
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
325
 
326
+
327
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
328
 
329
+
330
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
331
 
332
+
333
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
334
 
335
+
336
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
337
 
338
+
339
  26%|██▌ | 44/171 [00:05<00:03, 32.21it/s]
340
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
341
 
342
+
343
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
344
 
345
+
346
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
347
 
348
+
349
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
350
 
351
+
352
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
353
 
354
+
355
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
356
 
357
+
358
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
359
 
360
+
361
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
362
 
363
+
364
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
365
 
366
+
367
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
368
 
369
+
370
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
371
 
372
+
373
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
374
 
375
+
376
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
377
 
378
+
379
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
380
 
381
+
382
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
383
 
384
+
385
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
386
 
387
+
388
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
389
 
390
+
391
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
392
 
393
+
394
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
395
 
396
+
397
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
398
 
399
+
400
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
401
 
402
+
403
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
404
 
405
+
406
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
407
 
408
+
409
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
410
 
411
+
412
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
413
 
414
+
415
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
416
 
417
+
418
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
419
 
420
+
421
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
422
 
423
+
424
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
425
 
426
+
427
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
428
 
429
+
430
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
431
 
432
+
433
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
434
 
435
+
436
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
437
 
438
+
439
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
440
 
441
+
442
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
443
 
444
+
445
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
446
 
447
+
448
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
449
 
450
+
451
  32%|███▏ | 54/171 [00:05<00:02, 39.74it/s]
452
  46%|███���▌ | 78/171 [00:05<00:01, 62.38it/s]
453
 
454
+
455
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
456
 
457
+
458
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
459
 
460
+
461
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
462
 
463
+
464
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
465
 
466
+
467
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
468
 
469
+
470
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
471
 
472
+
473
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
474
 
475
+
476
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
477
 
478
+
479
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
480
 
481
+
482
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
483
 
484
+
485
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
486
 
487
+
488
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
489
 
490
+
491
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
492
 
493
+
494
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
495
 
496
+
497
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
498
 
499
+
500
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
501
 
502
+
503
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
504
 
505
+
506
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
507
 
508
+
509
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
510
 
511
+
512
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
513
 
514
+
515
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
516
 
517
+
518
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
519
 
520
+
521
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
522
 
523
+
524
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
525
 
526
+
527
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
528
 
529
+
530
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
531
 
532
+
533
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
534
 
535
+
536
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
537
 
538
+
539
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
540
 
541
+
542
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
543
 
544
+
545
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
546
 
547
+
548
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
549
 
550
+
551
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
552
 
553
+
554
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
555
 
556
+
557
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
558
 
559
+
560
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
561
 
562
+
563
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
564
 
565
+
566
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
567
 
568
+
569
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
570
 
571
+
572
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
573
 
574
+
575
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
576
 
577
+
578
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
579
 
580
+
581
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
582
 
583
+
584
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
585
 
586
+
587
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
588
 
589
+
590
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
591
 
592
+
593
  46%|████▌ | 78/171 [00:05<00:01, 62.38it/s]
594
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
595
 
596
+
597
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
598
 
599
+
600
  63%|██████▎ | 108/171 [00:05<00:00, 99.69it/s]
601
 
602
+
603
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
604
 
605
+
606
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
607
 
608
+
609
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
610
 
611
+
612
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
613
 
614
+
615
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
616
 
617
+
618
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
619
 
620
+
621
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
622
 
623
+
624
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
625
 
626
+
627
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
628
 
629
+
630
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
631
 
632
+
633
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
634
 
635
+
636
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
637
 
638
+
639
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
640
 
641
+
642
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
643
 
644
+
645
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
646
 
647
+
648
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
649
 
650
+
651
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
652
 
653
+
654
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
655
 
656
+
657
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
658
 
659
+
660
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
661
 
662
+
663
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
664
 
665
+
666
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
667
 
668
+
669
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
670
 
671
+
672
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
673
 
674
+
675
  63%|██████▎ | 108/171 [00:06<00:00, 99.69it/s]
676
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
677
 
678
+
679
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
680
 
681
+
682
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
683
 
684
+
685
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
686
 
687
+
688
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
689
 
690
+
691
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
692
 
693
+
694
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
695
 
696
+
697
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
698
 
699
+
700
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
701
 
702
+
703
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
704
 
705
+
706
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
707
 
708
+
709
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
710
 
711
+
712
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
713
 
714
+
715
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
716
 
717
+
718
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
719
 
720
+
721
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
722
 
723
+
724
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
725
 
726
+
727
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
728
 
729
+
730
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
731
 
732
+
733
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
734
 
735
+
736
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
737
 
738
+
739
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
740
 
741
+
742
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
743
 
744
+
745
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
746
 
747
+
748
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
749
 
750
+
751
  73%|███████▎ | 125/171 [00:06<00:00, 106.34it/s]
752
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
753
 
754
+
755
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
756
 
757
+
758
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
759
 
760
+
761
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
762
 
763
+
764
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
765
 
766
+
767
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
768
 
769
+
770
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
771
 
772
+
773
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
774
 
775
+
776
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
777
 
778
+
779
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
780
 
781
+
782
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
783
 
784
+
785
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
786
 
787
+
788
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
789
 
790
+
791
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
792
 
793
+
794
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
795
 
796
+
797
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
798
 
799
+
800
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
801
 
802
+
803
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
804
 
805
+
806
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
807
 
808
+
809
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
810
 
811
+
812
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
813
 
814
+
815
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
816
 
817
+
818
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
819
 
820
+
821
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
822
 
823
+
824
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
825
 
826
+
827
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
828
 
829
+
830
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
831
 
832
+
833
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
834
 
835
+
836
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
837
 
838
+
839
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
840
 
841
+
842
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
843
 
844
+
845
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
846
 
847
+
848
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
849
 
850
+
851
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
852
 
853
+
854
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
855
 
856
+
857
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
858
 
859
+
860
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
861
 
862
+
863
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
864
 
865
+
866
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
867
 
868
+
869
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
870
 
871
+
872
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
873
 
874
+
875
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
876
 
877
+
878
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
879
 
880
+
881
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
882
 
883
+
884
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
885
 
886
+
887
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
888
 
889
+
890
  82%|████████▏ | 141/171 [00:06<00:00, 112.83it/s]
891
  99%|█████████▉| 170/171 [00:06<00:00, 150.62it/s]
892
 
893
+
894
  99%|█████████▉| 170/171 [00:06<00:00, 150.62it/s]
895
+ [2024-06-04 03:31:19] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-0.5B-Chat/model.safetensors
896
+ [2024-06-04 03:31:19] INFO stats.py:77: Time usage: HF loading: 1.637 sec; Pre-quantization mapping: 0.799 sec; Quantization: 2.662 sec
897
+ [2024-06-04 03:31:19] INFO stats.py:91: RAM usage: Peak RAM: 2.308 GB. Total bytes loaded from disk: 2.308 GB
898
+ [2024-06-04 03:31:19] INFO convert_weight.py:155: Parameter size after quantization: 0.361 GB
899
+ [2024-06-04 03:31:19] INFO convert_weight.py:160: Total parameters: 619,570,176
900
+ [2024-06-04 03:31:19] INFO convert_weight.py:161: Bits per parameter: 5.005
901
+ [2024-06-04 03:31:19] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC
902
+
903
+ All finished, 8 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/ndarray-cache.json
904
+ Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f32_1-MLC/ndarray-cache-b16.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": "q4f32_1",
5
+ "model_config": {
6
+ "hidden_act": "silu",
7
+ "hidden_size": 1024,
8
+ "intermediate_size": 2816,
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": 64,
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-b16.json ADDED
The diff for this file is too large to render. See raw diff
 
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:b8f46d76cb480386eda181c91240606498c2ee70ffba41d112ff15eed0846b90
3
+ size 77791232
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f46d76cb480386eda181c91240606498c2ee70ffba41d112ff15eed0846b90
3
+ size 77791232
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d959ea95f29b46262014bcfb59763dde38bb13f3a68853c9d5fe6ba9b645e93a
3
+ size 33329152
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd77b3324e6218cbe2fd55fcc871ac9c6ccf2a9ec5b782911cdcd979aaee4fa
3
+ size 31156224
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6492d9719fc77f447908d62796f60ed02a9ca2d8fb60dd70c6302173084ae7
3
+ size 32194560
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a4c1d208353cd009dd6cd9017bfe3626b344d2c6084e22a8f4749a6da82a1e
3
+ size 32925696
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b194e9ab5995610ccdf11d0a1356407c905783cc140ec159478f49f0c432db
3
+ size 32194560
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0de2de1614475b2e3f28f5f80c114377d3798453dd407e1bc9df89880fee76
3
+ size 31303680
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