Hugging Face's logo

Tlopex
/
Qwen1.5-0.5B-Chat-q4f16_1-MLC

Model card Files Community
Tlopex commited on
Commit
26bbe72
•
1 Parent(s): bb8f4bc

Initial commit

Browse files
Files changed (15) 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. params_shard_7.bin +3 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +40 -0
  15. 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 [00:04<?, ?it/s]
9
  1%| | 1/171 [00:04<12:09, 4.29s/it]
10
 
 
11
  1%| | 1/171 [00:05<12:09, 4.29s/it]
12
 
 
13
  1%| | 1/171 [00:05<12:09, 4.29s/it]
14
  1%| | 2/171 [00:05<07:19, 2.60s/it]
15
 
 
16
  1%| | 2/171 [00:05<07:19, 2.60s/it]
17
 
 
18
  1%| | 2/171 [00:05<07:19, 2.60s/it]
19
 
 
20
  1%| | 2/171 [00:06<07:19, 2.60s/it]
21
 
 
22
  1%| | 2/171 [00:06<07:19, 2.60s/it]
23
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
24
 
 
25
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
26
 
 
27
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
28
 
 
29
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
30
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
31
 
 
32
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
33
 
 
34
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
35
 
 
36
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
37
 
 
38
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
39
 
 
40
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
41
  5%|▍ | 8/171 [00:06<01:15, 2.16it/s]
42
 
 
43
  5%|▍ | 8/171 [00:06<01:15, 2.16it/s]
44
 
 
45
  5%|▍ | 8/171 [00:07<01:15, 2.16it/s]
46
 
 
47
  5%|▍ | 8/171 [00:07<01:15, 2.16it/s]
48
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
49
 
 
50
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
51
 
 
52
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
53
 
 
54
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
55
 
 
56
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
57
 
 
58
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
59
 
 
60
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
61
 
 
62
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
63
 
 
64
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
65
 
 
66
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
67
 
 
68
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
69
 
 
70
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
71
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
72
 
 
73
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
74
 
 
75
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
76
 
 
77
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
78
 
 
79
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
80
 
 
81
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
82
 
 
83
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
84
 
 
85
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
86
 
 
87
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
88
 
 
89
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
90
 
 
91
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
92
 
 
93
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
94
 
 
95
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
96
 
 
97
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
98
 
 
99
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
100
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
101
 
 
102
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
103
 
 
104
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
105
 
 
106
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
107
 
 
108
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
109
 
 
110
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
111
 
 
112
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
113
 
 
114
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
115
 
 
116
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
117
 
 
118
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
119
 
 
120
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
121
 
 
122
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
123
 
 
124
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
125
 
 
126
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
127
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
128
 
 
129
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
130
 
 
131
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
132
 
 
133
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
134
 
 
135
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
136
 
 
137
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
138
 
 
139
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
140
 
 
141
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
142
 
 
143
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
144
 
 
145
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
146
 
 
147
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
148
 
 
149
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
150
 
 
151
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
152
 
 
153
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
154
 
 
155
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
156
 
 
157
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
158
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
159
 
 
160
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
161
 
 
162
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
163
 
 
164
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
165
 
 
166
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
167
 
 
168
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
169
 
 
170
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
171
 
 
172
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
173
 
 
174
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
175
 
 
176
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
177
 
 
178
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
179
 
 
180
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
181
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
182
 
 
183
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
184
 
 
185
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
186
 
 
187
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
188
 
 
189
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
190
 
 
191
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
192
 
 
193
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
194
 
 
195
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
196
 
 
197
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
198
 
 
199
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
200
 
 
201
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
202
 
 
203
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
204
 
 
205
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
206
 
 
207
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
208
 
 
209
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
210
 
 
211
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
212
 
 
213
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
214
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
215
 
 
216
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
217
 
 
218
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
219
 
 
220
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
221
 
 
222
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
223
 
 
224
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
225
 
 
226
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
227
 
 
228
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
229
 
 
230
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
231
 
 
232
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
233
 
 
234
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
235
 
 
236
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
237
 
 
238
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
239
 
 
240
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
241
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
242
 
 
243
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
244
 
 
245
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
246
 
 
247
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
248
 
 
249
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
250
 
 
251
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
252
 
 
253
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
254
 
 
255
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
256
 
 
257
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
258
 
 
259
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
260
 
 
261
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
262
 
 
263
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
264
 
 
265
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
266
 
 
267
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
268
 
 
269
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
270
 
 
271
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
272
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
273
 
 
274
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
275
 
 
276
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
277
 
 
278
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
279
 
 
280
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
281
 
 
282
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
283
 
 
284
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
285
 
 
286
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
287
 
 
288
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
289
 
 
290
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
291
 
 
292
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
293
 
 
294
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
295
 
 
296
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
297
 
 
298
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
299
 
 
300
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
301
 
 
302
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
303
 
 
304
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
305
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
306
 
 
307
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
308
 
 
309
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
310
 
 
311
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
312
 
 
313
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
314
 
 
315
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
316
 
 
317
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
318
 
 
319
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
320
 
 
321
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
322
 
 
323
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
324
 
 
325
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
326
 
 
327
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
328
 
 
329
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
330
 
 
331
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
332
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
333
 
 
334
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
335
 
 
336
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
337
 
 
338
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
339
 
 
340
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
341
 
 
342
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
343
 
 
344
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
345
 
 
346
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
347
 
 
348
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
349
 
 
350
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
351
 
 
352
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
353
 
 
354
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
355
 
 
356
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
357
 
 
358
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
359
 
 
360
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
361
 
 
362
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
363
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
364
 
 
365
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
366
 
 
367
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
368
 
 
369
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
370
 
 
371
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
372
 
 
373
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
374
 
 
375
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
376
 
 
377
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
378
 
 
379
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
380
 
 
381
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
382
 
 
383
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
384
 
 
385
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
386
 
 
387
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
388
 
 
389
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
390
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
391
 
 
392
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
393
 
 
394
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
395
 
 
396
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
397
 
 
398
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
399
 
 
400
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
401
 
 
402
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
403
 
 
404
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
405
 
 
406
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
407
 
 
408
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
409
 
 
410
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
411
 
 
412
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
413
 
 
414
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
415
 
 
416
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
417
 
 
418
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
419
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
420
 
 
421
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
422
 
 
423
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
424
 
 
425
  72%|█████���█▏ | 123/171 [00:09<00:00, 66.65it/s]
426
 
 
427
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
428
 
 
429
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
430
 
 
431
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
432
 
 
433
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
434
 
 
435
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
436
 
 
437
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
438
 
 
439
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
440
 
 
441
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
442
 
 
443
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
444
 
 
445
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
446
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
447
 
 
448
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
449
 
 
450
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
451
 
 
452
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
453
 
 
454
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
455
 
 
456
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
457
 
 
458
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
459
 
 
460
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
461
 
 
462
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
463
 
 
464
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
465
 
 
466
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
467
 
 
468
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
469
 
 
470
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
471
 
 
472
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
473
 
 
474
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
475
 
 
476
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
477
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
478
 
 
479
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
480
 
 
481
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
482
 
 
483
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
484
 
 
485
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
486
 
 
487
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
488
 
 
489
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
490
 
 
491
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
492
 
 
493
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
494
 
 
495
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
496
 
 
497
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
498
 
 
499
  82%|████��███▏ | 141/171 [00:09<00:00, 58.97it/s]
500
 
 
501
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
502
 
 
503
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
504
 
 
505
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
506
 
 
507
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
508
 
 
509
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
510
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
511
 
 
512
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
513
 
 
514
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
515
 
 
516
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
517
 
 
518
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
519
 
 
520
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
521
 
 
522
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
523
 
 
524
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
525
 
 
526
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
527
 
 
528
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
529
 
 
530
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
531
 
 
532
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
533
 
 
534
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
535
 
 
536
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
537
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
538
 
 
539
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
540
 
 
541
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
542
 
 
543
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
544
 
 
545
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
546
 
 
547
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
548
 
 
549
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
550
 
 
551
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
552
 
 
553
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
554
 
 
555
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
556
 
 
557
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
558
 
 
559
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
560
 
 
561
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
562
 
 
563
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
564
 
 
565
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
566
 
 
567
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
568
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
569
 
 
570
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
571
 
 
572
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
573
 
 
574
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
 
 
 
 
 
 
 
 
 
 
1
+ /usr/bin/python3 -m mlc_llm gen_config dist/models/Qwen1.5-0.5B-Chat --quantization q4f16_1 --conv-template chatml --output /tmp/tmpbz5k8a9j --context-window-size 32768
2
+ [2024-05-29 23:11:43] INFO auto_config.py:115: Found model configuration: dist/models/Qwen1.5-0.5B-Chat/config.json
3
+ [2024-05-29 23:11:43] INFO auto_config.py:153: Found model type: qwen2. Use `--model-type` to override.
4
+ [2024-05-29 23:11:43] INFO qwen2_model.py:48: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
5
+ [2024-05-29 23:11:43] INFO qwen2_model.py:65: prefill_chunk_size defaults to 2048
6
+ [2024-05-29 23:11:43] INFO config.py:106: Overriding context_window_size from 32768 to 32768
7
+ [2024-05-29 23:11:43] WARNING config.py:99: Warning: Cannot override max_batch_size, because QWen2Config does not have this field
8
+ [2024-05-29 23:11:43] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 151643
9
+ [2024-05-29 23:11:43] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 151643
10
+ [2024-05-29 23:11:43] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [151645, 151643]
11
+ [2024-05-29 23:11:43] INFO gen_config.py:255: [generation_config.json] Setting repetition_penalty: 1.1
12
+ [2024-05-29 23:11:43] INFO gen_config.py:255: [generation_config.json] Setting top_p: 0.8
13
+ [2024-05-29 23:11:43] INFO gen_config.py:269: Not found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer.model
14
+ [2024-05-29 23:11:43] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer.json. Copying to /tmp/tmpbz5k8a9j/tokenizer.json
15
+ [2024-05-29 23:11:43] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/vocab.json. Copying to /tmp/tmpbz5k8a9j/vocab.json
16
+ [2024-05-29 23:11:43] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/merges.txt. Copying to /tmp/tmpbz5k8a9j/merges.txt
17
+ [2024-05-29 23:11:43] INFO gen_config.py:269: Not found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/added_tokens.json
18
+ [2024-05-29 23:11:43] INFO gen_config.py:267: Found tokenizer config: dist/models/Qwen1.5-0.5B-Chat/tokenizer_config.json. Copying to /tmp/tmpbz5k8a9j/tokenizer_config.json
19
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting temperature: 0.7
20
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
21
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
22
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
23
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
24
+ [2024-05-29 23:11:43] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
25
+ [2024-05-29 23:11:43] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpbz5k8a9j/mlc-chat-config.json
26
+ /usr/bin/python3 -m mlc_llm convert_weight dist/models/Qwen1.5-0.5B-Chat --quantization q4f16_1 --source-format auto --output /tmp/tmpbz5k8a9j
27
+ [2024-05-29 23:11:44] INFO auto_config.py:115: Found model configuration: dist/models/Qwen1.5-0.5B-Chat/config.json
28
+ [2024-05-29 23:11:47] INFO auto_device.py:79: Found device: cuda:0
29
+ [2024-05-29 23:11:48] INFO auto_device.py:88: Not found device: rocm:0
30
+ [2024-05-29 23:11:48] INFO auto_device.py:88: Not found device: metal:0
31
+ [2024-05-29 23:11:49] INFO auto_device.py:88: Not found device: vulkan:0
32
+ [2024-05-29 23:11:50] INFO auto_device.py:88: Not found device: opencl:0
33
+ [2024-05-29 23:11:50] INFO auto_device.py:35: Using device: cuda:0
34
+ [2024-05-29 23:11:50] INFO auto_weight.py:70: Finding weights in: dist/models/Qwen1.5-0.5B-Chat
35
+ [2024-05-29 23:11:50] INFO auto_weight.py:136: Not found Huggingface PyTorch
36
+ [2024-05-29 23:11:50] 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
+ [2024-05-29 23:11:50] 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
+ [2024-05-29 23:11:50] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
39
+ [2024-05-29 23:11:50] INFO auto_config.py:153: Found model type: qwen2. Use `--model-type` to override.
40
+ [2024-05-29 23:11:50] INFO qwen2_model.py:48: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
41
+ [2024-05-29 23:11:50] 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='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
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/tmpbz5k8a9j
50
+ Start storing to cache /tmp/tmpbz5k8a9j
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 [00:04<?, ?it/s]
65
  1%| | 1/171 [00:04<12:09, 4.29s/it]
66
 
67
+
68
  1%| | 1/171 [00:05<12:09, 4.29s/it]
69
 
70
+
71
  1%| | 1/171 [00:05<12:09, 4.29s/it]
72
  1%| | 2/171 [00:05<07:19, 2.60s/it]
73
 
74
+
75
  1%| | 2/171 [00:05<07:19, 2.60s/it]
76
 
77
+
78
  1%| | 2/171 [00:05<07:19, 2.60s/it]
79
 
80
+
81
  1%| | 2/171 [00:06<07:19, 2.60s/it]
82
 
83
+
84
  1%| | 2/171 [00:06<07:19, 2.60s/it]
85
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
86
 
87
+
88
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
89
 
90
+
91
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
92
 
93
+
94
  2%|▏ | 4/171 [00:06<03:03, 1.10s/it]
95
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
96
 
97
+
98
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
99
 
100
+
101
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
102
 
103
+
104
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
105
 
106
+
107
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
108
 
109
+
110
  3%|▎ | 5/171 [00:06<02:27, 1.12it/s]
111
  5%|▍ | 8/171 [00:06<01:15, 2.16it/s]
112
 
113
+
114
  5%|▍ | 8/171 [00:06<01:15, 2.16it/s]
115
 
116
+
117
  5%|▍ | 8/171 [00:07<01:15, 2.16it/s]
118
 
119
+
120
  5%|▍ | 8/171 [00:07<01:15, 2.16it/s]
121
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
122
 
123
+
124
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
125
 
126
+
127
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
128
 
129
+
130
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
131
 
132
+
133
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
134
 
135
+
136
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
137
 
138
+
139
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
140
 
141
+
142
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
143
 
144
+
145
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
146
 
147
+
148
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
149
 
150
+
151
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
152
 
153
+
154
  5%|▌ | 9/171 [00:07<01:12, 2.23it/s]
155
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
156
 
157
+
158
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
159
 
160
+
161
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
162
 
163
+
164
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
165
 
166
+
167
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
168
 
169
+
170
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
171
 
172
+
173
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
174
 
175
+
176
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
177
 
178
+
179
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
180
 
181
+
182
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
183
 
184
+
185
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
186
 
187
+
188
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
189
 
190
+
191
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
192
 
193
+
194
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
195
 
196
+
197
  9%|▉ | 16/171 [00:07<00:24, 6.26it/s]
198
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
199
 
200
+
201
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
202
 
203
+
204
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
205
 
206
+
207
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
208
 
209
+
210
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
211
 
212
+
213
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
214
 
215
+
216
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
217
 
218
+
219
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
220
 
221
+
222
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
223
 
224
+
225
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
226
 
227
+
228
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
229
 
230
+
231
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
232
 
233
+
234
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
235
 
236
+
237
  15%|█▍ | 25/171 [00:07<00:11, 12.93it/s]
238
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
239
 
240
+
241
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
242
 
243
+
244
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
245
 
246
+
247
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
248
 
249
+
250
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
251
 
252
+
253
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
254
 
255
+
256
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
257
 
258
+
259
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
260
 
261
+
262
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
263
 
264
+
265
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
266
 
267
+
268
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
269
 
270
+
271
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
272
 
273
+
274
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
275
 
276
+
277
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
278
 
279
+
280
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
281
 
282
+
283
  19%|█▉ | 33/171 [00:07<00:07, 19.36it/s]
284
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
285
 
286
+
287
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
288
 
289
+
290
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
291
 
292
+
293
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
294
 
295
+
296
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
297
 
298
+
299
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
300
 
301
+
302
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
303
 
304
+
305
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
306
 
307
+
308
  25%|██▌ | 43/171 [00:07<00:04, 29.22it/s]
309
 
310
+
311
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
312
 
313
+
314
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
315
 
316
+
317
  25%|██▌ | 43/171 [00:08<00:04, 29.22it/s]
318
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
319
 
320
+
321
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
322
 
323
+
324
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
325
 
326
+
327
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
328
 
329
+
330
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
331
 
332
+
333
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
334
 
335
+
336
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
337
 
338
+
339
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
340
 
341
+
342
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
343
 
344
+
345
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
346
 
347
+
348
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
349
 
350
+
351
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
352
 
353
+
354
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
355
 
356
+
357
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
358
 
359
+
360
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
361
 
362
+
363
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
364
 
365
+
366
  29%|██▉ | 50/171 [00:08<00:03, 32.35it/s]
367
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
368
 
369
+
370
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
371
 
372
+
373
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
374
 
375
+
376
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
377
 
378
+
379
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
380
 
381
+
382
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
383
 
384
+
385
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
386
 
387
+
388
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
389
 
390
+
391
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
392
 
393
+
394
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
395
 
396
+
397
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
398
 
399
+
400
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
401
 
402
+
403
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
404
 
405
+
406
  35%|███▌ | 60/171 [00:08<00:02, 42.61it/s]
407
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
408
 
409
+
410
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
411
 
412
+
413
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
414
 
415
+
416
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
417
 
418
+
419
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
420
 
421
+
422
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
423
 
424
+
425
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
426
 
427
+
428
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
429
 
430
+
431
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
432
 
433
+
434
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
435
 
436
+
437
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
438
 
439
+
440
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
441
 
442
+
443
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
444
 
445
+
446
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
447
 
448
+
449
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
450
 
451
+
452
  40%|███▉ | 68/171 [00:08<00:02, 47.81it/s]
453
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
454
 
455
+
456
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
457
 
458
+
459
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
460
 
461
+
462
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
463
 
464
+
465
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
466
 
467
+
468
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
469
 
470
+
471
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
472
 
473
+
474
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
475
 
476
+
477
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
478
 
479
+
480
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
481
 
482
+
483
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
484
 
485
+
486
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
487
 
488
+
489
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
490
 
491
+
492
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
493
 
494
+
495
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
496
 
497
+
498
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
499
 
500
+
501
  46%|████▌ | 78/171 [00:08<00:01, 49.88it/s]
502
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
503
 
504
+
505
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
506
 
507
+
508
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
509
 
510
+
511
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
512
 
513
+
514
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
515
 
516
+
517
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
518
 
519
+
520
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
521
 
522
+
523
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
524
 
525
+
526
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
527
 
528
+
529
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
530
 
531
+
532
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
533
 
534
+
535
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
536
 
537
+
538
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
539
 
540
+
541
  51%|█████▏ | 88/171 [00:08<00:01, 58.01it/s]
542
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
543
 
544
+
545
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
546
 
547
+
548
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
549
 
550
+
551
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
552
 
553
+
554
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
555
 
556
+
557
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
558
 
559
+
560
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
561
 
562
+
563
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
564
 
565
+
566
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
567
 
568
+
569
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
570
 
571
+
572
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
573
 
574
+
575
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
576
 
577
+
578
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
579
 
580
+
581
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
582
 
583
+
584
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
585
 
586
+
587
  56%|█████▌ | 96/171 [00:08<00:01, 60.18it/s]
588
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
589
 
590
+
591
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
592
 
593
+
594
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
595
 
596
+
597
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
598
 
599
+
600
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
601
 
602
+
603
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
604
 
605
+
606
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
607
 
608
+
609
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
610
 
611
+
612
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
613
 
614
+
615
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
616
 
617
+
618
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
619
 
620
+
621
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
622
 
623
+
624
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
625
 
626
+
627
  62%|██████▏ | 106/171 [00:08<00:00, 68.44it/s]
628
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
629
 
630
+
631
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
632
 
633
+
634
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
635
 
636
+
637
  67%|██████▋ | 114/171 [00:08<00:00, 60.61it/s]
638
 
639
+
640
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
641
 
642
+
643
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
644
 
645
+
646
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
647
 
648
+
649
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
650
 
651
+
652
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
653
 
654
+
655
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
656
 
657
+
658
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
659
 
660
+
661
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
662
 
663
+
664
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
665
 
666
+
667
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
668
 
669
+
670
  67%|██████▋ | 114/171 [00:09<00:00, 60.61it/s]
671
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
672
 
673
+
674
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
675
 
676
+
677
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
678
 
679
+
680
  72%|█████���█▏ | 123/171 [00:09<00:00, 66.65it/s]
681
 
682
+
683
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
684
 
685
+
686
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
687
 
688
+
689
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
690
 
691
+
692
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
693
 
694
+
695
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
696
 
697
+
698
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
699
 
700
+
701
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
702
 
703
+
704
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
705
 
706
+
707
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
708
 
709
+
710
  72%|███████▏ | 123/171 [00:09<00:00, 66.65it/s]
711
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
712
 
713
+
714
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
715
 
716
+
717
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
718
 
719
+
720
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
721
 
722
+
723
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
724
 
725
+
726
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
727
 
728
+
729
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
730
 
731
+
732
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
733
 
734
+
735
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
736
 
737
+
738
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
739
 
740
+
741
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
742
 
743
+
744
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
745
 
746
+
747
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
748
 
749
+
750
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
751
 
752
+
753
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
754
 
755
+
756
  77%|███████▋ | 131/171 [00:09<00:00, 61.30it/s]
757
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
758
 
759
+
760
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
761
 
762
+
763
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
764
 
765
+
766
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
767
 
768
+
769
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
770
 
771
+
772
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
773
 
774
+
775
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
776
 
777
+
778
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
779
 
780
+
781
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
782
 
783
+
784
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
785
 
786
+
787
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
788
 
789
+
790
  82%|████��███▏ | 141/171 [00:09<00:00, 58.97it/s]
791
 
792
+
793
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
794
 
795
+
796
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
797
 
798
+
799
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
800
 
801
+
802
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
803
 
804
+
805
  82%|████████▏ | 141/171 [00:09<00:00, 58.97it/s]
806
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
807
 
808
+
809
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
810
 
811
+
812
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
813
 
814
+
815
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
816
 
817
+
818
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
819
 
820
+
821
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
822
 
823
+
824
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
825
 
826
+
827
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
828
 
829
+
830
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
831
 
832
+
833
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
834
 
835
+
836
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
837
 
838
+
839
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
840
 
841
+
842
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
843
 
844
+
845
  88%|████████▊ | 151/171 [00:09<00:00, 65.71it/s]
846
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
847
 
848
+
849
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
850
 
851
+
852
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
853
 
854
+
855
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
856
 
857
+
858
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
859
 
860
+
861
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
862
 
863
+
864
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
865
 
866
+
867
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
868
 
869
+
870
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
871
 
872
+
873
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
874
 
875
+
876
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
877
 
878
+
879
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
880
 
881
+
882
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
883
 
884
+
885
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
886
 
887
+
888
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
889
 
890
+
891
  93%|█████████▎| 159/171 [00:09<00:00, 65.93it/s]
892
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
893
 
894
+
895
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
896
 
897
+
898
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
899
 
900
+
901
  99%|█████████▉| 169/171 [00:09<00:00, 73.07it/s]
902
+ [2024-05-29 23:12:03] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/Qwen1.5-0.5B-Chat/model.safetensors
903
+ [2024-05-29 23:12:03] INFO stats.py:76: Time usage: HF loading: 1.413 sec; Pre-quantization mapping: 3.707 sec; Quantization: 3.039 sec
904
+ [2024-05-29 23:12:03] INFO stats.py:90: RAM usage: Peak RAM: 2.308 GB. Total bytes loaded from disk: 2.308 GB
905
+ [2024-05-29 23:12:03] INFO convert_weight.py:155: Parameter size after quantization: 0.325 GB
906
+ [2024-05-29 23:12:03] INFO convert_weight.py:160: Total parameters: 619,570,176
907
+ [2024-05-29 23:12:03] INFO convert_weight.py:161: Bits per parameter: 4.502
908
+ [2024-05-29 23:12:03] INFO convert_weight.py:166: Saved to directory: /tmp/tmpbz5k8a9j
909
+
910
+ All finished, 8 total shards committed, record saved to /tmp/tmpbz5k8a9j/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": "q4f16_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:e6cdec4c05b14a3edfe1cb4f9997905139511034d77cb5d6f4b4731524a528be
3
+ size 77791232
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6cdec4c05b14a3edfe1cb4f9997905139511034d77cb5d6f4b4731524a528be
3
+ size 77791232
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c2f1823ac925626866bacb00359cf838c1bfda0bc7e0f457aa89d36f9e9200
3
+ size 33329152
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2c2275f36f20cd76b1b331911b40038457984f9083eadb47ff274ddde787a7
3
+ size 31156224
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629f399433273fb57f7d28c35b1ed77e7d5cd36c86fdfa56f4018edf170b84c4
3
+ size 32194560
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd38b0f9801c9860ceff5f64fb76b8a574305899ff2f4fefe6d45cb7a036971c
3
+ size 32925696
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d24e952c343829ddbe4ce62963ca67ca7f7b800be4b1810199e52589e2be8a2
3
+ size 32194560
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3546b0fbf83efcfc8f2d5642fb3521b4d6a5b81c23b19bdd539a1601a9b385
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