danym commited on
Commit
66a83f3
·
verified ·
1 Parent(s): bad1693

paper-faithful v3 surgery qwen3_5_9b on B300

Browse files
.gitattributes CHANGED
@@ -60,3 +60,4 @@ stage2_v3pf_qwen3_5_9b_b300/latest/__4_0.distcp filter=lfs diff=lfs merge=lfs -t
60
  stage2_v3pf_qwen3_5_9b_b300/latest/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
61
  stage2_v3pf_qwen3_5_9b_b300/latest/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
62
  stage2_v3pf_qwen3_5_9b_b300/latest/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 
 
60
  stage2_v3pf_qwen3_5_9b_b300/latest/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
61
  stage2_v3pf_qwen3_5_9b_b300/latest/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
62
  stage2_v3pf_qwen3_5_9b_b300/latest/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
63
+ qwen3_5_9b_stage2_v3pf_b300/vllm_compat/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5RTPurboForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 12288,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention"
52
+ ],
53
+ "linear_conv_kernel_dim": 4,
54
+ "linear_key_head_dim": 128,
55
+ "linear_num_key_heads": 16,
56
+ "linear_num_value_heads": 32,
57
+ "linear_value_head_dim": 128,
58
+ "max_position_embeddings": 262144,
59
+ "mlp_only_layers": [],
60
+ "model_type": "qwen3_5_text",
61
+ "mtp_num_hidden_layers": 1,
62
+ "mtp_use_dedicated_embeddings": false,
63
+ "num_attention_heads": 16,
64
+ "num_hidden_layers": 32,
65
+ "num_key_value_heads": 4,
66
+ "rms_norm_eps": 1e-06,
67
+ "use_cache": true,
68
+ "vocab_size": 248320,
69
+ "mamba_ssm_dtype": "float32",
70
+ "rope_parameters": {
71
+ "mrope_interleaved": true,
72
+ "mrope_section": [
73
+ 11,
74
+ 11,
75
+ 10
76
+ ],
77
+ "rope_type": "default",
78
+ "rope_theta": 10000000,
79
+ "partial_rotary_factor": 0.25
80
+ },
81
+ "rtpurbo": {
82
+ "probe": "rtpurbo_probe.json",
83
+ "d_idx": 16,
84
+ "top_p": 0.9,
85
+ "sliding_window": 8192,
86
+ "sink_tokens": 4
87
+ }
88
+ },
89
+ "tie_word_embeddings": false,
90
+ "transformers_version": "4.57.0.dev0",
91
+ "video_token_id": 248057,
92
+ "vision_config": {
93
+ "deepstack_visual_indexes": [],
94
+ "depth": 27,
95
+ "hidden_act": "gelu_pytorch_tanh",
96
+ "hidden_size": 1152,
97
+ "in_channels": 3,
98
+ "initializer_range": 0.02,
99
+ "intermediate_size": 4304,
100
+ "model_type": "qwen3_5",
101
+ "num_heads": 16,
102
+ "num_position_embeddings": 2304,
103
+ "out_hidden_size": 4096,
104
+ "patch_size": 16,
105
+ "spatial_merge_size": 2,
106
+ "temporal_patch_size": 2
107
+ },
108
+ "vision_end_token_id": 248054,
109
+ "vision_start_token_id": 248053,
110
+ "rtpurbo": {
111
+ "probe": "rtpurbo_probe.json",
112
+ "d_idx": 16,
113
+ "top_p": 0.9,
114
+ "sliding_window": 8192,
115
+ "sink_tokens": 4
116
+ },
117
+ "image_token_index": 248056,
118
+ "video_token_index": 248057
119
+ }
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e707f198d0318e5778fb5955f91496ecceef26d4066829c914d302f7b482788
3
+ size 17907979728
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/rtpurbo_probe.json ADDED
@@ -0,0 +1,476 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "Qwen/Qwen3.5-9B",
3
+ "calibration_size": 8,
4
+ "retrieval_ratio": 0.15,
5
+ "seq_len": 8192,
6
+ "metric": "paper-eq3-dual-needle",
7
+ "scores_per_layer": {
8
+ "3": [
9
+ 0.050376028288155794,
10
+ 0.11922094877809286,
11
+ 0.05854044482111931,
12
+ 0.032847787253558636,
13
+ 0.05741418479010463,
14
+ 0.05625112820416689,
15
+ 0.0493226470425725,
16
+ 0.04844623408280313,
17
+ 0.023476658738218248,
18
+ 0.06786601105704904,
19
+ 0.1994509119540453,
20
+ 0.0638201697729528,
21
+ 0.1528812926262617,
22
+ 0.7819019183516502,
23
+ 0.11062866821885109,
24
+ 0.87675541639328
25
+ ],
26
+ "7": [
27
+ 0.12869573198258877,
28
+ 0.14752627722918987,
29
+ 0.3388279639184475,
30
+ 0.5131242349743843,
31
+ 0.4874109961092472,
32
+ 0.7025855705142021,
33
+ 0.39092252403497696,
34
+ 0.14150314684957266,
35
+ 0.44219953939318657,
36
+ 0.2333515603095293,
37
+ 0.7233279496431351,
38
+ 0.2724359445273876,
39
+ 0.27401214092969894,
40
+ 0.5271693803369999,
41
+ 0.4716362841427326,
42
+ 0.45831332728266716
43
+ ],
44
+ "11": [
45
+ 0.23507250379770994,
46
+ 0.4834546223282814,
47
+ 0.5047340877354145,
48
+ 0.17479609698057175,
49
+ 0.2732497751712799,
50
+ 0.4323376938700676,
51
+ 0.5748457536101341,
52
+ 0.24127990007400513,
53
+ 0.7752783223986626,
54
+ 0.5496058091521263,
55
+ 0.5648367330431938,
56
+ 0.48966652899980545,
57
+ 0.14060425106436014,
58
+ 0.291000222787261,
59
+ 0.4160652346909046,
60
+ 0.15067564230412245
61
+ ],
62
+ "15": [
63
+ 0.2812189981341362,
64
+ 0.5835527554154396,
65
+ 0.192391368560493,
66
+ 0.3239660430699587,
67
+ 0.24585177935659885,
68
+ 0.27992282435297966,
69
+ 0.5636329837143421,
70
+ 0.39050190709531307,
71
+ 0.5790155753493309,
72
+ 0.4465397596359253,
73
+ 0.2867701780050993,
74
+ 0.40504590049386024,
75
+ 0.5317178256809711,
76
+ 0.8333659246563911,
77
+ 0.46999988332390785,
78
+ 0.6920002326369286
79
+ ],
80
+ "19": [
81
+ 0.42862794548273087,
82
+ 0.5226101838052273,
83
+ 0.6486293971538544,
84
+ 0.5533918887376785,
85
+ 0.7957630529999733,
86
+ 0.7519400268793106,
87
+ 0.6469171568751335,
88
+ 0.8637371212244034,
89
+ 0.46260618790984154,
90
+ 0.5001496151089668,
91
+ 0.7652399316430092,
92
+ 0.6800480335950851,
93
+ 0.8987655788660049,
94
+ 0.40126700699329376,
95
+ 0.7516027614474297,
96
+ 0.8263772651553154
97
+ ],
98
+ "23": [
99
+ 0.6961957141757011,
100
+ 0.7441711574792862,
101
+ 0.6873607411980629,
102
+ 0.27471218444406986,
103
+ 0.6517725959420204,
104
+ 0.6787834092974663,
105
+ 0.7331148162484169,
106
+ 0.6840200945734978,
107
+ 0.6446156278252602,
108
+ 0.7456054165959358,
109
+ 0.4904380030930042,
110
+ 0.752664253115654,
111
+ 0.8189241364598274,
112
+ 0.8150171339511871,
113
+ 0.6963462829589844,
114
+ 0.8448804467916489
115
+ ],
116
+ "27": [
117
+ 0.5979977771639824,
118
+ 0.7811550348997116,
119
+ 0.23245308548212051,
120
+ 0.8301596865057945,
121
+ 0.527938824146986,
122
+ 0.6166251748800278,
123
+ 0.595462653785944,
124
+ 0.3049439452588558,
125
+ 0.6870232000946999,
126
+ 0.30581710301339626,
127
+ 0.6450319364666939,
128
+ 0.5612932220101357,
129
+ 0.6223992146551609,
130
+ 0.919038288295269,
131
+ 0.4159914180636406,
132
+ 0.5323963686823845
133
+ ],
134
+ "31": [
135
+ 0.5736934617161751,
136
+ 0.5905276015400887,
137
+ 0.4434502199292183,
138
+ 0.6384230926632881,
139
+ 0.29034815914928913,
140
+ 0.35119690373539925,
141
+ 0.18482187949120998,
142
+ 0.1312270099297166,
143
+ 0.27471743151545525,
144
+ 0.007977169239893556,
145
+ 0.0550543712452054,
146
+ 0.33692556247115135,
147
+ 0.025807054014876485,
148
+ 0.009456870378926396,
149
+ 0.33623810298740864,
150
+ 0.16282695811241865
151
+ ]
152
+ },
153
+ "layers": {
154
+ "3": {
155
+ "retrieval": [
156
+ 13,
157
+ 15
158
+ ],
159
+ "local": [
160
+ 0,
161
+ 1,
162
+ 2,
163
+ 3,
164
+ 4,
165
+ 5,
166
+ 6,
167
+ 7,
168
+ 8,
169
+ 9,
170
+ 10,
171
+ 11,
172
+ 12,
173
+ 14
174
+ ],
175
+ "scores": [
176
+ 0.050376,
177
+ 0.119221,
178
+ 0.05854,
179
+ 0.032848,
180
+ 0.057414,
181
+ 0.056251,
182
+ 0.049323,
183
+ 0.048446,
184
+ 0.023477,
185
+ 0.067866,
186
+ 0.199451,
187
+ 0.06382,
188
+ 0.152881,
189
+ 0.781902,
190
+ 0.110629,
191
+ 0.876755
192
+ ]
193
+ },
194
+ "7": {
195
+ "retrieval": [
196
+ 10
197
+ ],
198
+ "local": [
199
+ 0,
200
+ 1,
201
+ 2,
202
+ 3,
203
+ 4,
204
+ 5,
205
+ 6,
206
+ 7,
207
+ 8,
208
+ 9,
209
+ 11,
210
+ 12,
211
+ 13,
212
+ 14,
213
+ 15
214
+ ],
215
+ "scores": [
216
+ 0.128696,
217
+ 0.147526,
218
+ 0.338828,
219
+ 0.513124,
220
+ 0.487411,
221
+ 0.702586,
222
+ 0.390923,
223
+ 0.141503,
224
+ 0.4422,
225
+ 0.233352,
226
+ 0.723328,
227
+ 0.272436,
228
+ 0.274012,
229
+ 0.527169,
230
+ 0.471636,
231
+ 0.458313
232
+ ]
233
+ },
234
+ "11": {
235
+ "retrieval": [
236
+ 8
237
+ ],
238
+ "local": [
239
+ 0,
240
+ 1,
241
+ 2,
242
+ 3,
243
+ 4,
244
+ 5,
245
+ 6,
246
+ 7,
247
+ 9,
248
+ 10,
249
+ 11,
250
+ 12,
251
+ 13,
252
+ 14,
253
+ 15
254
+ ],
255
+ "scores": [
256
+ 0.235073,
257
+ 0.483455,
258
+ 0.504734,
259
+ 0.174796,
260
+ 0.27325,
261
+ 0.432338,
262
+ 0.574846,
263
+ 0.24128,
264
+ 0.775278,
265
+ 0.549606,
266
+ 0.564837,
267
+ 0.489667,
268
+ 0.140604,
269
+ 0.291,
270
+ 0.416065,
271
+ 0.150676
272
+ ]
273
+ },
274
+ "15": {
275
+ "retrieval": [
276
+ 13
277
+ ],
278
+ "local": [
279
+ 0,
280
+ 1,
281
+ 2,
282
+ 3,
283
+ 4,
284
+ 5,
285
+ 6,
286
+ 7,
287
+ 8,
288
+ 9,
289
+ 10,
290
+ 11,
291
+ 12,
292
+ 14,
293
+ 15
294
+ ],
295
+ "scores": [
296
+ 0.281219,
297
+ 0.583553,
298
+ 0.192391,
299
+ 0.323966,
300
+ 0.245852,
301
+ 0.279923,
302
+ 0.563633,
303
+ 0.390502,
304
+ 0.579016,
305
+ 0.44654,
306
+ 0.28677,
307
+ 0.405046,
308
+ 0.531718,
309
+ 0.833366,
310
+ 0.47,
311
+ 0.692
312
+ ]
313
+ },
314
+ "19": {
315
+ "retrieval": [
316
+ 4,
317
+ 5,
318
+ 7,
319
+ 10,
320
+ 12,
321
+ 15
322
+ ],
323
+ "local": [
324
+ 0,
325
+ 1,
326
+ 2,
327
+ 3,
328
+ 6,
329
+ 8,
330
+ 9,
331
+ 11,
332
+ 13,
333
+ 14
334
+ ],
335
+ "scores": [
336
+ 0.428628,
337
+ 0.52261,
338
+ 0.648629,
339
+ 0.553392,
340
+ 0.795763,
341
+ 0.75194,
342
+ 0.646917,
343
+ 0.863737,
344
+ 0.462606,
345
+ 0.50015,
346
+ 0.76524,
347
+ 0.680048,
348
+ 0.898766,
349
+ 0.401267,
350
+ 0.751603,
351
+ 0.826377
352
+ ]
353
+ },
354
+ "23": {
355
+ "retrieval": [
356
+ 11,
357
+ 12,
358
+ 13,
359
+ 15
360
+ ],
361
+ "local": [
362
+ 0,
363
+ 1,
364
+ 2,
365
+ 3,
366
+ 4,
367
+ 5,
368
+ 6,
369
+ 7,
370
+ 8,
371
+ 9,
372
+ 10,
373
+ 14
374
+ ],
375
+ "scores": [
376
+ 0.696196,
377
+ 0.744171,
378
+ 0.687361,
379
+ 0.274712,
380
+ 0.651773,
381
+ 0.678783,
382
+ 0.733115,
383
+ 0.68402,
384
+ 0.644616,
385
+ 0.745605,
386
+ 0.490438,
387
+ 0.752664,
388
+ 0.818924,
389
+ 0.815017,
390
+ 0.696346,
391
+ 0.84488
392
+ ]
393
+ },
394
+ "27": {
395
+ "retrieval": [
396
+ 1,
397
+ 3,
398
+ 13
399
+ ],
400
+ "local": [
401
+ 0,
402
+ 2,
403
+ 4,
404
+ 5,
405
+ 6,
406
+ 7,
407
+ 8,
408
+ 9,
409
+ 10,
410
+ 11,
411
+ 12,
412
+ 14,
413
+ 15
414
+ ],
415
+ "scores": [
416
+ 0.597998,
417
+ 0.781155,
418
+ 0.232453,
419
+ 0.83016,
420
+ 0.527939,
421
+ 0.616625,
422
+ 0.595463,
423
+ 0.304944,
424
+ 0.687023,
425
+ 0.305817,
426
+ 0.645032,
427
+ 0.561293,
428
+ 0.622399,
429
+ 0.919038,
430
+ 0.415991,
431
+ 0.532396
432
+ ]
433
+ },
434
+ "31": {
435
+ "retrieval": [
436
+ 3
437
+ ],
438
+ "local": [
439
+ 0,
440
+ 1,
441
+ 2,
442
+ 4,
443
+ 5,
444
+ 6,
445
+ 7,
446
+ 8,
447
+ 9,
448
+ 10,
449
+ 11,
450
+ 12,
451
+ 13,
452
+ 14,
453
+ 15
454
+ ],
455
+ "scores": [
456
+ 0.573693,
457
+ 0.590528,
458
+ 0.44345,
459
+ 0.638423,
460
+ 0.290348,
461
+ 0.351197,
462
+ 0.184822,
463
+ 0.131227,
464
+ 0.274717,
465
+ 0.007977,
466
+ 0.055054,
467
+ 0.336926,
468
+ 0.025807,
469
+ 0.009457,
470
+ 0.336238,
471
+ 0.162827
472
+ ]
473
+ }
474
+ },
475
+ "retrieval_fraction": 0.1484375
476
+ }
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
qwen3_5_9b_stage2_v3pf_b300/vllm_compat/vocab.json ADDED
The diff for this file is too large to render. See raw diff