Septend commited on
Commit
998f163
·
verified ·
1 Parent(s): 2b25efe

Upload model

Browse files
._args.json ADDED
Binary file (4.1 kB). View file
 
._chat_template.jinja ADDED
Binary file (4.1 kB). View file
 
._config.json ADDED
Binary file (4.1 kB). View file
 
._model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec62358817feee5612b25a285f028a043d2f370a447991921707efb4e81cd7d
3
+ size 4096
._model.safetensors.index.json ADDED
Binary file (4.1 kB). View file
 
._preprocessor_config.json ADDED
Binary file (4.1 kB). View file
 
._processor_config.json ADDED
Binary file (4.1 kB). View file
 
._tokenizer.json ADDED
Binary file (4.1 kB). View file
 
._tokenizer_config.json ADDED
Binary file (4.1 kB). View file
 
args.json CHANGED
@@ -35,12 +35,9 @@
35
  "enable_thinking": null,
36
  "add_non_thinking_prefix": true,
37
  "dataset": [
38
- "/inspire/qb-ilm/project/ai4education/p-liuwentao/ly-project/edu-test-data/edu_cot_sft.jsonl",
39
- "/inspire/qb-ilm/project/ai4education/p-liuwentao/ly-project/edu-test-data/self_identify_clean.jsonl",
40
- "/inspire/qb-ilm/project/ai4education/p-liuwentao/ly-project/edu-test-data/opus_merged_all_clean.jsonl",
41
- "/inspire/qb-ilm/project/ai4education/p-liuwentao/ly-project/edu-test-data/edu_writing_sft.jsonl",
42
- "/inspire/hdd/project/ai4education/p-liuwentao/monster/innospark/sft-data/self_identify_new_0521_final_messages.jsonl",
43
- "/inspire/hdd/project/ai4education/p-liuwentao/monster/innospark/sft-data/0518-all.jsonl"
44
  ],
45
  "val_dataset": [],
46
  "cached_dataset": [],
@@ -216,7 +213,7 @@
216
  "vllm_server_pass_dataset": false,
217
  "num_iterations": 1,
218
  "micro_batch_size": 2,
219
- "global_batch_size": 128,
220
  "recompute_granularity": "full",
221
  "recompute_method": "uniform",
222
  "recompute_num_layers": 1,
@@ -261,7 +258,7 @@
261
  "lr_decay_iters": null,
262
  "lr_warmup_iters": 0,
263
  "lr_warmup_fraction": 0.05,
264
- "min_lr": 1e-06,
265
  "lr_wsd_decay_style": "exponential",
266
  "lr_wsd_decay_iters": null,
267
  "weight_decay": 0.01,
@@ -273,7 +270,7 @@
273
  "adam_beta2": 0.95,
274
  "adam_eps": 1e-08,
275
  "sgd_momentum": 0.9,
276
- "output_dir": "/inspire/qb-ilm/project/ai4education/p-liuwentao/ms-swift/ckpt/Qwen3.6-35B-A3B/merge-all-test1/v2-20260525-202628",
277
  "save_steps": 100,
278
  "no_save_optim": true,
279
  "no_save_rng": true,
@@ -318,7 +315,7 @@
318
  "tensorboard"
319
  ],
320
  "logging_steps": 1,
321
- "tensorboard_dir": "/inspire/qb-ilm/project/ai4education/p-liuwentao/ms-swift/ckpt/Qwen3.6-35B-A3B/merge-all-test1/v2-20260525-202628/runs",
322
  "tensorboard_queue_size": 50,
323
  "wandb_project": "megatron-swift",
324
  "wandb_exp_name": null,
@@ -342,7 +339,7 @@
342
  "moe_enable_deepep": false,
343
  "moe_grouped_gemm": true,
344
  "moe_permute_fusion": true,
345
- "moe_aux_loss_coeff": 1e-06,
346
  "moe_z_loss_coeff": null,
347
  "moe_shared_expert_overlap": true,
348
  "moe_layer_recompute": false,
@@ -377,7 +374,7 @@
377
  "swift_version": "4.0.3",
378
  "ckpt_dir": null,
379
  "rank": 0,
380
- "global_world_size": 64,
381
  "local_world_size": 8,
382
  "model_suffix": "Qwen3.6-35B-A3B",
383
  "model_info": "ModelInfo(model_type='qwen3_5_moe', model_dir='/inspire/hdd/project/ai4education/public/Models/Qwen/Qwen3.6-35B-A3B', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
@@ -391,7 +388,7 @@
391
  "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_5', model_types=['qwen3_5', 'qwen3_5_moe'], bridge_cls=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Bridge'>, visual_cls=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Vit'>, is_multimodal=True, loader=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Loader'>)",
392
  "fp8": null,
393
  "params_dtype": "bfloat16",
394
- "world_size": 64,
395
- "data_parallel_size": 32,
396
- "num_microbatches": 2
397
  }
 
35
  "enable_thinking": null,
36
  "add_non_thinking_prefix": true,
37
  "dataset": [
38
+ "/inspire/hdd/global_user/p-liuwentao/ly-data/Data/merged_all.jsonl",
39
+ "/inspire/hdd/global_user/p-liuwentao/ly-data/Data/self_identify.jsonl",
40
+ "/inspire/hdd/global_user/p-liuwentao/ly-data/Data/sft_train.jsonl"
 
 
 
41
  ],
42
  "val_dataset": [],
43
  "cached_dataset": [],
 
213
  "vllm_server_pass_dataset": false,
214
  "num_iterations": 1,
215
  "micro_batch_size": 2,
216
+ "global_batch_size": 64,
217
  "recompute_granularity": "full",
218
  "recompute_method": "uniform",
219
  "recompute_num_layers": 1,
 
258
  "lr_decay_iters": null,
259
  "lr_warmup_iters": 0,
260
  "lr_warmup_fraction": 0.05,
261
+ "min_lr": 1e-05,
262
  "lr_wsd_decay_style": "exponential",
263
  "lr_wsd_decay_iters": null,
264
  "weight_decay": 0.01,
 
270
  "adam_beta2": 0.95,
271
  "adam_eps": 1e-08,
272
  "sgd_momentum": 0.9,
273
+ "output_dir": "/inspire/qb-ilm/project/ai4education/p-liuwentao/ms-swift/ckpt/Qwen3.6-35B-A3B/distilled-all-v2/v0-20260515-153118",
274
  "save_steps": 100,
275
  "no_save_optim": true,
276
  "no_save_rng": true,
 
315
  "tensorboard"
316
  ],
317
  "logging_steps": 1,
318
+ "tensorboard_dir": "/inspire/qb-ilm/project/ai4education/p-liuwentao/ms-swift/ckpt/Qwen3.6-35B-A3B/distilled-all-v2/v0-20260515-153118/runs",
319
  "tensorboard_queue_size": 50,
320
  "wandb_project": "megatron-swift",
321
  "wandb_exp_name": null,
 
339
  "moe_enable_deepep": false,
340
  "moe_grouped_gemm": true,
341
  "moe_permute_fusion": true,
342
+ "moe_aux_loss_coeff": 0.001,
343
  "moe_z_loss_coeff": null,
344
  "moe_shared_expert_overlap": true,
345
  "moe_layer_recompute": false,
 
374
  "swift_version": "4.0.3",
375
  "ckpt_dir": null,
376
  "rank": 0,
377
+ "global_world_size": 16,
378
  "local_world_size": 8,
379
  "model_suffix": "Qwen3.6-35B-A3B",
380
  "model_info": "ModelInfo(model_type='qwen3_5_moe', model_dir='/inspire/hdd/project/ai4education/public/Models/Qwen/Qwen3.6-35B-A3B', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
 
388
  "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_5', model_types=['qwen3_5', 'qwen3_5_moe'], bridge_cls=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Bridge'>, visual_cls=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Vit'>, is_multimodal=True, loader=<class 'swift.megatron.model.mm_gpts.qwen3_5.Qwen3_5Loader'>)",
389
  "fp8": null,
390
  "params_dtype": "bfloat16",
391
+ "world_size": 16,
392
+ "data_parallel_size": 8,
393
+ "num_microbatches": 4
394
  }
model-00001-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8e51d488e4af479326c9a3b091c6697954ebcd9145be7c61baf35d9c8c3a376
3
  size 4998182088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1c7da35e72c6edcacb858a850c534cc72a8a01dfb54b7575295183f6619bf8
3
  size 4998182088
model-00002-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d81f30915d2d894924eabee68989ecfcab0bbb941090a760232479ed2a32bb03
3
  size 4999577880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a86884af3b4c41e39a24b929938b98db20a12ba74c49dce2b9a11802ee1fdb1b
3
  size 4999577880
model-00003-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:567b1daabd9d2e5c065ea7b22cac5323f5087e9c3422de5c193db3bf319668b6
3
  size 4999577888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff644c4cc201ff9d7294f17d8a778111070aeba1852894f3550e94ba2cd65a61
3
  size 4999577888
model-00004-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:485b17fdf8c353843316e7ecb0bd046461d047f6c4b4dffd1e067cc67c630e8a
3
  size 4999905080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895bb33c613463ff64a5068713c1179c444ca908d65eeccfa6155dc4e0feeef0
3
  size 4999905080
model-00005-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:315ef80a1053a8f3ee21b0921dbed733e88411e78d2b565121683cb92f344e46
3
  size 4999580144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15020f6a96729016ebfce1f84f3568d9c93eb7df2ef07c59bd5fe0548394cb27
3
  size 4999580144
model-00006-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8ac130be34dbc83ce130a3eec39a6afdacd863c24af5415b74073c12c00b868
3
  size 4999580208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e8e563d0db1e42ac2ca2fd9a1a6cae2c197b057b3c4b82fd9442134efe8ecd
3
  size 4999580208
model-00007-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a72d865713f31abf3d2711a3b1e9a1459c98985372d98f65a53c2fc48a959e15
3
  size 4999580216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c96b4a1a2d5588212293d9a55155e0574aaf31553fe73c391644ba319cdcbf6
3
  size 4999580216
model-00008-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28cf510ed4bedbbfe85c7cde078d78881cec09a7f8010d8117ba87b5a41b1b38
3
  size 4999906808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f77973c8591981f0509f99d6d17d97c4270ca64449ee81f82309a5ca422b19
3
  size 4999906808
model-00009-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbb2784a8b145d61ee8323595b549f32c2dcb31b12e4f8e1e2885bea77fa4a26
3
  size 4999580144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8eb1418b913dfb0e9614c6cb6095d3fc3a54a60fab77ad9c35a9876a8337f5
3
  size 4999580144
model-00010-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f53f3b62b2032ec4dd4b97021d48323160b87903ad00011ffe118a05e8f759
3
  size 4999580208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752673c11cd42d919ecfc2c213cd780d7a578e57df6a050f7f5ddbc2f54ac383
3
  size 4999580208
model-00011-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85aa0046de1355d9bdfdc3d540d795d7d185496e151b554ece88f80fd8a4043e
3
  size 4999580216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49cb0622c3ebfdc17e8776b1924d91456d23ea97f8862121facff8c21a6b54e
3
  size 4999580216
model-00012-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ec07bab50e0d6f985932a84dd67738f1f19e4f6b8d93dbf50a7cc9e88ef1cd1
3
  size 4999906816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6fd40e956ce6ea887c80aae9cc1a2c65f127dfd338701c71db5d427331609a
3
  size 4999906816
model-00013-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f04bf50aecf8fced02f44631f30fa420b64924a4d6149f04a15dabbe7bc6eb
3
  size 4999580144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd55b611a95cd802f86a1eb8098125e0ea22722df120c978722a991e73b1171
3
  size 4999580144
model-00014-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6d17373378ea9e167a47806d4cd19b57a967a6065c6e0ff800d434c9c81d915
3
  size 4207519416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf85ab7d20a712a2013e8ca5f539e991c7b7cccb25748a09a29862699b9cc9e
3
  size 4207519416
tokenizer_config.json CHANGED
@@ -1,32 +1,305 @@
1
  {
2
- "add_prefix_space": false,
3
- "audio_bos_token": "<|audio_start|>",
4
- "audio_eos_token": "<|audio_end|>",
5
- "audio_token": "<|audio_pad|>",
6
- "backend": "tokenizers",
7
- "bos_token": null,
8
- "clean_up_tokenization_spaces": false,
9
- "eos_token": "<|im_end|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": true,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|endoftext|>",
24
- "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+",
25
- "processor_class": "Qwen3VLProcessor",
26
- "split_special_tokens": false,
27
- "tokenizer_class": "TokenizersBackend",
28
- "unk_token": null,
29
- "video_token": "<|video_pad|>",
30
- "vision_bos_token": "<|vision_start|>",
31
- "vision_eos_token": "<|vision_end|>"
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}\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
+ }