Hugging Face's logo

youmeng937
/
captioner

Safetensors
qwen2_5_omni
Model card Files
xet
 Community
youmeng937 commited on
Commit
f3e0f71
·
verified ·
1 Parent(s): 3ff13e5

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/added_tokens.json +24 -0
  3. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/args.json +389 -0
  4. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/chat_template.jinja +7 -0
  5. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/config.json +637 -0
  6. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/generation_config.json +8 -0
  7. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  8. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  9. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
  10. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  11. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
  12. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  13. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  14. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
  15. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
  16. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
  17. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
  18. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  19. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
  20. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
  21. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
  22. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
  23. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
  24. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
  25. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
  26. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
  27. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
  28. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
  29. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  30. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
  31. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
  32. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  33. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  34. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  35. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  36. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  37. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
  38. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  39. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/mp_rank_00_model_states.pt +3 -0
  40. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/latest +1 -0
  41. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/merges.txt +0 -0
  42. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00001-of-00005.safetensors +3 -0
  43. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00002-of-00005.safetensors +3 -0
  44. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00003-of-00005.safetensors +3 -0
  45. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00004-of-00005.safetensors +3 -0
  46. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00005-of-00005.safetensors +3 -0
  47. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model.safetensors.index.json +0 -0
  48. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/preprocessor_config.json +31 -0
  49. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/rng_state_0.pth +3 -0
  50. v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/rng_state_1.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|AUDIO|>": 151646,
5
+ "<|IMAGE|>": 151655,
6
+ "<|VIDEO|>": 151656,
7
+ "<|audio_bos|>": 151647,
8
+ "<|audio_eos|>": 151648,
9
+ "<|box_end|>": 151649,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|vision_bos|>": 151652,
22
+ "<|vision_eos|>": 151653,
23
+ "<|vision_pad|>": 151654
24
+ }
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/args.json ADDED
@@ -0,0 +1,389 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": 100000,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 200.0,
39
+ "save_total_limit": 5,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 200.0,
64
+ "dataloader_num_workers": 32,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": null,
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 1,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "allgather_partitions": true,
102
+ "allgather_bucket_size": 200000000.0,
103
+ "overlap_comm": false,
104
+ "reduce_scatter": true,
105
+ "reduce_bucket_size": 200000000.0,
106
+ "contiguous_gradients": true
107
+ },
108
+ "gradient_accumulation_steps": "auto",
109
+ "gradient_clipping": "auto",
110
+ "steps_per_print": 2000,
111
+ "train_batch_size": "auto",
112
+ "train_micro_batch_size_per_gpu": "auto",
113
+ "wall_clock_breakdown": false
114
+ },
115
+ "label_smoothing_factor": 0.0,
116
+ "optim": "adamw_torch",
117
+ "optim_args": null,
118
+ "adafactor": false,
119
+ "group_by_length": false,
120
+ "length_column_name": "length",
121
+ "report_to": [
122
+ "tensorboard"
123
+ ],
124
+ "project": "huggingface",
125
+ "trackio_space_id": "trackio",
126
+ "ddp_find_unused_parameters": null,
127
+ "ddp_bucket_cap_mb": null,
128
+ "ddp_broadcast_buffers": null,
129
+ "dataloader_pin_memory": true,
130
+ "dataloader_persistent_workers": false,
131
+ "skip_memory_metrics": true,
132
+ "use_legacy_prediction_loop": false,
133
+ "push_to_hub": false,
134
+ "resume_from_checkpoint": null,
135
+ "hub_model_id": null,
136
+ "hub_strategy": "every_save",
137
+ "hub_token": null,
138
+ "hub_private_repo": null,
139
+ "hub_always_push": false,
140
+ "hub_revision": null,
141
+ "gradient_checkpointing": true,
142
+ "gradient_checkpointing_kwargs": null,
143
+ "include_inputs_for_metrics": false,
144
+ "include_for_metrics": [],
145
+ "eval_do_concat_batches": true,
146
+ "fp16_backend": "auto",
147
+ "push_to_hub_model_id": null,
148
+ "push_to_hub_organization": null,
149
+ "push_to_hub_token": null,
150
+ "mp_parameters": "",
151
+ "auto_find_batch_size": false,
152
+ "full_determinism": false,
153
+ "torchdynamo": null,
154
+ "ray_scope": "last",
155
+ "ddp_timeout": 18000000,
156
+ "torch_compile": false,
157
+ "torch_compile_backend": null,
158
+ "torch_compile_mode": null,
159
+ "include_tokens_per_second": false,
160
+ "include_num_input_tokens_seen": false,
161
+ "neftune_noise_alpha": null,
162
+ "optim_target_modules": null,
163
+ "batch_eval_metrics": false,
164
+ "eval_on_start": false,
165
+ "use_liger_kernel": false,
166
+ "liger_kernel_config": null,
167
+ "eval_use_gather_object": false,
168
+ "average_tokens_across_devices": true,
169
+ "sortish_sampler": false,
170
+ "predict_with_generate": false,
171
+ "generation_max_length": null,
172
+ "generation_num_beams": null,
173
+ "generation_config": null,
174
+ "tuner_backend": "peft",
175
+ "vit_gradient_checkpointing": null,
176
+ "router_aux_loss_coef": 0.0,
177
+ "enable_dft_loss": false,
178
+ "enable_channel_loss": false,
179
+ "check_model": true,
180
+ "acc_strategy": "token",
181
+ "train_dataloader_shuffle": true,
182
+ "max_epochs": null,
183
+ "aligner_lr": null,
184
+ "vit_lr": null,
185
+ "use_logits_to_keep": null,
186
+ "ds3_gather_for_generation": true,
187
+ "resume_only_model": false,
188
+ "optimizer": null,
189
+ "loss_type": null,
190
+ "metric": null,
191
+ "eval_use_evalscope": false,
192
+ "eval_dataset": [],
193
+ "eval_dataset_args": null,
194
+ "eval_limit": null,
195
+ "eval_generation_config": null,
196
+ "extra_eval_args": null,
197
+ "use_flash_ckpt": false,
198
+ "use_ray": false,
199
+ "ray_exp_name": null,
200
+ "device_groups": null,
201
+ "model": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/qwen2.5omni",
202
+ "model_type": "my_qwen2_5_omni",
203
+ "model_revision": null,
204
+ "task_type": "causal_lm",
205
+ "torch_dtype": "bfloat16",
206
+ "attn_impl": "flash_attn",
207
+ "new_special_tokens": [],
208
+ "num_labels": null,
209
+ "problem_type": null,
210
+ "rope_scaling": null,
211
+ "device_map": null,
212
+ "max_memory": {},
213
+ "max_model_len": null,
214
+ "local_repo_path": null,
215
+ "init_strategy": null,
216
+ "template": "my_qwen2_5_omni",
217
+ "system": null,
218
+ "max_length": 8192,
219
+ "truncation_strategy": "delete",
220
+ "max_pixels": null,
221
+ "agent_template": null,
222
+ "norm_bbox": null,
223
+ "use_chat_template": true,
224
+ "padding_free": true,
225
+ "padding_side": "right",
226
+ "loss_scale": "default",
227
+ "sequence_parallel_size": 1,
228
+ "response_prefix": null,
229
+ "template_backend": "swift",
230
+ "dataset": [
231
+ "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/full_length_tagging/train.jsonl#800000",
232
+ "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/gemini70w_with_bpm/train.jsonl#800000",
233
+ "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/bgm_data/train.jsonl#400000"
234
+ ],
235
+ "val_dataset": [],
236
+ "split_dataset_ratio": 0.001,
237
+ "dataset_num_proc": 16,
238
+ "load_from_cache_file": true,
239
+ "dataset_shuffle": true,
240
+ "val_dataset_shuffle": false,
241
+ "streaming": false,
242
+ "interleave_prob": null,
243
+ "stopping_strategy": "first_exhausted",
244
+ "shuffle_buffer_size": 1000,
245
+ "download_mode": "reuse_dataset_if_exists",
246
+ "columns": {},
247
+ "strict": false,
248
+ "model_name": null,
249
+ "model_author": null,
250
+ "custom_dataset_info": [],
251
+ "quant_method": null,
252
+ "quant_bits": null,
253
+ "hqq_axis": null,
254
+ "bnb_4bit_compute_dtype": "bfloat16",
255
+ "bnb_4bit_quant_type": "nf4",
256
+ "bnb_4bit_use_double_quant": true,
257
+ "bnb_4bit_quant_storage": null,
258
+ "max_new_tokens": 64,
259
+ "temperature": 0.0,
260
+ "top_k": null,
261
+ "top_p": null,
262
+ "repetition_penalty": null,
263
+ "num_beams": 1,
264
+ "stream": false,
265
+ "stop_words": [],
266
+ "logprobs": false,
267
+ "top_logprobs": null,
268
+ "ckpt_dir": null,
269
+ "lora_modules": [],
270
+ "train_type": "full",
271
+ "adapters": [],
272
+ "external_plugins": [],
273
+ "model_kwargs": {},
274
+ "load_args": false,
275
+ "load_data_args": false,
276
+ "packing": true,
277
+ "packing_length": 8192,
278
+ "lazy_tokenize": false,
279
+ "cached_dataset": [],
280
+ "custom_register_path": [
281
+ "register_model/my_register.py"
282
+ ],
283
+ "use_hf": false,
284
+ "ignore_args_error": false,
285
+ "use_swift_lora": false,
286
+ "freeze_parameters": [
287
+ "thinker.audio_tower",
288
+ "thinker.visual",
289
+ "talker",
290
+ "token2wav"
291
+ ],
292
+ "freeze_parameters_regex": null,
293
+ "freeze_parameters_ratio": 0.0,
294
+ "trainable_parameters": [
295
+ "thinker.audio_tower.proj",
296
+ "thinker.visual.merger"
297
+ ],
298
+ "trainable_parameters_regex": null,
299
+ "freeze_llm": false,
300
+ "freeze_vit": true,
301
+ "freeze_aligner": false,
302
+ "target_modules": [
303
+ "all-linear"
304
+ ],
305
+ "target_regex": null,
306
+ "target_parameters": null,
307
+ "modules_to_save": [],
308
+ "lora_rank": 8,
309
+ "lora_alpha": 32,
310
+ "lora_dropout": 0.05,
311
+ "lora_bias": "none",
312
+ "lora_dtype": null,
313
+ "lorap_lr_ratio": null,
314
+ "use_rslora": false,
315
+ "use_dora": false,
316
+ "lora_ga_batch_size": 2,
317
+ "lora_ga_iters": 2,
318
+ "lora_ga_max_length": 1024,
319
+ "lora_ga_direction": "ArB2r",
320
+ "lora_ga_scale": "stable",
321
+ "lora_ga_stable_gamma": 16,
322
+ "init_weights": true,
323
+ "fourier_n_frequency": 2000,
324
+ "fourier_scaling": 300.0,
325
+ "boft_block_size": 4,
326
+ "boft_block_num": 0,
327
+ "boft_n_butterfly_factor": 1,
328
+ "boft_dropout": 0.0,
329
+ "vera_rank": 256,
330
+ "vera_projection_prng_key": 0,
331
+ "vera_dropout": 0.0,
332
+ "vera_d_initial": 0.1,
333
+ "adapter_act": "gelu",
334
+ "adapter_length": 128,
335
+ "use_galore": false,
336
+ "galore_target_modules": null,
337
+ "galore_rank": 128,
338
+ "galore_update_proj_gap": 50,
339
+ "galore_scale": 1.0,
340
+ "galore_proj_type": "std",
341
+ "galore_optim_per_parameter": false,
342
+ "galore_with_embedding": false,
343
+ "galore_quantization": false,
344
+ "galore_proj_quant": false,
345
+ "galore_proj_bits": 4,
346
+ "galore_proj_group_size": 256,
347
+ "galore_cos_threshold": 0.4,
348
+ "galore_gamma_proj": 2,
349
+ "galore_queue_size": 5,
350
+ "adalora_target_r": 8,
351
+ "adalora_init_r": 12,
352
+ "adalora_tinit": 0,
353
+ "adalora_tfinal": 0,
354
+ "adalora_deltaT": 1,
355
+ "adalora_beta1": 0.85,
356
+ "adalora_beta2": 0.85,
357
+ "adalora_orth_reg_weight": 0.5,
358
+ "llamapro_num_new_blocks": 4,
359
+ "llamapro_num_groups": null,
360
+ "lisa_activated_layers": 0,
361
+ "lisa_step_interval": 20,
362
+ "reft_layer_key": null,
363
+ "reft_layers": null,
364
+ "reft_rank": 4,
365
+ "reft_intervention_type": "LoreftIntervention",
366
+ "reft_args": null,
367
+ "swanlab_token": null,
368
+ "swanlab_project": null,
369
+ "swanlab_workspace": null,
370
+ "swanlab_exp_name": null,
371
+ "swanlab_lark_webhook_url": null,
372
+ "swanlab_lark_secret": null,
373
+ "swanlab_mode": "cloud",
374
+ "add_version": true,
375
+ "create_checkpoint_symlink": false,
376
+ "zero_hpz_partition_size": null,
377
+ "deepspeed_autotp_size": null,
378
+ "early_stop_interval": null,
379
+ "rank": 0,
380
+ "global_world_size": 32,
381
+ "local_world_size": 8,
382
+ "model_suffix": "qwen2.5omni",
383
+ "model_info": "ModelInfo(model_type='my_qwen2_5_omni', model_dir='/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/qwen2.5omni', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
384
+ "model_meta": "ModelMeta(model_type='my_qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='my_qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fc55d606ac0>, model_arch=MultiModelKeys(arch_name='my_qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model', 'thinker.lm_head'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
385
+ "model_dir": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/qwen2.5omni",
386
+ "hub": "<class 'swift.hub.hub.MSHub'>",
387
+ "evaluation_strategy": "steps",
388
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=100000, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=200, save_total_limit=5, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=200, dataloader_num_workers=32, dataloader_prefetch_factor=10, past_index=-1, run_name='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/exps/v5_200w_32gpus_full_params_add_aligner/v0-20260404-024132', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, padding_side='right', padding_free=True, task_type='causal_lm', problem_type=None)"
389
+ }
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/config.json ADDED
@@ -0,0 +1,637 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "enable_audio_output": true,
7
+ "enable_talker": true,
8
+ "eos_token_id": 151645,
9
+ "hidden_size": 3584,
10
+ "keys_to_ignore_at_inference": [
11
+ "past_key_values",
12
+ "hidden_states",
13
+ "attention_mask"
14
+ ],
15
+ "model_type": "qwen2_5_omni",
16
+ "pad_token_id": 151643,
17
+ "talker_config": {
18
+ "_attn_implementation_autoset": true,
19
+ "_name_or_path": "Qwen2.5-Omni-7B/talker",
20
+ "architectures": [
21
+ "Qwen2OmniTalkerForConditionalGeneration"
22
+ ],
23
+ "attention_dropout": 0.0,
24
+ "audio_end_token_id": 151648,
25
+ "audio_start_token_id": 151647,
26
+ "audio_token_index": 151646,
27
+ "dtype": "bfloat16",
28
+ "embedding_size": 3584,
29
+ "head_dim": 128,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 896,
32
+ "image_token_index": 151655,
33
+ "init_std": 0.02,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 18944,
36
+ "layer_types": [
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention"
61
+ ],
62
+ "max_position_embeddings": 32768,
63
+ "max_window_layers": 28,
64
+ "model_type": "qwen2_5_omni_talker",
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 24,
67
+ "num_key_value_heads": 4,
68
+ "position_id_per_seconds": 25,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_scaling": {
71
+ "mrope_section": [
72
+ 16,
73
+ 24,
74
+ 24
75
+ ],
76
+ "rope_type": "default",
77
+ "type": "default"
78
+ },
79
+ "rope_theta": 1000000.0,
80
+ "seconds_per_chunk": 2,
81
+ "sliding_window": null,
82
+ "spatial_merge_size": 2,
83
+ "tts_codec_end_token_id": 8294,
84
+ "tts_codec_mask_token_id": 8296,
85
+ "tts_codec_pad_token_id": 8292,
86
+ "tts_codec_start_token_id": 8293,
87
+ "tts_text_end_token_id": 151861,
88
+ "tts_text_pad_token_id": 151859,
89
+ "tts_text_start_token_id": 151860,
90
+ "use_cache": false,
91
+ "use_sliding_window": false,
92
+ "video_token_index": 151656,
93
+ "vision_end_token_id": 151653,
94
+ "vision_start_token_id": 151652,
95
+ "vocab_size": 8448
96
+ },
97
+ "thinker_config": {
98
+ "_attn_implementation_autoset": true,
99
+ "_name_or_path": "Qwen2.5-Omni-7B/thinker",
100
+ "architectures": [
101
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
102
+ ],
103
+ "audio_config": {
104
+ "_attn_implementation_autoset": true,
105
+ "_name_or_path": "",
106
+ "activation_dropout": 0.0,
107
+ "activation_function": "gelu",
108
+ "add_cross_attention": false,
109
+ "architectures": null,
110
+ "attention_dropout": 0.0,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "d_model": 1280,
117
+ "decoder_start_token_id": null,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "dropout": 0.0,
121
+ "dtype": "bfloat16",
122
+ "early_stopping": false,
123
+ "encoder_attention_heads": 20,
124
+ "encoder_ffn_dim": 5120,
125
+ "encoder_layerdrop": 0.0,
126
+ "encoder_layers": 32,
127
+ "encoder_no_repeat_ngram_size": 0,
128
+ "eos_token_id": null,
129
+ "exponential_decay_length_penalty": null,
130
+ "finetuning_task": null,
131
+ "forced_bos_token_id": null,
132
+ "forced_eos_token_id": null,
133
+ "id2label": {
134
+ "0": "LABEL_0",
135
+ "1": "LABEL_1"
136
+ },
137
+ "init_std": 0.02,
138
+ "initializer_range": 0.02,
139
+ "is_decoder": false,
140
+ "is_encoder_decoder": false,
141
+ "label2id": {
142
+ "LABEL_0": 0,
143
+ "LABEL_1": 1
144
+ },
145
+ "length_penalty": 1.0,
146
+ "max_length": 20,
147
+ "max_source_positions": 1500,
148
+ "min_length": 0,
149
+ "model_type": "qwen2_5_omni_audio_encoder",
150
+ "n_window": 100,
151
+ "no_repeat_ngram_size": 0,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_hidden_layers": 32,
155
+ "num_mel_bins": 128,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_dim": 3584,
159
+ "output_hidden_states": false,
160
+ "output_scores": false,
161
+ "pad_token_id": 151643,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "remove_invalid_values": false,
166
+ "repetition_penalty": 1.0,
167
+ "return_dict": true,
168
+ "return_dict_in_generate": false,
169
+ "scale_embedding": false,
170
+ "sep_token_id": null,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": true,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torchscript": false,
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "audio_end_token_id": 151648,
185
+ "audio_start_token_id": 151647,
186
+ "audio_token_index": 151646,
187
+ "bos_token_id": 151644,
188
+ "dtype": "bfloat16",
189
+ "eos_token_id": 151645,
190
+ "ignore_index": -100,
191
+ "image_token_index": 151655,
192
+ "init_std": 0.02,
193
+ "initializer_range": 0.02,
194
+ "model_type": "qwen2_5_omni_thinker",
195
+ "pad_token_id": 151643,
196
+ "position_id_per_seconds": 25,
197
+ "seconds_per_chunk": 2,
198
+ "text_config": {
199
+ "_name_or_path": "",
200
+ "add_cross_attention": false,
201
+ "architectures": null,
202
+ "attention_dropout": 0.0,
203
+ "bad_words_ids": null,
204
+ "begin_suppress_tokens": null,
205
+ "bos_token_id": null,
206
+ "chunk_size_feed_forward": 0,
207
+ "cross_attention_hidden_size": null,
208
+ "decoder_start_token_id": null,
209
+ "diversity_penalty": 0.0,
210
+ "do_sample": false,
211
+ "dtype": "bfloat16",
212
+ "early_stopping": false,
213
+ "encoder_no_repeat_ngram_size": 0,
214
+ "eos_token_id": null,
215
+ "exponential_decay_length_penalty": null,
216
+ "finetuning_task": null,
217
+ "forced_bos_token_id": null,
218
+ "forced_eos_token_id": null,
219
+ "hidden_act": "silu",
220
+ "hidden_size": 3584,
221
+ "id2label": {
222
+ "0": "LABEL_0",
223
+ "1": "LABEL_1"
224
+ },
225
+ "init_std": 0.02,
226
+ "initializer_range": 0.02,
227
+ "intermediate_size": 18944,
228
+ "is_decoder": false,
229
+ "is_encoder_decoder": false,
230
+ "label2id": {
231
+ "LABEL_0": 0,
232
+ "LABEL_1": 1
233
+ },
234
+ "layer_types": [
235
+ "full_attention",
236
+ "full_attention",
237
+ "full_attention",
238
+ "full_attention",
239
+ "full_attention",
240
+ "full_attention",
241
+ "full_attention",
242
+ "full_attention",
243
+ "full_attention",
244
+ "full_attention",
245
+ "full_attention",
246
+ "full_attention",
247
+ "full_attention",
248
+ "full_attention",
249
+ "full_attention",
250
+ "full_attention",
251
+ "full_attention",
252
+ "full_attention",
253
+ "full_attention",
254
+ "full_attention",
255
+ "full_attention",
256
+ "full_attention",
257
+ "full_attention",
258
+ "full_attention",
259
+ "full_attention",
260
+ "full_attention",
261
+ "full_attention",
262
+ "full_attention"
263
+ ],
264
+ "length_penalty": 1.0,
265
+ "max_length": 20,
266
+ "max_position_embeddings": 32768,
267
+ "max_window_layers": 28,
268
+ "min_length": 0,
269
+ "model_type": "qwen2_5_omni_text",
270
+ "no_repeat_ngram_size": 0,
271
+ "num_attention_heads": 28,
272
+ "num_beam_groups": 1,
273
+ "num_beams": 1,
274
+ "num_hidden_layers": 28,
275
+ "num_key_value_heads": 4,
276
+ "num_return_sequences": 1,
277
+ "output_attentions": false,
278
+ "output_hidden_states": false,
279
+ "output_scores": false,
280
+ "pad_token_id": 151643,
281
+ "prefix": null,
282
+ "problem_type": null,
283
+ "pruned_heads": {},
284
+ "remove_invalid_values": false,
285
+ "repetition_penalty": 1.0,
286
+ "return_dict": true,
287
+ "return_dict_in_generate": false,
288
+ "rms_norm_eps": 1e-06,
289
+ "rope_scaling": {
290
+ "mrope_section": [
291
+ 16,
292
+ 24,
293
+ 24
294
+ ],
295
+ "rope_type": "default",
296
+ "type": "default"
297
+ },
298
+ "rope_theta": 1000000.0,
299
+ "sep_token_id": null,
300
+ "sliding_window": null,
301
+ "suppress_tokens": null,
302
+ "task_specific_params": null,
303
+ "temperature": 1.0,
304
+ "tf_legacy_loss": false,
305
+ "tie_encoder_decoder": false,
306
+ "tie_word_embeddings": false,
307
+ "tokenizer_class": null,
308
+ "top_k": 50,
309
+ "top_p": 1.0,
310
+ "torchscript": false,
311
+ "typical_p": 1.0,
312
+ "use_bfloat16": false,
313
+ "use_cache": false,
314
+ "use_sliding_window": false,
315
+ "vocab_size": 152064
316
+ },
317
+ "user_token_id": 872,
318
+ "video_token_index": 151656,
319
+ "vision_config": {
320
+ "_attn_implementation_autoset": true,
321
+ "_name_or_path": "",
322
+ "add_cross_attention": false,
323
+ "architectures": null,
324
+ "bad_words_ids": null,
325
+ "begin_suppress_tokens": null,
326
+ "bos_token_id": null,
327
+ "chunk_size_feed_forward": 0,
328
+ "cross_attention_hidden_size": null,
329
+ "decoder_start_token_id": null,
330
+ "depth": 32,
331
+ "diversity_penalty": 0.0,
332
+ "do_sample": false,
333
+ "dtype": "bfloat16",
334
+ "early_stopping": false,
335
+ "embed_dim": 1280,
336
+ "encoder_no_repeat_ngram_size": 0,
337
+ "eos_token_id": null,
338
+ "exponential_decay_length_penalty": null,
339
+ "finetuning_task": null,
340
+ "forced_bos_token_id": null,
341
+ "forced_eos_token_id": null,
342
+ "fullatt_block_indexes": [
343
+ 7,
344
+ 15,
345
+ 23,
346
+ 31
347
+ ],
348
+ "hidden_act": "silu",
349
+ "hidden_size": 1280,
350
+ "id2label": {
351
+ "0": "LABEL_0",
352
+ "1": "LABEL_1"
353
+ },
354
+ "in_channels": 3,
355
+ "in_chans": 3,
356
+ "init_std": 0.02,
357
+ "initializer_range": 0.02,
358
+ "intermediate_size": 3420,
359
+ "is_decoder": false,
360
+ "is_encoder_decoder": false,
361
+ "label2id": {
362
+ "LABEL_0": 0,
363
+ "LABEL_1": 1
364
+ },
365
+ "length_penalty": 1.0,
366
+ "max_length": 20,
367
+ "min_length": 0,
368
+ "model_type": "qwen2_5_omni_vision_encoder",
369
+ "no_repeat_ngram_size": 0,
370
+ "num_beam_groups": 1,
371
+ "num_beams": 1,
372
+ "num_heads": 16,
373
+ "num_return_sequences": 1,
374
+ "out_hidden_size": 3584,
375
+ "output_attentions": false,
376
+ "output_hidden_states": false,
377
+ "output_scores": false,
378
+ "pad_token_id": 151643,
379
+ "patch_size": 14,
380
+ "prefix": null,
381
+ "problem_type": null,
382
+ "pruned_heads": {},
383
+ "remove_invalid_values": false,
384
+ "repetition_penalty": 1.0,
385
+ "return_dict": true,
386
+ "return_dict_in_generate": false,
387
+ "sep_token_id": null,
388
+ "spatial_merge_size": 2,
389
+ "spatial_patch_size": 14,
390
+ "suppress_tokens": null,
391
+ "task_specific_params": null,
392
+ "temperature": 1.0,
393
+ "temporal_patch_size": 2,
394
+ "tf_legacy_loss": false,
395
+ "tie_encoder_decoder": false,
396
+ "tie_word_embeddings": true,
397
+ "tokenizer_class": null,
398
+ "tokens_per_second": 25,
399
+ "top_k": 50,
400
+ "top_p": 1.0,
401
+ "torchscript": false,
402
+ "typical_p": 1.0,
403
+ "use_bfloat16": false,
404
+ "window_size": 112
405
+ },
406
+ "vision_end_token_id": 151653,
407
+ "vision_start_token_id": 151652,
408
+ "vision_token_id": 151654
409
+ },
410
+ "token2wav_config": {
411
+ "_attn_implementation_autoset": true,
412
+ "bigvgan_config": {
413
+ "_attn_implementation_autoset": true,
414
+ "_name_or_path": "",
415
+ "add_cross_attention": false,
416
+ "architectures": null,
417
+ "bad_words_ids": null,
418
+ "begin_suppress_tokens": null,
419
+ "bos_token_id": null,
420
+ "chunk_size_feed_forward": 0,
421
+ "cross_attention_hidden_size": null,
422
+ "decoder_start_token_id": null,
423
+ "diversity_penalty": 0.0,
424
+ "do_sample": false,
425
+ "dtype": null,
426
+ "early_stopping": false,
427
+ "encoder_no_repeat_ngram_size": 0,
428
+ "eos_token_id": null,
429
+ "exponential_decay_length_penalty": null,
430
+ "finetuning_task": null,
431
+ "forced_bos_token_id": null,
432
+ "forced_eos_token_id": null,
433
+ "id2label": {
434
+ "0": "LABEL_0",
435
+ "1": "LABEL_1"
436
+ },
437
+ "is_decoder": false,
438
+ "is_encoder_decoder": false,
439
+ "label2id": {
440
+ "LABEL_0": 0,
441
+ "LABEL_1": 1
442
+ },
443
+ "length_penalty": 1.0,
444
+ "max_length": 20,
445
+ "mel_dim": 80,
446
+ "min_length": 0,
447
+ "model_type": "qwen2_5_omni_bigvgan",
448
+ "no_repeat_ngram_size": 0,
449
+ "num_beam_groups": 1,
450
+ "num_beams": 1,
451
+ "num_return_sequences": 1,
452
+ "output_attentions": false,
453
+ "output_hidden_states": false,
454
+ "output_scores": false,
455
+ "pad_token_id": 151643,
456
+ "prefix": null,
457
+ "problem_type": null,
458
+ "pruned_heads": {},
459
+ "remove_invalid_values": false,
460
+ "repetition_penalty": 1.0,
461
+ "resblock_dilation_sizes": [
462
+ [
463
+ 1,
464
+ 3,
465
+ 5
466
+ ],
467
+ [
468
+ 1,
469
+ 3,
470
+ 5
471
+ ],
472
+ [
473
+ 1,
474
+ 3,
475
+ 5
476
+ ]
477
+ ],
478
+ "resblock_kernel_sizes": [
479
+ 3,
480
+ 7,
481
+ 11
482
+ ],
483
+ "return_dict": true,
484
+ "return_dict_in_generate": false,
485
+ "sep_token_id": null,
486
+ "suppress_tokens": null,
487
+ "task_specific_params": null,
488
+ "temperature": 1.0,
489
+ "tf_legacy_loss": false,
490
+ "tie_encoder_decoder": false,
491
+ "tie_word_embeddings": true,
492
+ "tokenizer_class": null,
493
+ "top_k": 50,
494
+ "top_p": 1.0,
495
+ "torchscript": false,
496
+ "typical_p": 1.0,
497
+ "upsample_initial_channel": 1536,
498
+ "upsample_kernel_sizes": [
499
+ 11,
500
+ 7,
501
+ 4,
502
+ 4,
503
+ 4,
504
+ 4
505
+ ],
506
+ "upsample_rates": [
507
+ 5,
508
+ 3,
509
+ 2,
510
+ 2,
511
+ 2,
512
+ 2
513
+ ],
514
+ "use_bfloat16": false,
515
+ "use_bias_at_final": false
516
+ },
517
+ "dit_config": {
518
+ "_attn_implementation_autoset": true,
519
+ "_name_or_path": "",
520
+ "add_cross_attention": false,
521
+ "architectures": null,
522
+ "bad_words_ids": null,
523
+ "begin_suppress_tokens": null,
524
+ "block_size": 24,
525
+ "bos_token_id": null,
526
+ "chunk_size_feed_forward": 0,
527
+ "cross_attention_hidden_size": null,
528
+ "decoder_start_token_id": null,
529
+ "depth": 22,
530
+ "dim": 1024,
531
+ "diversity_penalty": 0.0,
532
+ "do_sample": false,
533
+ "dropout": 0.1,
534
+ "dtype": "float32",
535
+ "early_stopping": false,
536
+ "emb_dim": 512,
537
+ "enc_attention_channels": 64,
538
+ "enc_channels": [
539
+ 256,
540
+ 256,
541
+ 256,
542
+ 256,
543
+ 768
544
+ ],
545
+ "enc_dilations": [
546
+ 1,
547
+ 2,
548
+ 3,
549
+ 4,
550
+ 1
551
+ ],
552
+ "enc_dim": 128,
553
+ "enc_emb_dim": 192,
554
+ "enc_global_context": true,
555
+ "enc_kernel_sizes": [
556
+ 5,
557
+ 3,
558
+ 3,
559
+ 3,
560
+ 1
561
+ ],
562
+ "enc_lin_neurons": 192,
563
+ "enc_res2net_scale": 2,
564
+ "enc_se_channels": 64,
565
+ "encoder_no_repeat_ngram_size": 0,
566
+ "eos_token_id": null,
567
+ "exponential_decay_length_penalty": null,
568
+ "ff_mult": 2,
569
+ "finetuning_task": null,
570
+ "forced_bos_token_id": null,
571
+ "forced_eos_token_id": null,
572
+ "head_dim": 64,
573
+ "heads": 16,
574
+ "hidden_size": 1024,
575
+ "id2label": {
576
+ "0": "LABEL_0",
577
+ "1": "LABEL_1"
578
+ },
579
+ "is_decoder": false,
580
+ "is_encoder_decoder": false,
581
+ "label2id": {
582
+ "LABEL_0": 0,
583
+ "LABEL_1": 1
584
+ },
585
+ "length_penalty": 1.0,
586
+ "look_ahead_layers": [
587
+ 10
588
+ ],
589
+ "look_backward_layers": [
590
+ 0,
591
+ 20
592
+ ],
593
+ "max_length": 20,
594
+ "max_position_embeddings": 32768,
595
+ "mel_dim": 80,
596
+ "min_length": 0,
597
+ "model_type": "qwen2_5_omni_dit",
598
+ "no_repeat_ngram_size": 0,
599
+ "num_attention_heads": 16,
600
+ "num_beam_groups": 1,
601
+ "num_beams": 1,
602
+ "num_embeds": 8193,
603
+ "num_hidden_layers": 22,
604
+ "num_return_sequences": 1,
605
+ "output_attentions": false,
606
+ "output_hidden_states": false,
607
+ "output_scores": false,
608
+ "pad_token_id": 151643,
609
+ "prefix": null,
610
+ "problem_type": null,
611
+ "pruned_heads": {},
612
+ "remove_invalid_values": false,
613
+ "repeats": 2,
614
+ "repetition_penalty": 1.0,
615
+ "return_dict": true,
616
+ "return_dict_in_generate": false,
617
+ "rope_theta": 10000.0,
618
+ "sep_token_id": null,
619
+ "suppress_tokens": null,
620
+ "task_specific_params": null,
621
+ "temperature": 1.0,
622
+ "tf_legacy_loss": false,
623
+ "tie_encoder_decoder": false,
624
+ "tie_word_embeddings": true,
625
+ "tokenizer_class": null,
626
+ "top_k": 50,
627
+ "top_p": 1.0,
628
+ "torchscript": false,
629
+ "typical_p": 1.0,
630
+ "use_bfloat16": false
631
+ },
632
+ "dtype": "bfloat16",
633
+ "model_type": "qwen2_5_omni_token2wav",
634
+ "pad_token_id": 151643
635
+ },
636
+ "transformers_version": "4.57.6"
637
+ }
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "transformers_version": "4.57.6"
8
+ }
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cdb7b69a4d1801042778bb233b7615103f12591ca02826a1ed2b69c4019b7a5
3
+ size 2874299056
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deda69bab7a93d17a549e6f50c9013febeb9b2827245003c62383bf7abadbd1a
3
+ size 2874299580
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36b170017181c0d24b583eb85845e1da54563b7a97a038edaf8e68f901d5242
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32589ea1f36249ec80e4c5020ca76a5bbc8bcee07c983b19820a3039c9209b0d
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff17fe42159f324816dd18f900bc61d9d6c60cbabc5dd7cdf7792a34d6eb7bc
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc1c7a60c4a152c2112aa58887159a0177b3d12944a066603b628630b872fc9
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137323bb566cb06756f4574015f654d460bb06405f26bfa0a62e5603b1554f08
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf97bcf4c2ca0e522530d10cd2d30a60c9c277cd13f9eb2be0d7ded58229b6c
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a179de03774ef8a5403ccf513ef544f85ea98fb09781ca7db5a0d7bba9bb32e
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeaaea1a2a47eda5e19ac23fc0bc815bbba66d200cd7e8ca21f71d9093698649
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d229905a19e9b9710449600522e4624e04c25ea9b5d4de751c2df92cf141196
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d504ff129672439ed724e4a0f148b0bb5cf04087049f8c13b4a908c0f017965b
3
+ size 2874298992
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d0f62150b903c479e686464d58e8d7cd0ffe17d58cf9bc7590bb214c82d188
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b9550fb4013fae2babb524e03d7c68c8adeff1cc93718b2f2c2198631943f3
3
+ size 2874299708
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6542b18283db476646e9dc45a240b046da8bb02a9371889d138acc286ceb02
3
+ size 2874299772
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c71ce0945c854828b93e1394fbbfa2ff8ae60d4eafa60033655f6157c49a812
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e2526f834adb2e71e878db3ae7111d1cfbaefaea1a324ed046ecc210e6e72e
3
+ size 2874299708
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d46dee87496eaa908b090e4dbca44253f6127f7addef15a6ca35c7dba419389
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f14e1eeefa58ac34fdf71a0613d5bb40e6056772c5d89b460250621b2e437dc
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b6b442847915cbbd4048e54fa2cca856b2e2235a45ff1fc7b078af557af049
3
+ size 2874299516
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96eaf507587d5140d7d4bb16fb87ff65d17f40a2c3e52b9484934e2f9074d19f
3
+ size 2874299644
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a1fa8927e54859a99474e50f08dd429d21eb01cd248680da451dcf8c393813
3
+ size 2874299260
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ee6ef2a08aa009f49076c908abe2382a7eacf0f46fe715dde07607a7263cc5
3
+ size 2874299504
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6e212cbd439426be14849853be7ab06a38e41fc1ae7ceacc2cb7ccde118d02
3
+ size 2874298940
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cdef2605d2027b7ad1df6f77346ed6d1771d715aa72d22699faec2adca9313b
3
+ size 2874298876
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46cc6eff4a5ab4f7db5991eeafdb0be51bad9add48aaaa1549df7fc483a4acd
3
+ size 2874299504
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb6957f7453be8b01282156ce1cd869feb2f787d0b8ec42818ecc74a280f9cf
3
+ size 2874299568
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09409214208ac949bbb0aee9b2475eb894c2df5df739949736616ad33927a82
3
+ size 2874299568
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd2a34b9f87ce9d050ac69e326a34d0ec4117151cf16aa4bf3facf26c0d3c4d
3
+ size 2874299504
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4075e8a143f826c2f40a52eed574254a5532016933d89aba4d2876919532d1a7
3
+ size 2874299440
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec46a8debc9bbf52139912d3e468d62bc2b1a80758c9af11d4255cd6d49948a9
3
+ size 2874299568
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0da267af3e7cde0c692d0c9bdfbfeae1912216c79d106dfc33fd0e4cb6bdc3f
3
+ size 2874299632
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/global_step2400/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7473a736054f911057f0ff20f0ec4bca2fb5c82b7e98f3a3aa5cfcd3d46f9878
3
+ size 21465485654
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step2400
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7558ebc4129171174cbd048fe2cb122468e12aecfedd8157207ed5045ead88e
3
+ size 4985055536
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a999eef959f00de28580a7e6c7554991e6d23ca3ede014664840f9757016db
3
+ size 4991496832
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011f10db5675d4e7a80f65945e5099d7f3fd22c23e15116a48a1476f29f7431c
3
+ size 4991496936
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bce5683ea8f483261143413f1d564a4731e9a17442c6582f8db2f5cee36d47
3
+ size 4969489856
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac1e7daca22acb04383f454edd83826fee7c30cac603f2cc81431f5201b2f12
3
+ size 1527220552
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "max_pixels": 12845056,
19
+ "merge_size": 2,
20
+ "min_pixels": 3136,
21
+ "n_fft": 400,
22
+ "n_samples": 4800000,
23
+ "nb_max_frames": 30000,
24
+ "padding_side": "right",
25
+ "padding_value": 0.0,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5OmniProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d0a42a76c6856b42516358f397705cff8f5ae2210de23f6abc8fc7d370ce43
3
+ size 15984
v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79d39762bf88c59ea58ab8c192f4d9721ab6eba78debc69a369654d4199af50
3
+ size 15984