Remove nested MultiDialect-ASR folder

MultiDialect-ASR/added_tokens.json

@@ -1,64 +0,0 @@
-{
-  "</think>": 151668,
-  "</tool_call>": 151658,
-  "</tool_response>": 151666,
-  "<asr_text>": 151704,
-  "<blank10>": 151686,
-  "<blank11>": 151687,
-  "<blank12>": 151688,
-  "<blank13>": 151689,
-  "<blank14>": 151690,
-  "<blank15>": 151691,
-  "<blank16>": 151692,
-  "<blank17>": 151693,
-  "<blank18>": 151694,
-  "<blank19>": 151695,
-  "<blank1>": 151677,
-  "<blank20>": 151696,
-  "<blank21>": 151697,
-  "<blank22>": 151698,
-  "<blank23>": 151699,
-  "<blank24>": 151700,
-  "<blank25>": 151701,
-  "<blank26>": 151702,
-  "<blank27>": 151703,
-  "<blank2>": 151678,
-  "<blank3>": 151679,
-  "<blank4>": 151680,
-  "<blank5>": 151681,
-  "<blank6>": 151682,
-  "<blank7>": 151683,
-  "<blank8>": 151684,
-  "<blank9>": 151685,
-  "<non_speech>": 151675,
-  "<think>": 151667,
-  "<tool_call>": 151657,
-  "<tool_response>": 151665,
-  "<tts_pad>": 151671,
-  "<tts_text_bos>": 151672,
-  "<tts_text_bos_single>": 151674,
-  "<tts_text_eod>": 151673,
-  "<|audio_end|>": 151670,
-  "<|audio_pad|>": 151676,
-  "<|audio_start|>": 151669,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

MultiDialect-ASR/args.json

@@ -1,404 +0,0 @@
-{
-  "output_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534",
-  "overwrite_output_dir": false,
-  "do_train": false,
-  "do_eval": false,
-  "do_predict": false,
-  "eval_strategy": "steps",
-  "prediction_loss_only": false,
-  "per_device_train_batch_size": 96,
-  "per_device_eval_batch_size": 96,
-  "per_gpu_train_batch_size": null,
-  "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 2,
-  "eval_accumulation_steps": null,
-  "eval_delay": 0,
-  "torch_empty_cache_steps": null,
-  "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": 1.0,
-  "max_steps": -1,
-  "lr_scheduler_type": "cosine",
-  "lr_scheduler_kwargs": null,
-  "warmup_ratio": 0.05,
-  "warmup_steps": 0,
-  "log_level": "passive",
-  "log_level_replica": "warning",
-  "log_on_each_node": true,
-  "logging_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534/runs",
-  "logging_strategy": "steps",
-  "logging_first_step": true,
-  "logging_steps": 5,
-  "logging_nan_inf_filter": true,
-  "save_strategy": "steps",
-  "save_steps": 500.0,
-  "save_total_limit": null,
-  "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": null,
-  "local_rank": 0,
-  "ddp_backend": null,
-  "tpu_num_cores": null,
-  "tpu_metrics_debug": false,
-  "debug": null,
-  "dataloader_drop_last": false,
-  "eval_steps": 500.0,
-  "dataloader_num_workers": 16,
-  "dataloader_prefetch_factor": null,
-  "past_index": -1,
-  "run_name": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534",
-  "disable_tqdm": null,
-  "remove_unused_columns": true,
-  "label_names": null,
-  "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": null,
-  "fsdp_transformer_layer_cls_to_wrap": null,
-  "accelerator_config": {
-    "dispatch_batches": false
-  },
-  "parallelism_config": null,
-  "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": 2,
-      "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": "adamw_torch_fused",
-  "optim_args": null,
-  "adafactor": false,
-  "group_by_length": false,
-  "length_column_name": "length",
-  "report_to": [
-    "tensorboard"
-  ],
-  "project": "huggingface",
-  "trackio_space_id": "trackio",
-  "ddp_find_unused_parameters": null,
-  "ddp_bucket_cap_mb": null,
-  "ddp_broadcast_buffers": null,
-  "dataloader_pin_memory": true,
-  "dataloader_persistent_workers": false,
-  "skip_memory_metrics": true,
-  "use_legacy_prediction_loop": false,
-  "push_to_hub": false,
-  "resume_from_checkpoint": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v6-20260707-132425/checkpoint-8500",
-  "hub_model_id": null,
-  "hub_strategy": "every_save",
-  "hub_token": null,
-  "hub_private_repo": null,
-  "hub_always_push": false,
-  "hub_revision": null,
-  "gradient_checkpointing": true,
-  "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
-  "include_inputs_for_metrics": false,
-  "include_for_metrics": [],
-  "eval_do_concat_batches": true,
-  "fp16_backend": "auto",
-  "push_to_hub_model_id": null,
-  "push_to_hub_organization": null,
-  "push_to_hub_token": null,
-  "mp_parameters": "",
-  "auto_find_batch_size": false,
-  "full_determinism": false,
-  "torchdynamo": null,
-  "ray_scope": "last",
-  "ddp_timeout": 18000000,
-  "torch_compile": false,
-  "torch_compile_backend": null,
-  "torch_compile_mode": null,
-  "include_tokens_per_second": false,
-  "include_num_input_tokens_seen": false,
-  "neftune_noise_alpha": null,
-  "optim_target_modules": null,
-  "batch_eval_metrics": false,
-  "eval_on_start": false,
-  "use_liger_kernel": false,
-  "liger_kernel_config": null,
-  "eval_use_gather_object": false,
-  "average_tokens_across_devices": true,
-  "sortish_sampler": false,
-  "predict_with_generate": false,
-  "generation_max_length": null,
-  "generation_num_beams": null,
-  "generation_config": null,
-  "tuner_backend": "peft",
-  "vit_gradient_checkpointing": true,
-  "router_aux_loss_coef": 0.0,
-  "enable_dft_loss": false,
-  "enable_channel_loss": false,
-  "safe_serialization": true,
-  "max_shard_size": "5GB",
-  "check_model": false,
-  "acc_strategy": "token",
-  "train_dataloader_shuffle": true,
-  "max_epochs": null,
-  "aligner_lr": null,
-  "vit_lr": null,
-  "use_logits_to_keep": null,
-  "ds3_gather_for_generation": true,
-  "resume_only_model": false,
-  "optimizer": null,
-  "loss_type": null,
-  "eval_metric": null,
-  "callbacks": [],
-  "early_stop_interval": null,
-  "eval_use_evalscope": false,
-  "eval_dataset": [],
-  "eval_dataset_args": null,
-  "eval_limit": null,
-  "eval_generation_config": null,
-  "extra_eval_args": null,
-  "tuner_type": "full",
-  "use_galore": false,
-  "galore_target_modules": null,
-  "galore_rank": 128,
-  "galore_update_proj_gap": 50,
-  "galore_scale": 1.0,
-  "galore_proj_type": "std",
-  "galore_optim_per_parameter": false,
-  "galore_with_embedding": false,
-  "galore_quantization": false,
-  "galore_proj_quant": false,
-  "galore_proj_bits": 4,
-  "galore_proj_group_size": 256,
-  "galore_cos_threshold": 0.4,
-  "galore_gamma_proj": 2,
-  "galore_queue_size": 5,
-  "lisa_activated_layers": 0,
-  "lisa_step_interval": 20,
-  "use_flash_ckpt": false,
-  "use_ray": false,
-  "ray_exp_name": null,
-  "device_groups": null,
-  "model": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",
-  "model_type": "qwen3_asr",
-  "model_revision": null,
-  "task_type": "causal_lm",
-  "torch_dtype": "bfloat16",
-  "attn_impl": "flash_attention_2",
-  "experts_impl": null,
-  "new_special_tokens": [],
-  "num_labels": null,
-  "problem_type": null,
-  "rope_scaling": null,
-  "device_map": null,
-  "max_memory": {},
-  "max_model_len": null,
-  "local_repo_path": null,
-  "init_strategy": null,
-  "template": "qwen3_asr",
-  "system": null,
-  "max_length": 1024,
-  "truncation_strategy": "delete",
-  "max_pixels": null,
-  "agent_template": null,
-  "norm_bbox": null,
-  "use_chat_template": true,
-  "padding_side": "right",
-  "padding_free": true,
-  "loss_scale": "default",
-  "sequence_parallel_size": 1,
-  "is_binary_loss_scale": null,
-  "template_backend": "swift",
-  "response_prefix": null,
-  "enable_thinking": null,
-  "preserve_thinking": null,
-  "add_non_thinking_prefix": true,
-  "disable_ignore_empty_think": false,
-  "dataset": [
-    "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/data/train_v8_processed/train_new.jsonl"
-  ],
-  "val_dataset": [
-    "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/data/train_v8_processed/dev.jsonl"
-  ],
-  "cached_dataset": [],
-  "cached_val_dataset": [],
-  "split_dataset_ratio": 0.0,
-  "dataset_num_proc": 8,
-  "load_from_cache_file": true,
-  "dataset_shuffle": true,
-  "val_dataset_shuffle": false,
-  "streaming": false,
-  "interleave_prob": null,
-  "stopping_strategy": "first_exhausted",
-  "shuffle_buffer_size": 1000,
-  "download_mode": "reuse_dataset_if_exists",
-  "columns": {},
-  "strict": false,
-  "disable_auto_column_mapping": false,
-  "model_name": null,
-  "model_author": null,
-  "custom_dataset_info": [],
-  "quant_method": null,
-  "quant_bits": null,
-  "hqq_axis": null,
-  "bnb_4bit_compute_dtype": "bfloat16",
-  "bnb_4bit_quant_type": "nf4",
-  "bnb_4bit_use_double_quant": true,
-  "bnb_4bit_quant_storage": null,
-  "max_new_tokens": 64,
-  "temperature": 0.0,
-  "top_k": null,
-  "top_p": null,
-  "repetition_penalty": null,
-  "num_beams": 1,
-  "stream": false,
-  "stop_words": [],
-  "logprobs": false,
-  "top_logprobs": null,
-  "structured_outputs_regex": null,
-  "adapters": [],
-  "external_plugins": [],
-  "custom_register_path": [],
-  "model_kwargs": {},
-  "enable_npu_model_patch": true,
-  "load_args": false,
-  "load_data_args": false,
-  "packing": false,
-  "packing_length": null,
-  "packing_num_proc": 1,
-  "lazy_tokenize": true,
-  "use_hf": false,
-  "ignore_args_error": false,
-  "use_swift_lora": false,
-  "freeze_parameters": [],
-  "freeze_parameters_regex": null,
-  "freeze_parameters_ratio": 0.0,
-  "trainable_parameters": [
-    "thinker.audio_tower.proj1",
-    "thinker.audio_tower.proj2"
-  ],
-  "trainable_parameters_regex": null,
-  "freeze_llm": false,
-  "freeze_vit": false,
-  "freeze_aligner": false,
-  "target_modules": [
-    "all-linear"
-  ],
-  "target_regex": null,
-  "target_parameters": null,
-  "modules_to_save": [],
-  "lora_rank": 8,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "lora_bias": "none",
-  "lora_dtype": null,
-  "lorap_lr_ratio": null,
-  "use_rslora": false,
-  "use_dora": false,
-  "lora_ga_batch_size": 2,
-  "lora_ga_iters": 2,
-  "lora_ga_max_length": 1024,
-  "lora_ga_direction": "ArB2r",
-  "lora_ga_scale": "stable",
-  "lora_ga_stable_gamma": 16,
-  "init_weights": true,
-  "fourier_n_frequency": 2000,
-  "fourier_scaling": 300.0,
-  "boft_block_size": 4,
-  "boft_block_num": 0,
-  "boft_n_butterfly_factor": 1,
-  "boft_dropout": 0.0,
-  "vera_rank": 256,
-  "vera_projection_prng_key": 0,
-  "vera_dropout": 0.0,
-  "vera_d_initial": 0.1,
-  "adapter_act": "gelu",
-  "adapter_length": 128,
-  "adalora_target_r": 8,
-  "adalora_init_r": 12,
-  "adalora_tinit": 0,
-  "adalora_tfinal": 0,
-  "adalora_deltaT": 1,
-  "adalora_beta1": 0.85,
-  "adalora_beta2": 0.85,
-  "adalora_orth_reg_weight": 0.5,
-  "llamapro_num_new_blocks": 4,
-  "llamapro_num_groups": null,
-  "reft_layer_key": null,
-  "reft_layers": null,
-  "reft_rank": 4,
-  "reft_intervention_type": "LoreftIntervention",
-  "reft_args": null,
-  "swanlab_token": null,
-  "swanlab_project": "ms-swift",
-  "swanlab_workspace": null,
-  "swanlab_exp_name": null,
-  "swanlab_notification_method": null,
-  "swanlab_webhook_url": null,
-  "swanlab_secret": null,
-  "swanlab_sender_email": null,
-  "swanlab_receiver_email": null,
-  "swanlab_smtp_server": null,
-  "swanlab_smtp_port": null,
-  "swanlab_email_language": "zh",
-  "swanlab_mode": "cloud",
-  "add_version": true,
-  "create_checkpoint_symlink": false,
-  "zero_hpz_partition_size": null,
-  "deepspeed_autotp_size": null,
-  "swift_version": "4.3.1",
-  "ckpt_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",
-  "rank": 0,
-  "global_world_size": 8,
-  "local_world_size": 8,
-  "model_suffix": "checkpoint-10000-merged",
-  "model_info": "ModelInfo(model_type='qwen3_asr', model_dir='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged', torch_dtype=torch.bfloat16, max_model_len=65536, quant_method=None, quant_bits=None, rope_scaling={'interleaved': True, 'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='qwen3_asr', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-ASR-1.7B', hf_model_id='Qwen/Qwen3-ASR-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-ASR-0.6B', hf_model_id='Qwen/Qwen3-ASR-0.6B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_asr', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3ASRLoader'>, template=None, model_arch=MultiModelKeys(arch_name='qwen3_asr', 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.proj1', 'thinker.audio_tower.proj2'], vision_tower=['thinker.audio_tower'], generator=[]), mcore_model_type=None, architectures=['Qwen3ASRForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['qwen-asr', 'transformers==4.57.6'], tags=['audio'])",
-  "model_dir": "/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en_lora/v2-20260629-195144/checkpoint-10000-merged",
-  "template_meta": "QwenTemplateMeta(template_type='qwen3_asr', prefix=['<|im_start|>system\\n<|im_end|>\\n'], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3ASRTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
-  "_val_dataset_exists": true,
-  "hub": "<class 'swift.hub.hub.MSHub'>",
-  "evaluation_strategy": "steps",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534', 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=96, per_device_eval_batch_size=96, 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=1.0, max_steps=-1, 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='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534/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=500, save_total_limit=None, 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=500, dataloader_num_workers=16, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v7-20260708-235534', 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': 2, '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_FUSED: 'adamw_torch_fused'>, 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='/home/work_nfs23/sywang/code/ms-swift/examples/qwen3asr/exp3/exp_stage6_zh_en/v6-20260707-132425/checkpoint-8500', 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={'use_reentrant': False}, 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, safe_serialization=True, max_shard_size='5GB', check_model=False, 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, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
-}

MultiDialect-ASR/chat_template.jinja

@@ -1,31 +0,0 @@
-{%- set ns = namespace(system_text="") -%}
-{%- for m in messages -%}
-  {%- if m.role == 'system' -%}
-    {%- if m.content is string -%}
-      {%- set ns.system_text = ns.system_text + m.content -%}
-    {%- else -%}
-      {%- for c in m.content -%}
-        {%- if c.type == 'text' and (c.text is defined) -%}
-          {%- set ns.system_text = ns.system_text + c.text -%}
-        {%- endif -%}
-      {%- endfor -%}
-    {%- endif -%}
-  {%- endif -%}
-{%- endfor -%}
-
-{%- set ns2 = namespace(audio_tokens="") -%}
-{%- for m in messages -%}
-  {%- if m.content is not string -%}
-    {%- for c in m.content -%}
-      {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}
-        {%- set ns2.audio_tokens = ns2.audio_tokens + "<|audio_start|><|audio_pad|><|audio_end|>" -%}
-      {%- endif -%}
-    {%- endfor -%}
-  {%- endif -%}
-{%- endfor -%}
-
-{{- '<|im_start|>system\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\n' -}}
-{{- '<|im_start|>user\n' + ns2.audio_tokens + '<|im_end|>\n' -}}
-{%- if add_generation_prompt -%}
-{{- '<|im_start|>assistant\n' -}}
-{%- endif -%}

MultiDialect-ASR/config.json

@@ -1,228 +0,0 @@
-{
-  "architectures": [
-    "Qwen3ASRForConditionalGeneration"
-  ],
-  "dtype": "bfloat16",
-  "eos_token_id": 151645,
-  "hidden_size": 2048,
-  "keys_to_ignore_at_inference": [
-    "past_key_values"
-  ],
-  "model_type": "qwen3_asr",
-  "pad_token_id": 151643,
-  "support_languages": [
-    "Chinese",
-    "English",
-    "Cantonese",
-    "Arabic",
-    "German",
-    "French",
-    "Spanish",
-    "Portuguese",
-    "Indonesian",
-    "Italian",
-    "Korean",
-    "Russian",
-    "Thai",
-    "Vietnamese",
-    "Japanese",
-    "Turkish",
-    "Hindi",
-    "Malay",
-    "Dutch",
-    "Swedish",
-    "Danish",
-    "Finnish",
-    "Polish",
-    "Czech",
-    "Filipino",
-    "Persian",
-    "Greek",
-    "Romanian",
-    "Hungarian",
-    "Macedonian"
-  ],
-  "thinker_config": {
-    "architectures": [
-      "Qwen3ASRForConditionalGeneration"
-    ],
-    "audio_config": {
-      "_name_or_path": "",
-      "activation_dropout": 0,
-      "activation_function": "gelu",
-      "add_cross_attention": false,
-      "architectures": null,
-      "attention_dropout": 0,
-      "bad_words_ids": null,
-      "begin_suppress_tokens": null,
-      "bos_token_id": null,
-      "chunk_size_feed_forward": 0,
-      "conv_chunksize": 500,
-      "cross_attention_hidden_size": null,
-      "d_model": 1024,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "downsample_hidden_size": 480,
-      "dropout": 0,
-      "dtype": "bfloat16",
-      "early_stopping": false,
-      "encoder_attention_heads": 16,
-      "encoder_ffn_dim": 4096,
-      "encoder_layers": 24,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": null,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "initializer_range": 0.02,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "max_source_positions": 1500,
-      "min_length": 0,
-      "model_type": "qwen3_asr_audio_encoder",
-      "n_window": 50,
-      "n_window_infer": 800,
-      "no_repeat_ngram_size": 0,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_hidden_layers": 24,
-      "num_mel_bins": 128,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_dim": 2048,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": null,
-      "prefix": null,
-      "problem_type": null,
-      "pruned_heads": {},
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "scale_embedding": false,
-      "sep_token_id": null,
-      "suppress_tokens": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": true,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torchscript": false,
-      "typical_p": 1.0,
-      "use_bfloat16": false
-    },
-    "audio_end_token_id": 151670,
-    "audio_start_token_id": 151669,
-    "audio_token_id": 151676,
-    "dtype": "bfloat16",
-    "initializer_range": 0.02,
-    "model_type": "qwen3_asr_thinker",
-    "text_config": {
-      "_name_or_path": "",
-      "add_cross_attention": false,
-      "architectures": null,
-      "attention_bias": false,
-      "attention_dropout": 0.0,
-      "bad_words_ids": null,
-      "begin_suppress_tokens": null,
-      "bos_token_id": null,
-      "chunk_size_feed_forward": 0,
-      "cross_attention_hidden_size": null,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "dtype": "bfloat16",
-      "early_stopping": false,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": null,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "head_dim": 128,
-      "hidden_act": "silu",
-      "hidden_size": 2048,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "initializer_range": 0.02,
-      "intermediate_size": 6144,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "max_position_embeddings": 65536,
-      "min_length": 0,
-      "model_type": "qwen3_asr_text",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 16,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_hidden_layers": 28,
-      "num_key_value_heads": 8,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": 151643,
-      "prefix": null,
-      "problem_type": null,
-      "pruned_heads": {},
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "rms_norm_eps": 1e-06,
-      "rope_scaling": {
-        "interleaved": true,
-        "mrope_interleaved": true,
-        "mrope_section": [
-          24,
-          20,
-          20
-        ],
-        "rope_type": "default",
-        "type": "default"
-      },
-      "rope_theta": 1000000,
-      "sep_token_id": null,
-      "suppress_tokens": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": true,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torchscript": false,
-      "typical_p": 1.0,
-      "use_bfloat16": false,
-      "use_cache": false,
-      "vocab_size": 151936
-    },
-    "user_token_id": 872
-  },
-  "transformers_version": "4.57.6"
-}

MultiDialect-ASR/generation_config.json

@@ -1,8 +0,0 @@
-{
-  "_from_model_config": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "transformers_version": "4.57.6"
-}

MultiDialect-ASR/latest

@@ -1 +0,0 @@
-global_step16000

MultiDialect-ASR/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dc75555d5558ebcdf84a6f4121bf7613e22d251d1d0110b35fbdc5054643bc0a
-size 4698521600

MultiDialect-ASR/preprocessor_config.json

@@ -1,14 +0,0 @@
-{
-  "chunk_length": 30,
-  "dither": 0.0,
-  "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 128,
-  "hop_length": 160,
-  "n_fft": 400,
-  "n_samples": 480000,
-  "nb_max_frames": 3000,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "processor_class": "Qwen3ASRProcessor",
-  "return_attention_mask": true
-}

MultiDialect-ASR/special_tokens_map.json

@@ -1,44 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>",
-    "<|audio_start|>",
-    "<|audio_end|>",
-    "<tts_pad>",
-    "<tts_text_bos>",
-    "<tts_text_bos_single>",
-    "<|audio_pad|>"
-  ],
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "image_token": "<|image_pad|>",
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

MultiDialect-ASR/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd2a97b55c8f7f9c328c73ee9b9178771037e9f566dfca8e238a063d41cbac92
-size 11429377

MultiDialect-ASR/tokenizer_config.json

@@ -1,549 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151669": {
-      "content": "<|audio_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151670": {
-      "content": "<|audio_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151671": {
-      "content": "<tts_pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151672": {
-      "content": "<tts_text_bos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151673": {
-      "content": "<tts_text_eod>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151674": {
-      "content": "<tts_text_bos_single>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151675": {
-      "content": "<non_speech>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151676": {
-      "content": "<|audio_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151677": {
-      "content": "<blank1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151678": {
-      "content": "<blank2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151679": {
-      "content": "<blank3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151680": {
-      "content": "<blank4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151681": {
-      "content": "<blank5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151682": {
-      "content": "<blank6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151683": {
-      "content": "<blank7>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151684": {
-      "content": "<blank8>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151685": {
-      "content": "<blank9>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151686": {
-      "content": "<blank10>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151687": {
-      "content": "<blank11>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151688": {
-      "content": "<blank12>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151689": {
-      "content": "<blank13>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151690": {
-      "content": "<blank14>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151691": {
-      "content": "<blank15>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151692": {
-      "content": "<blank16>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151693": {
-      "content": "<blank17>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151694": {
-      "content": "<blank18>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151695": {
-      "content": "<blank19>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151696": {
-      "content": "<blank20>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151697": {
-      "content": "<blank21>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151698": {
-      "content": "<blank22>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151699": {
-      "content": "<blank23>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151700": {
-      "content": "<blank24>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151701": {
-      "content": "<blank25>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151702": {
-      "content": "<blank26>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151703": {
-      "content": "<blank27>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151704": {
-      "content": "<asr_text>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>",
-    "<|audio_start|>",
-    "<|audio_end|>",
-    "<tts_pad>",
-    "<tts_text_bos>",
-    "<tts_text_bos_single>",
-    "<|audio_pad|>"
-  ],
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "image_token": "<|image_pad|>",
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "processor_class": "Qwen3ASRProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

MultiDialect-ASR/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6ab0e00f239679378219e95b7e3a48b66077abb2ecc2eb61cbe4ca0a1b7c83e
-size 9489

MultiDialect-ASR/zero_to_fp32.py

@@ -1,760 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example:
-#   python zero_to_fp32.py . output_dir/
-#   or
-#   python zero_to_fp32.py . output_dir/ --safe_serialization
-
-import argparse
-import torch
-import glob
-import math
-import os
-import re
-import gc
-import json
-import numpy as np
-from tqdm import tqdm
-from collections import OrderedDict
-from dataclasses import dataclass
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-from deepspeed.utils import logger
-from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
-                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
-                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
-
-
-@dataclass
-class zero_model_state:
-    buffers: dict()
-    param_shapes: dict()
-    shared_params: list
-    ds_version: int
-    frozen_param_shapes: dict()
-    frozen_param_fragments: dict()
-
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def atoi(text):
-    return int(text) if text.isdigit() else text
-
-
-def natural_keys(text):
-    '''
-    alist.sort(key=natural_keys) sorts in human order
-    http://nedbatchelder.com/blog/200712/human_sorting.html
-    (See Toothy's implementation in the comments)
-    '''
-    return [atoi(c) for c in re.split(r'(\d+)', text)]
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage <= 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_checkpoint_files(checkpoint_dir, glob_pattern):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
-
-    if len(ckpt_files) == 0:
-        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
-
-    return ckpt_files
-
-
-def get_optim_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
-
-
-def get_model_state_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
-
-
-def parse_model_states(files):
-    zero_model_states = []
-    for file in files:
-        state_dict = torch.load(file, map_location=device, weights_only=False)
-
-        if BUFFER_NAMES not in state_dict:
-            raise ValueError(f"{file} is not a model state checkpoint")
-        buffer_names = state_dict[BUFFER_NAMES]
-        if debug:
-            print("Found buffers:", buffer_names)
-
-        # recover just the buffers while restoring them to fp32 if they were saved in fp16
-        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
-        param_shapes = state_dict[PARAM_SHAPES]
-
-        # collect parameters that are included in param_shapes
-        param_names = []
-        for s in param_shapes:
-            for name in s.keys():
-                param_names.append(name)
-
-        # update with frozen parameters
-        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
-        if frozen_param_shapes is not None:
-            if debug:
-                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
-            param_names += list(frozen_param_shapes.keys())
-
-        # handle shared params
-        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
-
-        ds_version = state_dict.get(DS_VERSION, None)
-
-        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
-
-        z_model_state = zero_model_state(buffers=buffers,
-                                         param_shapes=param_shapes,
-                                         shared_params=shared_params,
-                                         ds_version=ds_version,
-                                         frozen_param_shapes=frozen_param_shapes,
-                                         frozen_param_fragments=frozen_param_fragments)
-        zero_model_states.append(z_model_state)
-
-    return zero_model_states
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-    total_files = len(files)
-    state_dicts = []
-    for f in tqdm(files, desc='Loading checkpoint shards'):
-        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
-        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
-        # and also handle the case where it was already removed by another helper script
-        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
-        state_dicts.append(state_dict)
-
-    if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
-    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
-
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage <= 2:
-        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
-    elif zero_stage == 3:
-        fp32_groups_key = FP32_FLAT_GROUPS
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
-    return zero_stage, world_size, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_files = get_model_state_files(ds_checkpoint_dir)
-
-    zero_model_states = parse_model_states(model_files)
-    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
-
-    if zero_stage <= 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-
-
-def _zero2_merge_frozen_params(state_dict, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
-
-    if debug:
-        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
-        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        state_dict[name] = frozen_param_fragments[name]
-
-        if debug:
-            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _has_callable(obj, fn):
-    attr = getattr(obj, fn, None)
-    return callable(attr)
-
-
-def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum(
-        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero2_merge_frozen_params(state_dict, zero_model_states)
-
-    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    if debug:
-        for i in range(world_size):
-            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
-            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in zero_model_states[0].frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
-        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-class GatheredTensor:
-    """
-    A pseudo tensor that collects partitioned weights.
-    It is more memory efficient when there are multiple groups.
-    """
-
-    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
-        self.flat_groups = flat_groups
-        self.flat_groups_offset = flat_groups_offset
-        self.offset = offset
-        self.partitioned_numel = partitioned_numel
-        self.shape = shape
-        self.dtype = self.flat_groups[0][0].dtype
-
-    def contiguous(self):
-        """
-        Merge partitioned weights from flat_groups into a single tensor.
-        """
-        end_idx = self.offset + self.partitioned_numel
-        world_size = len(self.flat_groups)
-        pad_flat_param_chunks = []
-
-        for rank_i in range(world_size):
-            # for each rank, we need to collect weights from related group/groups
-            flat_groups_at_rank_i = self.flat_groups[rank_i]
-            start_group_id = None
-            end_group_id = None
-            for group_id in range(len(self.flat_groups_offset)):
-                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
-                    start_group_id = group_id
-                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
-                    end_group_id = group_id
-                    break
-            # collect weights from related group/groups
-            for group_id in range(start_group_id, end_group_id + 1):
-                flat_tensor = flat_groups_at_rank_i[group_id]
-                start_offset = self.offset - self.flat_groups_offset[group_id]
-                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
-                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
-
-        # collect weights from all ranks
-        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
-        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
-        return param
-
-
-def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
-
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        avail_numel = fp32_flat_groups[0].numel() * world_size
-        print(f"Trainable params: Have {avail_numel} numels to process.")
-        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
-    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # memory efficient tensor
-        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
-        state_dict[name] = tensor
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
-
-    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def to_torch_tensor(state_dict, return_empty_tensor=False):
-    """
-    Convert state_dict of GatheredTensor to torch tensor
-    """
-    torch_state_dict = {}
-    converted_tensors = {}
-    for name, tensor in state_dict.items():
-        tensor_id = id(tensor)
-        if tensor_id in converted_tensors:  # shared tensors
-            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
-            torch_state_dict[name] = shared_tensor
-        else:
-            converted_tensors[tensor_id] = name
-            if return_empty_tensor:
-                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
-            else:
-                torch_state_dict[name] = tensor.contiguous()
-    return torch_state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                             tag=None,
-                                             exclude_frozen_parameters=False,
-                                             lazy_mode=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
-          Convert the pesduo tensor to torch tensor by ``.contiguous()``
-
-    Returns:
-        - pytorch ``state_dict``
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
-    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint. Or you can load state_dict in lazy mode ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
-        for name, lazy_tensor in state_dict.item():
-            tensor = lazy_tensor.contiguous()  # to cpu
-            print(name, tensor)
-            # del tensor to release memory if it no longer in use
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
-    if lazy_mode:
-        return state_dict
-    else:
-        return to_torch_tensor(state_dict)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
-                                               output_dir,
-                                               max_shard_size="5GB",
-                                               safe_serialization=False,
-                                               tag=None,
-                                               exclude_frozen_parameters=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_dir``: directory to the pytorch fp32 state_dict output files
-        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
-        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-    """
-
-    # Dependency pre-check
-    if safe_serialization:
-        try:
-            from safetensors.torch import save_file
-        except ImportError:
-            print('If you want to use `safe_serialization`, please `pip install safetensors`')
-            raise
-    if max_shard_size is not None:
-        try:
-            from huggingface_hub import split_torch_state_dict_into_shards
-        except ImportError:
-            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
-            raise
-
-    # Convert zero checkpoint to state_dict
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                                          tag,
-                                                          exclude_frozen_parameters,
-                                                          lazy_mode=True)
-
-    # Shard the model if it is too big.
-    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
-    if max_shard_size is not None:
-        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
-        # an memory-efficient approach for sharding
-        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
-        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
-                                                              filename_pattern=filename_pattern,
-                                                              max_shard_size=max_shard_size)
-    else:
-        from collections import namedtuple
-        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
-        state_dict_split = StateDictSplit(is_sharded=False,
-                                          filename_to_tensors={weights_name: list(state_dict.keys())})
-
-    # Save the model by shard
-    os.makedirs(output_dir, exist_ok=True)
-    filename_to_tensors = state_dict_split.filename_to_tensors.items()
-    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
-        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
-        shard_state_dict = to_torch_tensor(shard_state_dict)
-        output_path = os.path.join(output_dir, shard_file)
-        if safe_serialization:
-            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
-        else:
-            torch.save(shard_state_dict, output_path)
-        # release the memory of current shard
-        for tensor_name in list(shard_state_dict.keys()):
-            del state_dict[tensor_name]
-            del shard_state_dict[tensor_name]
-        del shard_state_dict
-        gc.collect()
-
-    # Save index if sharded
-    if state_dict_split.is_sharded:
-        index = {
-            "metadata": state_dict_split.metadata,
-            "weight_map": state_dict_split.tensor_to_filename,
-        }
-        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
-        save_index_file = os.path.join(output_dir, save_index_file)
-        with open(save_index_file, "w", encoding="utf-8") as f:
-            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
-            f.write(content)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info("Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info("Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("checkpoint_dir",
-                        type=str,
-                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument("output_dir",
-                        type=str,
-                        help="directory to the pytorch fp32 state_dict output files"
-                        "(e.g. path/checkpoint-12-output/)")
-    parser.add_argument(
-        "--max_shard_size",
-        type=str,
-        default="5GB",
-        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
-        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
-        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
-        "without CPU OOM issues.")
-    parser.add_argument(
-        "--safe_serialization",
-        default=False,
-        action='store_true',
-        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
-    parser.add_argument("-t",
-                        "--tag",
-                        type=str,
-                        default=None,
-                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
-    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
-                                               args.output_dir,
-                                               max_shard_size=args.max_shard_size,
-                                               safe_serialization=args.safe_serialization,
-                                               tag=args.tag,
-                                               exclude_frozen_parameters=args.exclude_frozen_parameters)