Upload folder using huggingface_hub

added_tokens.json

@@ -1,5 +1,24 @@
 {
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+  "<|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
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/modelscope/hub/qwen/Qwen2-7B-Instruct",
+  "_name_or_path": "/root/.cache/modelscope/hub/qwen/Qwen2___5-7B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

configuration.json

@@ -1,4 +1 @@
-{
-    "framework": "Pytorch",
-    "task": "text-generation"
-}
+{}

generation_config.json

@@ -1,10 +1,12 @@
 {
+  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": 151645,
   "max_new_tokens": 2048,
   "pad_token_id": 151643,
-  "temperature": 0.3,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
   "top_k": 20,
-  "top_p": 0.7,
+  "top_p": 0.8,
   "transformers_version": "4.41.2"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9852a67fddb619b46917f6da48e6d4e59d3849f277ec7dd8a2685d39391702
+oid sha256:679d7d16ba922f003f2a18ded787696113850cc460104bd38b1925db1a4f9756
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695a7ec7b365a8411e3f301f937a22224c669ff8633e80f2f168ccd6dec5fb08
+oid sha256:72606189477258d80f803153aabc53f55dca6450308856e4612d14b41d6d40fd
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38d29f7f3fd1e081379c2294298a346413a831ea4a5cf1845e90f1871f34c5a
+oid sha256:1054e5ff0b0f28415800a4e083d7b0988f666c0f02249b78b6d7bfa971f2f201
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2d09c439927af4e903ceebc4f350fb45ee891c794475a7001650ff5ca2b998
+oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
 size 1089994880

sft_args.json

@@ -1,54 +1,46 @@
 {
-  "model_type": "qwen2-7b-instruct",
-  "model_id_or_path": "qwen/Qwen2-7B-Instruct",
+  "model_type": "qwen2_5-7b-instruct",
+  "model_id_or_path": "qwen/Qwen2.5-7B-Instruct",
   "model_revision": "master",
+  "full_determinism": false,
   "sft_type": "full",
-  "freeze_parameters": 0.0,
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
-  "template_type": "qwen",
-  "output_dir": "/root/swift/esft/output/qwen2-7b-instruct/v12-20240702-120746",
+  "template_type": "qwen2_5",
+  "output_dir": "/root/swift/esft/output/qwen2_5-7b-instruct/v1-20240928-133855",
   "add_output_dir_suffix": true,
   "ddp_backend": "nccl",
   "ddp_find_unused_parameters": null,
   "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
   "seed": 42,
-  "resume_from_checkpoint": null,
+  "resume_from_checkpoint": "/root/swift/esft/output/qwen2_5-7b-instruct/v0-20240928-125720/checkpoint-150",
   "resume_only_model": false,
   "ignore_data_skip": false,
   "dtype": "bf16",
   "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": {},
+  "loss_name": null,
   "dataset": [
     "dataset/moni_dataset.jsonl",
-    "dataset/moni_dataset.jsonl",
-    "dataset/moni_dataset.jsonl",
-    "dataset/moni_dataset.jsonl",
-    "dataset/covid_new.jsonl",
-    "dataset/covid_new.jsonl",
+    "dataset/moni_dataset_en.jsonl",
     "dataset/covid_new.jsonl",
-    "dataset/covid_new.jsonl",
-    "dataset/covid_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "HF::roleplay-base#2500",
-    "iic/MSAgent-MultiRole#1000",
-    "AI-ModelScope/wikipedia-cn-20230720-filtered#500",
-    "AI-ModelScope/ruozhiba#500",
-    "modelscope/chinese-poetry-collection#1000",
-    "AI-ModelScope/webnovel_cn#500"
+    "AI-ModelScope/deepctrl-sft-data:default#1600",
+    "AI-ModelScope/deepctrl-sft-data:en#1100",
+    "AI-ModelScope/ruozhiba#250"
   ],
   "val_dataset": [
-    "dataset/ds_new.jsonl"
+    "dataset/moni_dataset.jsonl#50"
   ],
   "dataset_seed": 42,
   "dataset_test_ratio": 0.0,
@@ -56,9 +48,12 @@
   "loss_scale_config_path": "/root/swift/swift_new/lib/python3.11/site-packages/swift/llm/agent/default_loss_scale_config.json",
   "system": "None",
   "tools_prompt": "react_en",
-  "max_length": 1500,
+  "max_length": 1344,
   "truncation_strategy": "delete",
   "check_dataset_strategy": "warning",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
   "model_name": [
     null,
     null
@@ -75,48 +70,49 @@
   "bnb_4bit_quant_type": "nf4",
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
-  "lora_target_modules": [
-    "q_proj",
-    "k_proj",
-    "v_proj"
+  "rescale_image": -1,
+  "target_modules": [
+    "ALL"
   ],
+  "target_regex": null,
+  "modules_to_save": [],
   "lora_rank": 16,
   "lora_alpha": 32,
-  "lora_dropout_p": 0.06,
+  "lora_dropout": 0.05,
   "lora_bias_trainable": "none",
-  "lora_modules_to_save": [],
-  "lora_dtype": null,
+  "lora_dtype": "AUTO",
   "lora_lr_ratio": null,
   "use_rslora": false,
   "use_dora": false,
-  "init_lora_weights": true,
+  "init_lora_weights": "true",
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
   "rope_scaling": null,
   "boft_block_size": 4,
   "boft_block_num": 0,
   "boft_n_butterfly_factor": 1,
-  "boft_target_modules": [
-    "DEFAULT"
-  ],
   "boft_dropout": 0.0,
-  "boft_modules_to_save": [],
   "vera_rank": 256,
-  "vera_target_modules": [
-    "DEFAULT"
-  ],
   "vera_projection_prng_key": 0,
   "vera_dropout": 0.0,
   "vera_d_initial": 0.1,
-  "vera_modules_to_save": [],
   "adapter_act": "gelu",
   "adapter_length": 128,
   "use_galore": false,
-  "galore_rank": 128,
   "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,
   "adalora_target_r": 8,
   "adalora_init_r": 12,
   "adalora_tinit": 0,
@@ -125,39 +121,45 @@
   "adalora_beta1": 0.85,
   "adalora_beta2": 0.85,
   "adalora_orth_reg_weight": 0.5,
-  "ia3_target_modules": [
-    "DEFAULT"
-  ],
   "ia3_feedforward_modules": [],
-  "ia3_modules_to_save": [],
   "llamapro_num_new_blocks": 4,
   "llamapro_num_groups": null,
   "neftune_noise_alpha": null,
   "neftune_backend": "transformers",
   "lisa_activated_layers": 0,
   "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
   "gradient_checkpointing": true,
   "deepspeed": null,
   "batch_size": 2,
-  "eval_batch_size": 2,
-  "num_train_epochs": 6,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 80,
   "max_steps": -1,
   "optim": "adamw_torch",
   "adam_beta1": 0.9,
-  "adam_beta2": 0.999,
+  "adam_beta2": 0.95,
   "adam_epsilon": 1e-08,
   "learning_rate": 0.0001,
   "weight_decay": 0.1,
-  "gradient_accumulation_steps": 4,
-  "max_grad_norm": 0.5,
+  "gradient_accumulation_steps": 16,
+  "max_grad_norm": 1.0,
   "predict_with_generate": false,
-  "lr_scheduler_type": "linear",
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
   "warmup_ratio": 0.03,
+  "warmup_steps": 0,
   "eval_steps": 50,
   "save_steps": 50,
   "save_only_model": false,
   "save_total_limit": null,
   "logging_steps": 5,
+  "acc_steps": 1,
   "dataloader_num_workers": 1,
   "dataloader_pin_memory": true,
   "dataloader_drop_last": false,
@@ -165,7 +167,7 @@
   "hub_model_id": null,
   "hub_token": null,
   "hub_private_repo": false,
-  "push_hub_strategy": "push_best",
+  "hub_strategy": "every_save",
   "test_oom_error": false,
   "disable_tqdm": false,
   "lazy_tokenize": false,
@@ -173,12 +175,12 @@
   "use_flash_attn": true,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/root/swift/esft/output/qwen2-7b-instruct/v12-20240702-120746/runs",
+  "logging_dir": "/root/swift/esft/output/qwen2_5-7b-instruct/v1-20240928-133855/runs",
   "report_to": [
     "tensorboard"
   ],
   "acc_strategy": "token",
-  "save_on_each_node": true,
+  "save_on_each_node": false,
   "evaluation_strategy": "steps",
   "save_strategy": "steps",
   "save_safetensors": true,
@@ -187,13 +189,14 @@
   "local_repo_path": null,
   "custom_register_path": null,
   "custom_dataset_info": "/root/swift/dataset/ds_info.json",
-  "device_map_config_path": null,
+  "device_map_config": null,
+  "device_max_memory": [],
   "max_new_tokens": 2048,
-  "do_sample": true,
-  "temperature": 0.3,
-  "top_k": 20,
-  "top_p": 0.7,
-  "repetition_penalty": 1.0,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
   "num_beams": 1,
   "fsdp": "",
   "fsdp_config": null,
@@ -216,19 +219,40 @@
   "neftune_alpha": null,
   "deepspeed_config_path": null,
   "model_cache_dir": null,
+  "lora_dropout_p": 0.05,
+  "lora_target_modules": [
+    "ALL"
+  ],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
   "custom_train_dataset_path": [],
   "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
   "use_self_cognition": false,
+  "is_multimodal": false,
+  "is_vision": false,
   "lora_use_embedding": false,
-  "lora_use_all": false,
+  "lora_use_all": true,
   "lora_m2s_use_embedding": false,
   "lora_m2s_use_ln": false,
   "torch_dtype": "torch.bfloat16",
   "fp16": false,
   "bf16": true,
+  "rank": 0,
+  "local_rank": 0,
+  "world_size": 4,
+  "local_world_size": 4,
   "bnb_4bit_compute_dtype": "torch.bfloat16",
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/esft/output/qwen2-7b-instruct/v12-20240702-120746', 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=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=6, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/esft/output/qwen2-7b-instruct/v12-20240702-120746/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=True, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/esft/output/qwen2-7b-instruct/v12-20240702-120746', 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=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None), deepspeed=None, 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'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, 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=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=14019)"
+  "train_type": "sft",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/esft/output/qwen2_5-7b-instruct/v1-20240928-133855', 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=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=80, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/esft/output/qwen2_5-7b-instruct/v1-20240928-133855/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, 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, use_ipex=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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/esft/output/qwen2_5-7b-instruct/v1-20240928-133855', 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), deepspeed=None, 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'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint='/root/swift/esft/output/qwen2_5-7b-instruct/v0-20240928-125720/checkpoint-150', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"repetition_penalty\": 1.05,\n  \"temperature\": 0.7,\n  \"top_k\": 20,\n  \"top_p\": 0.8\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)"
 }

special_tokens_map.json

@@ -1,7 +1,18 @@
 {
   "additional_special_tokens": [
     "<|im_start|>",
-    "<|im_end|>"
+    "<|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|>"
   ],
   "eos_token": "<|im_end|>",
   "pad_token": {

tokenizer.json

@@ -29,6 +29,177 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 151646,
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151647,
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151648,
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151649,
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151650,
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151651,
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151652,
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151653,
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151654,
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151655,
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151656,
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151657,
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151658,
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151659,
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151660,
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151661,
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151662,
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151663,
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151664,
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
@@ -24,14 +25,177 @@
       "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
     }
   },
   "additional_special_tokens": [
     "<|im_start|>",
-    "<|im_end|>"
+    "<|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|>"
   ],
   "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",