wyhewy/Qwen3_1.7B_Distill_SFT
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: wyhewy/Qwen3_1.7B_Distill_SFT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 21:14:14 +08:00
commit 28db2e0278
12 changed files with 909622 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|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
}

329
args.json Normal file
View File

@@ -0,0 +1,329 @@
{
"model": "Qwen/Qwen3-1.7B",
"model_type": "qwen3",
"model_revision": null,
"task_type": "causal_lm",
"torch_dtype": "bfloat16",
"attn_impl": null,
"num_labels": null,
"problem_type": null,
"rope_scaling": null,
"device_map": null,
"max_memory": {},
"local_repo_path": null,
"init_strategy": null,
"template": "qwen3",
"system": "You are a helpful assistant.",
"max_length": 8192,
"truncation_strategy": "delete",
"max_pixels": null,
"agent_template": null,
"norm_bbox": null,
"response_prefix": null,
"padding_side": "right",
"loss_scale": "default",
"sequence_parallel_size": 1,
"use_chat_template": true,
"template_backend": "swift",
"dataset": [
"/mnt/data/0/wangyin/deep_math-103k_train_sorted_split_singe.jsonl"
],
"val_dataset": [],
"split_dataset_ratio": 0.01,
"data_seed": 42,
"dataset_num_proc": 1,
"load_from_cache_file": false,
"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,
"remove_unused_columns": true,
"model_name": [
null,
null
],
"model_author": [
null,
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,
"ckpt_dir": null,
"lora_modules": [],
"tuner_backend": "peft",
"train_type": "lora",
"adapters": [],
"external_plugins": [],
"seed": 42,
"model_kwargs": {},
"load_args": false,
"load_data_args": false,
"use_hf": false,
"hub_token": null,
"custom_register_path": [],
"ignore_args_error": false,
"use_swift_lora": false,
"output_dir": "/mnt/data/0/wangyin/output/v1-20250519-214109",
"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": 2,
"per_device_eval_batch_size": 2,
"per_gpu_train_batch_size": null,
"per_gpu_eval_batch_size": null,
"gradient_accumulation_steps": 8,
"eval_accumulation_steps": null,
"eval_delay": 0,
"torch_empty_cache_steps": null,
"learning_rate": 0.0003,
"weight_decay": 0.01,
"adam_beta1": 0.9,
"adam_beta2": 0.95,
"adam_epsilon": 1e-08,
"max_grad_norm": 0.3,
"num_train_epochs": 3.0,
"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": "/mnt/data/0/wangyin/output/v1-20250519-214109/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": 2,
"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,
"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": null,
"local_rank": -1,
"ddp_backend": null,
"tpu_num_cores": null,
"tpu_metrics_debug": false,
"debug": null,
"dataloader_drop_last": false,
"eval_steps": 500.0,
"dataloader_num_workers": 4,
"dataloader_prefetch_factor": null,
"past_index": -1,
"run_name": "/mnt/data/0/wangyin/output/v1-20250519-214109",
"disable_tqdm": null,
"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,
"tp_size": 0,
"fsdp_transformer_layer_cls_to_wrap": null,
"accelerator_config": {
"dispatch_batches": false
},
"deepspeed": null,
"label_smoothing_factor": 0.0,
"optim": "adamw_torch",
"optim_args": null,
"adafactor": false,
"group_by_length": false,
"length_column_name": "length",
"report_to": [
"none"
],
"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": null,
"hub_model_id": null,
"hub_strategy": "every_save",
"hub_private_repo": null,
"hub_always_push": false,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": null,
"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": 1800,
"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,
"eval_use_gather_object": false,
"average_tokens_across_devices": false,
"sortish_sampler": false,
"predict_with_generate": false,
"generation_max_length": null,
"generation_num_beams": null,
"generation_config": null,
"check_model": true,
"acc_strategy": "token",
"train_dataloader_shuffle": true,
"max_epochs": null,
"metric_warmup_step": 0,
"fsdp_num": 1,
"acc_steps": 1,
"eval_use_evalscope": false,
"eval_datasets": [],
"eval_limit": null,
"eval_datasets_args": null,
"eval_generation_config": null,
"freeze_parameters": [],
"freeze_parameters_regex": null,
"freeze_parameters_ratio": 0.0,
"trainable_parameters": [],
"trainable_parameters_regex": null,
"freeze_llm": false,
"freeze_vit": true,
"freeze_aligner": true,
"target_modules": [
"all-linear"
],
"target_regex": 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,
"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,
"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,
"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,
"swanlab_token": null,
"swanlab_project": null,
"swanlab_workspace": null,
"swanlab_exp_name": null,
"swanlab_mode": "cloud",
"add_version": true,
"resume_only_model": false,
"create_checkpoint_symlink": false,
"packing": false,
"lazy_tokenize": false,
"loss_type": null,
"optimizer": null,
"metric": null,
"zero_hpz_partition_size": null,
"rank": -1,
"global_world_size": 1,
"local_world_size": 1,
"model_suffix": "Qwen3-1.7B",
"model_info": "ModelInfo(model_type='qwen3', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
"model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-Base', hf_model_id='Qwen/Qwen3-32B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f83b3a52dd0>, model_arch='llama', architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
"model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B",
"hub": "<class 'swift.hub.hub.MSHub'>",
"evaluation_strategy": "steps",
"training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/data/0/wangyin/output/v1-20250519-214109', 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=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0003, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=0.3, num_train_epochs=3.0, 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='/mnt/data/0/wangyin/output/v1-20250519-214109/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=2, 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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/0/wangyin/output/v1-20250519-214109', 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}, tp_size=0, 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), 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=[], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, 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, 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None)"
}

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

31
configuration.json Normal file
View File

@@ -0,0 +1,31 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.51.0"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94ea856f478d4a0191d4ddb32fafa749f659401abe6d5fc19f2921740f977a2d
size 3441185608

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"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|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

757480
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

240
tokenizer_config.json Normal file
View File

@@ -0,0 +1,240 @@
{
"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
}
},
"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|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long