Dingzou commited on Oct 31, 2025

Commit

2b9fd71

verified ·

1 Parent(s): 590a3da

Upload 29 files

Browse files

Files changed (30) hide show

.gitattributes +1 -0
added_tokens.json +24 -0
args.json +499 -0
chat_template.jinja +54 -0
config.json +172 -0
generation_config.json +12 -0
merges.txt +0 -0
model-00001-of-00014.safetensors +3 -0
model-00002-of-00014.safetensors +3 -0
model-00003-of-00014.safetensors +3 -0
model-00004-of-00014.safetensors +3 -0
model-00005-of-00014.safetensors +3 -0
model-00006-of-00014.safetensors +3 -0
model-00007-of-00014.safetensors +3 -0
model-00008-of-00014.safetensors +3 -0
model-00009-of-00014.safetensors +3 -0
model-00010-of-00014.safetensors +3 -0
model-00011-of-00014.safetensors +3 -0
model-00012-of-00014.safetensors +3 -0
model-00013-of-00014.safetensors +3 -0
model-00014-of-00014.safetensors +3 -0
model.safetensors.index.json +1169 -0
preprocessor_config.json +19 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +208 -0
trainer_state.json +0 -0
training_args.bin +3 -0
video_preprocessor_config.json +43 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json ADDED Viewed

	@@ -0,0 +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,
+  "<|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
+}

args.json ADDED Viewed

	@@ -0,0 +1,499 @@

+{
+  "output_dir": "/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 4,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 1,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 2.5e-06,
+  "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": "/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 100.0,
+  "save_total_limit": 500,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": true,
+  "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": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923",
+  "disable_tqdm": null,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "reward",
+  "greater_is_better": true,
+  "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
+  },
+  "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": 3,
+      "offload_optimizer": {
+        "device": "cpu",
+        "pin_memory": true
+      },
+      "offload_param": {
+        "device": "cpu",
+        "pin_memory": true
+      },
+      "overlap_comm": false,
+      "contiguous_gradients": true,
+      "sub_group_size": 1000000000.0,
+      "reduce_bucket_size": "auto",
+      "stage3_prefetch_bucket_size": "auto",
+      "stage3_param_persistence_threshold": "auto",
+      "stage3_max_live_parameters": 1000000000.0,
+      "stage3_max_reuse_distance": 1000000000.0,
+      "stage3_gather_16bit_weights_on_model_save": 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",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "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_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "hub_revision": null,
+  "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": 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": null,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "optimizer": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "model": "/mnt/shared/wireless_robot/tj_models/best_model_0928_32B",
+  "model_type": "qwen2_5_vl",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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": "qwen2_5_vl",
+  "system": null,
+  "max_length": 4096,
+  "truncation_strategy": "left",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "last_round",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/embspatial_all_right_partial_right_all_wrong_but_consistent_with_question_known.jsonl",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/selfrevision_formatted_rl_26k_except_sft_questA.jsonl",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/Alfred_data_mid_v4_with_system_prompt.jsonl",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/swift_VPT_grpo_except_ocr_with_tasktype.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 4,
+  "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,
+  "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": 2048,
+  "temperature": 1.2,
+  "top_k": 160,
+  "top_p": 0.98,
+  "repetition_penalty": 1.0,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": "/mnt/shared/wireless_robot/tj_models/best_model_0928_32B",
+  "lora_modules": [],
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/plugins/plugin_rm_v2_async_p31415.py",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/plugins/plugin_joint_if_spatial_training_with_question_known.py",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/plugins/plugin_vpt.py",
+    "/mnt/shared/wireless_robot/robodata/swift_rl_datasets/plugins/plugin_joint_if_spatial_planningformat_training.py"
+  ],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [
+    "model.visual",
+    "model.visual.merger"
+  ],
+  "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_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "lazy_tokenize": true,
+  "loss_type": "bnpo",
+  "metric": null,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "sft_alpha": 0,
+  "reward_model": null,
+  "reward_adapters": [],
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "num_ppo_epochs": 4,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_mini_batches": 1,
+  "local_rollout_forward_batch_size": 64,
+  "num_sample_generations": 10,
+  "response_length": 2048,
+  "missing_eos_penalty": null,
+  "vllm_gpu_memory_utilization": 0.9,
+  "vllm_tensor_parallel_size": 1,
+  "vllm_pipeline_parallel_size": 1,
+  "vllm_enable_expert_parallel": false,
+  "vllm_max_num_seqs": 256,
+  "vllm_max_model_len": 1024,
+  "vllm_disable_custom_all_reduce": true,
+  "vllm_enforce_eager": false,
+  "vllm_limit_mm_per_prompt": {},
+  "vllm_max_lora_rank": 16,
+  "vllm_enable_prefix_caching": true,
+  "vllm_use_async_engine": false,
+  "vllm_quantization": null,
+  "vllm_data_parallel_size": 1,
+  "gpu_memory_utilization": null,
+  "tensor_parallel_size": null,
+  "limit_mm_per_prompt": null,
+  "data_parallel_size": null,
+  "use_async_engine": null,
+  "epsilon": 0.2,
+  "epsilon_high": 0.28,
+  "delta": null,
+  "vllm_mode": "colocate",
+  "vllm_server_base_url": null,
+  "vllm_server_host": null,
+  "vllm_server_port": [
+    8000
+  ],
+  "vllm_server_timeout": 240.0,
+  "cosine_min_len_value_wrong": -0.5,
+  "cosine_max_len_value_wrong": 0.0,
+  "cosine_min_len_value_correct": 1.0,
+  "cosine_max_len_value_correct": 0.5,
+  "cosine_max_len": null,
+  "repetition_n_grams": 3,
+  "repetition_max_penalty": -1.0,
+  "reward_model_plugin": null,
+  "sync_ref_model": false,
+  "ref_model_sync_steps": 512,
+  "ref_model_mixup_alpha": 0.6,
+  "async_generate": false,
+  "sleep_level": 0,
+  "move_model_batches": null,
+  "offload_optimizer": false,
+  "offload_model": false,
+  "gc_collect_after_offload": false,
+  "multi_turn_func": null,
+  "multi_turn_scheduler": null,
+  "max_turns": null,
+  "completion_length_limit_scope": "per_round",
+  "dynamic_sample": true,
+  "max_resample_times": 3,
+  "overlong_filter": true,
+  "soft_max_length": null,
+  "soft_cache_length": null,
+  "scale_rewards": true,
+  "log_entropy": false,
+  "top_entropy_quantile": 1.0,
+  "importance_sampling_level": "token",
+  "wandb_log_unique_prompts": null,
+  "generation_batch_size": null,
+  "steps_per_generation": null,
+  "num_generations": 16,
+  "reward_funcs": [
+    "external_sr_ORM",
+    "external_wothink_format",
+    "external_planning_rm_ORM",
+    "external_planning_rule_ORM",
+    "visual_perception_accuracy"
+  ],
+  "reward_weights": [
+    0.95,
+    0.05,
+    0.8,
+    0.2,
+    1.0
+  ],
+  "log_completions": true,
+  "use_vllm": false,
+  "num_iterations": 1,
+  "teacher_model": null,
+  "teacher_adapters": [],
+  "teacher_model_type": null,
+  "teacher_model_revision": null,
+  "rlhf_type": "grpo",
+  "ref_model": "/mnt/shared/wireless_robot/tj_models/best_model_0928_32B",
+  "ref_model_type": "qwen2_5_vl",
+  "ref_model_revision": null,
+  "beta": 0.001,
+  "label_smoothing": 0,
+  "max_completion_length": 2048,
+  "rpo_alpha": 1.0,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "center_rewards_coefficient": null,
+  "lmbda": 0.5,
+  "seq_kd": false,
+  "rank": 0,
+  "global_world_size": 16,
+  "local_world_size": 8,
+  "model_suffix": "best_model_0928_32B",
+  "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/shared/wireless_robot/tj_models/best_model_0928_32B', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fd44e477ac0>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
+  "model_dir": "/mnt/shared/wireless_robot/tj_models/best_model_0928_32B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "no",
+  "training_args": "GRPOConfig(output_dir='/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2.5e-06, 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='/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=500, save_safetensors=True, save_on_each_node=False, save_only_model=True, 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=True, eval_steps=None, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/shared/wireless_robot/gemengyu/proj/ms-swift-main-250730/my_experiments/saved_model/tjsft_32b_dapo/v0-20250930-072923', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, 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), 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': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=16, max_completion_length=2048, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=64, steps_per_generation=1, temperature=1.2, top_p=0.98, top_k=160, min_p=None, generation_kwargs=None, repetition_penalty=1.0, cache_implementation=None, use_vllm=False, vllm_server_base_url=None, vllm_mode='colocate', vllm_guided_decoding_regex=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.001, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=0.28, reward_weights=[0.95, 0.05, 0.8, 0.2, 1.0], scale_rewards=True, loss_type='bnpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, resume_only_model=False, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=1024, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=2048, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', dynamic_sample=True, max_resample_times=3, overlong_filter=True, soft_max_length=None, soft_cache_length=None, log_entropy=False, top_entropy_quantile=1.0, importance_sampling_level='token', dataset_shuffle=True, stop_words=[])"
+}

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,54 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,172 @@

+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 64,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 64,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3456,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 5120,
+    "pad_token_id": 151643,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.54.1"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model-00001-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a9f215eeaef8e67b293b16205cc047d54fb4c49617200acbe0868ebfa6fe04
+size 4958700928

model-00002-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bee5a86b33f897ac2e837c50d9554b0f6a190d95ca24a7bc238f3f2113aecf43
+size 4928488272

model-00003-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcec222f0ddf6029fbdb233f59d1463a986e5e0f03b18ff6c89c5682c45ff86
+size 4876059368

model-00004-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0008da9335b1df30ab6f7c0e403f301165b0c6275632d1950d223f8a08db921a
+size 4876059416

model-00005-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:665d804ddea6bfa2f2a79a633a44a71705a5fcb9b40509520f483cfd384b7089
+size 4876059416

model-00006-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:25fddb41c5de9954965d673e0f5e1235d3bbb685e116934d3303dd05b58f2948
+size 4876059416

model-00007-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:00a432d144a3ee865e210dcc46880a86f87c7b9c5a805e0d05405f2d93a67285
+size 4876059416

model-00008-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fff660aad31c06e0921c2012cb5e330ae6aeadbc54b791d74c2b073623c07f3a
+size 4876059416

model-00009-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:754acc0ee6463ae3e1e6e5e1c8c2d16d3b9bb0621edff63a26a9c279b390fc8e
+size 4876059416

model-00010-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e5ac080be7b68e3e287badf6e7331fab346dd1836c59b1845ed9c42085c123
+size 4876059416

model-00011-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:477fd67340a0d962916e6d89d48f9f13f43d1d519e44b5ab3d3a2b91ff33a041
+size 4876059416

model-00012-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:95245b3cf0a60d971bd13b44e460dd3fd8ceb48ab2e617d1b7d046d1e78ef754
+size 4876059416

model-00013-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:51bc831ca5962b64aaa793c555d1351e9d46a5c8417f2113572ec8765ea80775
+size 4876059416

model-00014-of-00014.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b127e5870805751ffb2aaf913fd62c8d07bc9e8b7e61510571c693d185e23123
+size 3381725320

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,1169 @@

+{
+  "metadata": {
+    "total_parameters": 1638656,
+    "total_size": 66905436672
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00014.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00014.safetensors"
+  }
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae8594f633daa21dc0e04606279856d0ccb8abb64bb7a5a93e72531fb12b9d9
+size 11421890

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,208 @@

+{
+  "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
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b15bab60bc7d07416e6b1fd083f18fed5a7f4a9051d8778ff02f3a4712c597
+size 11537

video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff