add AWQ-int4_128_calibsample ckpt

.gitattributes

@@ -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
+*.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -1,16 +1,3 @@
-{
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa54985b58718a8fdb4f4d97484c4bd908db114847675e4bf3afe3e1d5d7bd4
+size 392

args.json

@@ -1,349 +1,3 @@
-{
-  "model": "/home/data3/zys/MLLM/pretrained_models/Qwen2-VL-7B-Instruct",
-  "model_type": "qwen2_vl",
-  "model_revision": null,
-  "torch_dtype": "bfloat16",
-  "attn_impl": "flash_attn",
-  "rope_scaling": null,
-  "device_map": null,
-  "local_repo_path": null,
-  "template": "qwen2_vl",
-  "system": null,
-  "max_length": 32768,
-  "truncation_strategy": "delete",
-  "max_pixels": null,
-  "tools_prompt": "react_en",
-  "loss_scale": "default",
-  "sequence_parallel_size": 1,
-  "use_chat_template": true,
-  "template_backend": "swift",
-  "dataset": [
-    "/home/data2/zys/Mars_o1/stage_3/cruise_and_sample_train_final.jsonl"
-  ],
-  "val_dataset": [],
-  "split_dataset_ratio": 0.0,
-  "data_seed": 42,
-  "dataset_num_proc": 1,
-  "streaming": false,
-  "load_from_cache_file": false,
-  "download_mode": "reuse_dataset_if_exists",
-  "strict": false,
-  "model_name": [
-    null,
-    null
-  ],
-  "model_author": [
-    null,
-    null
-  ],
-  "custom_dataset_info": [],
-  "quant_method": null,
-  "quant_bits": null,
-  "hqq_axis": null,
-  "bnb_4bit_compute_dtype": "bfloat16",
-  "bnb_4bit_quant_type": "nf4",
-  "bnb_4bit_use_double_quant": true,
-  "bnb_4bit_quant_storage": null,
-  "max_new_tokens": null,
-  "temperature": 0.0,
-  "top_k": null,
-  "top_p": null,
-  "repetition_penalty": null,
-  "num_beams": 1,
-  "stream": false,
-  "stop_words": [],
-  "ckpt_dir": null,
-  "load_dataset_config": null,
-  "lora_modules": [],
-  "tuner_backend": "peft",
-  "train_type": "lora",
-  "adapters": [],
-  "seed": 42,
-  "model_kwargs": {},
-  "load_args": true,
-  "load_data_args": false,
-  "use_hf": false,
-  "hub_token": null,
-  "custom_register_path": [],
-  "num_labels": null,
-  "ignore_args_error": false,
-  "use_swift_lora": false,
-  "output_dir": "/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943",
-  "overwrite_output_dir": false,
-  "do_train": false,
-  "do_eval": false,
-  "do_predict": false,
-  "eval_strategy": "epoch",
-  "prediction_loss_only": false,
-  "per_device_train_batch_size": 1,
-  "per_device_eval_batch_size": 1,
-  "per_gpu_train_batch_size": null,
-  "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 4,
-  "eval_accumulation_steps": null,
-  "eval_delay": 0,
-  "torch_empty_cache_steps": null,
-  "learning_rate": 1e-05,
-  "weight_decay": 0.1,
-  "adam_beta1": 0.9,
-  "adam_beta2": 0.999,
-  "adam_epsilon": 1e-08,
-  "max_grad_norm": 1.0,
-  "num_train_epochs": 3.0,
-  "max_steps": -1,
-  "lr_scheduler_type": "cosine",
-  "lr_scheduler_kwargs": null,
-  "warmup_ratio": 0.0,
-  "warmup_steps": 0,
-  "log_level": "passive",
-  "log_level_replica": "warning",
-  "log_on_each_node": true,
-  "logging_dir": "/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943/runs",
-  "logging_strategy": "steps",
-  "logging_first_step": true,
-  "logging_steps": 5,
-  "logging_nan_inf_filter": true,
-  "save_strategy": "epoch",
-  "save_steps": 500,
-  "save_total_limit": null,
-  "save_safetensors": true,
-  "save_on_each_node": false,
-  "save_only_model": false,
-  "restore_callback_states_from_checkpoint": false,
-  "no_cuda": false,
-  "use_cpu": false,
-  "use_mps_device": false,
-  "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": 0,
-  "dataloader_prefetch_factor": null,
-  "past_index": -1,
-  "run_name": null,
-  "disable_tqdm": null,
-  "remove_unused_columns": false,
-  "label_names": null,
-  "load_best_model_at_end": false,
-  "metric_for_best_model": "loss",
-  "greater_is_better": false,
-  "ignore_data_skip": false,
-  "fsdp": "",
-  "fsdp_min_num_params": 0,
-  "fsdp_config": null,
-  "fsdp_transformer_layer_cls_to_wrap": null,
-  "accelerator_config": {
-    "dispatch_batches": false
-  },
-  "deepspeed": {
-    "fp16": {
-      "enabled": "auto",
-      "loss_scale": 0,
-      "loss_scale_window": 1000,
-      "initial_scale_power": 16,
-      "hysteresis": 2,
-      "min_loss_scale": 1
-    },
-    "bf16": {
-      "enabled": "auto"
-    },
-    "optimizer": {
-      "type": "AdamW",
-      "params": {
-        "lr": "auto",
-        "betas": "auto",
-        "eps": "auto",
-        "weight_decay": "auto"
-      }
-    },
-    "scheduler": {
-      "type": "WarmupCosineLR",
-      "params": {
-        "total_num_steps": "auto",
-        "warmup_num_steps": "auto"
-      }
-    },
-    "zero_optimization": {
-      "stage": 2,
-      "offload_optimizer": {
-        "device": "none",
-        "pin_memory": true
-      },
-      "allgather_partitions": true,
-      "allgather_bucket_size": 200000000.0,
-      "overlap_comm": true,
-      "reduce_scatter": true,
-      "reduce_bucket_size": 200000000.0,
-      "contiguous_gradients": true
-    },
-    "gradient_accumulation_steps": "auto",
-    "gradient_clipping": "auto",
-    "steps_per_print": 2000,
-    "train_batch_size": "auto",
-    "train_micro_batch_size_per_gpu": "auto",
-    "wall_clock_breakdown": false
-  },
-  "label_smoothing_factor": 0.0,
-  "optim": "adamw_torch",
-  "optim_args": null,
-  "adafactor": false,
-  "group_by_length": false,
-  "length_column_name": "length",
-  "report_to": [
-    "tensorboard"
-  ],
-  "ddp_find_unused_parameters": false,
-  "ddp_bucket_cap_mb": null,
-  "ddp_broadcast_buffers": null,
-  "dataloader_pin_memory": true,
-  "dataloader_persistent_workers": false,
-  "skip_memory_metrics": true,
-  "use_legacy_prediction_loop": false,
-  "push_to_hub": false,
-  "resume_from_checkpoint": null,
-  "hub_model_id": null,
-  "hub_strategy": "every_save",
-  "hub_private_repo": false,
-  "hub_always_push": false,
-  "gradient_checkpointing": false,
-  "gradient_checkpointing_kwargs": null,
-  "include_inputs_for_metrics": false,
-  "eval_do_concat_batches": true,
-  "fp16_backend": "auto",
-  "evaluation_strategy": "epoch",
-  "push_to_hub_model_id": null,
-  "push_to_hub_organization": null,
-  "push_to_hub_token": null,
-  "mp_parameters": "",
-  "auto_find_batch_size": false,
-  "full_determinism": false,
-  "torchdynamo": null,
-  "ray_scope": "last",
-  "ddp_timeout": 1800,
-  "torch_compile": false,
-  "torch_compile_backend": null,
-  "torch_compile_mode": null,
-  "dispatch_batches": null,
-  "split_batches": null,
-  "include_tokens_per_second": null,
-  "include_num_input_tokens_seen": null,
-  "neftune_noise_alpha": null,
-  "optim_target_modules": null,
-  "batch_eval_metrics": false,
-  "eval_on_start": false,
-  "use_liger_kernel": false,
-  "eval_use_gather_object": false,
-  "sortish_sampler": false,
-  "predict_with_generate": false,
-  "generation_max_length": null,
-  "generation_num_beams": null,
-  "generation_config": null,
-  "freeze_parameters": [
-    "visual"
-  ],
-  "freeze_parameters_ratio": 0.0,
-  "trainable_parameters": [
-    "visual.merger"
-  ],
-  "freeze_llm": false,
-  "freeze_vit": true,
-  "freeze_aligner": false,
-  "target_modules": [
-    "all-linear"
-  ],
-  "target_regex": null,
-  "modules_to_save": [],
-  "lora_rank": 32,
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
-  "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,
-  "use_liger": false,
-  "model_layer_cls_name": null,
-  "metric_warmup_step": 0,
-  "fsdp_num": 1,
-  "acc_steps": 1,
-  "add_version": true,
-  "resume_only_model": false,
-  "check_model": true,
-  "loss_type": null,
-  "packing": false,
-  "lazy_tokenize": null,
-  "acc_strategy": "token",
-  "optimizer": null,
-  "metric": null,
-  "rank": 0,
-  "local_world_size": 4,
-  "model_suffix": "Qwen2-VL-7B-Instruct",
-  "model_info": "ModelInfo(model_type='qwen2_vl', model_dir='/home/data3/zys/MLLM/pretrained_models/Qwen2-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, config={'type': 'mrope', 'mrope_section': [16, 24, 24]})",
-  "model_meta": "ModelMeta(model_type='qwen2_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct', hf_model_id='Qwen/Qwen2-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct', hf_model_id='Qwen/Qwen2-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct', hf_model_id='Qwen/Qwen2-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B', hf_model_id='Qwen/Qwen2-VL-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B', hf_model_id='Qwen/Qwen2-VL-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B', hf_model_id='Qwen/Qwen2-VL-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_file_pattern=None, requires=None, tags=[])], template='qwen2_vl', get_function=<function get_model_tokenizer_qwen2_vl at 0x7f761f672b60>, model_arch='qwen2_vl', architectures=['Qwen2VLForConditionalGeneration'], is_multimodal=True, additional_saved_files=[], torch_dtype=None, ignore_file_pattern=['*.zip', '*.gguf', '*.pth', '*.pt', 'consolidated*', 'onnx', '*.safetensors.md', '*.msgpack', '*.onnx', '*.ot', '*.h5', '*.bin', '*.safetensors'], requires=['transformers>=4.45', 'qwen_vl_utils', 'pyav'], tags=[])",
-  "model_dir": "/home/data3/zys/MLLM/pretrained_models/Qwen2-VL-7B-Instruct",
-  "hub": "<class 'swift.hub.hub.MSHub'>",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=None, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'optimizer': {'type': 'AdamW', 'params': {'lr': 'auto', 'betas': 'auto', 'eps': 'auto', 'weight_decay': 'auto'}}, 'scheduler': {'type': 'WarmupCosineLR', 'params': {'total_num_steps': 'auto', 'warmup_num_steps': 'auto'}}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=False, 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=False, hub_always_push=False, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='epoch', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora')"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ca11a8bde1d0e6830ca1e569474ac07b1d0577d63158fe1de251231c0deb68
+size 17053

chat_template.json

@@ -1,3 +1,3 @@
-{
-  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
+size 1049

config.json

@@ -1,58 +1,3 @@
-{
-  "_name_or_path": "/home/data2/zys/Mars_o1/stage_3/v5-20250110-182943/checkpoint-735-merged",
-  "architectures": [
-    "Qwen2VLForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 3584,
-  "image_token_id": 151655,
-  "initializer_range": 0.02,
-  "intermediate_size": 18944,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
-  "model_type": "qwen2_vl",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "pad_token_id": 151643,
-  "quantization_config": {
-    "bits": 4,
-    "group_size": 128,
-    "modules_to_not_convert": [
-      "visual"
-    ],
-    "quant_method": "awq",
-    "version": "gemm",
-    "zero_point": true
-  },
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "mrope_section": [
-      16,
-      24,
-      24
-    ],
-    "rope_type": "default",
-    "type": "default"
-  },
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.45.0",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "video_token_id": 151656,
-  "vision_config": {
-    "in_chans": 3,
-    "model_type": "qwen2_vl",
-    "spatial_patch_size": 14
-  },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652,
-  "vision_token_id": 151654,
-  "vocab_size": 152064
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58de03dd80dfbe6b469c4a706a406be40c068f8fc8c7c77bc4af28f8a9d8a4a
+size 1388

generation_config.json

@@ -1,13 +1,3 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.01,
-  "top_k": 1,
-  "top_p": 0.001,
-  "transformers_version": "4.45.0"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:526fbf729bb87749cceb12678c83399b1ac01acac7feb15c23532b086b08fab1
+size 215

model.safetensors.index.json

@@ -1,1129 +1,3 @@
-{
-  "metadata": {
-    "total_size": 6922265600
-  },
-  "weight_map": {
-    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm2.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.ln_q.bias": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors",
-    "lm_head.weight": "model-00002-of-00002.safetensors"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0fbbcb3c938a01836039ca8761a796e7180b0eadf478d8bef391acf5cb4c4b
+size 88444

preprocessor_config.json

@@ -1,19 +1,3 @@
-{
-  "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": "Qwen2VLProcessor"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5eaad0c2815f07631535dcc58f3c462b0d73693638ad21d19f3c50820eae1cc
+size 347

special_tokens_map.json

@@ -1,31 +1,3 @@
-{
-  "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
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

tokenizer_config.json

@@ -1,144 +1,3 @@
-{
-  "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
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "processor_class": "Qwen2VLProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3c5a310899d7d65feec0dee4dff9067d7bc4ad2a17e2005bc9163f1ace0531
+size 4297