初始化项目，由ModelHub XC社区提供模型
Model: ry6666/Qwen2.5-VL-3B-HRI-Expert2 Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
349
args.json
Normal file
349
args.json
Normal file
@@ -0,0 +1,349 @@
|
|||||||
|
{
|
||||||
|
"output_dir": "/home/lry/Qwen/output_3b_sft/v6-20251228-235811",
|
||||||
|
"overwrite_output_dir": false,
|
||||||
|
"do_train": false,
|
||||||
|
"do_eval": false,
|
||||||
|
"do_predict": false,
|
||||||
|
"eval_strategy": "no",
|
||||||
|
"prediction_loss_only": false,
|
||||||
|
"per_device_train_batch_size": 1,
|
||||||
|
"per_device_eval_batch_size": 1,
|
||||||
|
"per_gpu_train_batch_size": null,
|
||||||
|
"per_gpu_eval_batch_size": null,
|
||||||
|
"gradient_accumulation_steps": 16,
|
||||||
|
"eval_accumulation_steps": null,
|
||||||
|
"eval_delay": 0,
|
||||||
|
"torch_empty_cache_steps": null,
|
||||||
|
"learning_rate": 0.0001,
|
||||||
|
"weight_decay": 0.1,
|
||||||
|
"adam_beta1": 0.9,
|
||||||
|
"adam_beta2": 0.95,
|
||||||
|
"adam_epsilon": 1e-08,
|
||||||
|
"max_grad_norm": 1.0,
|
||||||
|
"num_train_epochs": 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/lry/Qwen/output_3b_sft/v6-20251228-235811/runs",
|
||||||
|
"logging_strategy": "steps",
|
||||||
|
"logging_first_step": true,
|
||||||
|
"logging_steps": 5,
|
||||||
|
"logging_nan_inf_filter": true,
|
||||||
|
"save_strategy": "steps",
|
||||||
|
"save_steps": 50.0,
|
||||||
|
"save_total_limit": null,
|
||||||
|
"save_safetensors": true,
|
||||||
|
"save_on_each_node": false,
|
||||||
|
"save_only_model": false,
|
||||||
|
"restore_callback_states_from_checkpoint": false,
|
||||||
|
"no_cuda": false,
|
||||||
|
"use_cpu": false,
|
||||||
|
"use_mps_device": false,
|
||||||
|
"seed": 42,
|
||||||
|
"data_seed": 42,
|
||||||
|
"jit_mode_eval": false,
|
||||||
|
"bf16": true,
|
||||||
|
"fp16": false,
|
||||||
|
"fp16_opt_level": "O1",
|
||||||
|
"half_precision_backend": "auto",
|
||||||
|
"bf16_full_eval": false,
|
||||||
|
"fp16_full_eval": false,
|
||||||
|
"tf32": null,
|
||||||
|
"local_rank": -1,
|
||||||
|
"ddp_backend": null,
|
||||||
|
"tpu_num_cores": null,
|
||||||
|
"tpu_metrics_debug": false,
|
||||||
|
"debug": null,
|
||||||
|
"dataloader_drop_last": false,
|
||||||
|
"eval_steps": 50.0,
|
||||||
|
"dataloader_num_workers": null,
|
||||||
|
"dataloader_prefetch_factor": null,
|
||||||
|
"past_index": -1,
|
||||||
|
"run_name": "/home/lry/Qwen/output_3b_sft/v6-20251228-235811",
|
||||||
|
"disable_tqdm": null,
|
||||||
|
"remove_unused_columns": true,
|
||||||
|
"label_names": null,
|
||||||
|
"load_best_model_at_end": false,
|
||||||
|
"metric_for_best_model": "loss",
|
||||||
|
"greater_is_better": false,
|
||||||
|
"ignore_data_skip": false,
|
||||||
|
"fsdp": null,
|
||||||
|
"fsdp_min_num_params": 0,
|
||||||
|
"fsdp_config": null,
|
||||||
|
"fsdp_transformer_layer_cls_to_wrap": null,
|
||||||
|
"accelerator_config": {
|
||||||
|
"dispatch_batches": false
|
||||||
|
},
|
||||||
|
"parallelism_config": null,
|
||||||
|
"deepspeed": null,
|
||||||
|
"label_smoothing_factor": 0.0,
|
||||||
|
"optim": "adamw_torch_fused",
|
||||||
|
"optim_args": null,
|
||||||
|
"adafactor": false,
|
||||||
|
"group_by_length": false,
|
||||||
|
"length_column_name": "length",
|
||||||
|
"report_to": [
|
||||||
|
"tensorboard"
|
||||||
|
],
|
||||||
|
"project": "huggingface",
|
||||||
|
"trackio_space_id": "trackio",
|
||||||
|
"ddp_find_unused_parameters": null,
|
||||||
|
"ddp_bucket_cap_mb": null,
|
||||||
|
"ddp_broadcast_buffers": null,
|
||||||
|
"dataloader_pin_memory": true,
|
||||||
|
"dataloader_persistent_workers": false,
|
||||||
|
"skip_memory_metrics": true,
|
||||||
|
"use_legacy_prediction_loop": false,
|
||||||
|
"push_to_hub": false,
|
||||||
|
"resume_from_checkpoint": null,
|
||||||
|
"hub_model_id": null,
|
||||||
|
"hub_strategy": "every_save",
|
||||||
|
"hub_token": null,
|
||||||
|
"hub_private_repo": null,
|
||||||
|
"hub_always_push": false,
|
||||||
|
"hub_revision": null,
|
||||||
|
"gradient_checkpointing": true,
|
||||||
|
"gradient_checkpointing_kwargs": null,
|
||||||
|
"include_inputs_for_metrics": false,
|
||||||
|
"include_for_metrics": [],
|
||||||
|
"eval_do_concat_batches": true,
|
||||||
|
"fp16_backend": "auto",
|
||||||
|
"push_to_hub_model_id": null,
|
||||||
|
"push_to_hub_organization": null,
|
||||||
|
"push_to_hub_token": null,
|
||||||
|
"mp_parameters": "",
|
||||||
|
"auto_find_batch_size": false,
|
||||||
|
"full_determinism": false,
|
||||||
|
"torchdynamo": null,
|
||||||
|
"ray_scope": "last",
|
||||||
|
"ddp_timeout": 18000000,
|
||||||
|
"torch_compile": false,
|
||||||
|
"torch_compile_backend": null,
|
||||||
|
"torch_compile_mode": null,
|
||||||
|
"include_tokens_per_second": false,
|
||||||
|
"include_num_input_tokens_seen": false,
|
||||||
|
"neftune_noise_alpha": null,
|
||||||
|
"optim_target_modules": null,
|
||||||
|
"batch_eval_metrics": false,
|
||||||
|
"eval_on_start": false,
|
||||||
|
"use_liger_kernel": false,
|
||||||
|
"liger_kernel_config": null,
|
||||||
|
"eval_use_gather_object": false,
|
||||||
|
"average_tokens_across_devices": true,
|
||||||
|
"sortish_sampler": false,
|
||||||
|
"predict_with_generate": false,
|
||||||
|
"generation_max_length": null,
|
||||||
|
"generation_num_beams": null,
|
||||||
|
"generation_config": null,
|
||||||
|
"tuner_backend": "peft",
|
||||||
|
"vit_gradient_checkpointing": null,
|
||||||
|
"router_aux_loss_coef": 0.0,
|
||||||
|
"enable_dft_loss": false,
|
||||||
|
"enable_channel_loss": false,
|
||||||
|
"check_model": true,
|
||||||
|
"acc_strategy": "token",
|
||||||
|
"train_dataloader_shuffle": true,
|
||||||
|
"max_epochs": null,
|
||||||
|
"aligner_lr": null,
|
||||||
|
"vit_lr": null,
|
||||||
|
"use_logits_to_keep": null,
|
||||||
|
"ds3_gather_for_generation": true,
|
||||||
|
"resume_only_model": false,
|
||||||
|
"optimizer": null,
|
||||||
|
"loss_type": null,
|
||||||
|
"metric": null,
|
||||||
|
"eval_use_evalscope": false,
|
||||||
|
"eval_dataset": [],
|
||||||
|
"eval_dataset_args": null,
|
||||||
|
"eval_limit": null,
|
||||||
|
"eval_generation_config": null,
|
||||||
|
"extra_eval_args": null,
|
||||||
|
"use_flash_ckpt": false,
|
||||||
|
"use_ray": false,
|
||||||
|
"ray_exp_name": null,
|
||||||
|
"device_groups": null,
|
||||||
|
"model": "/home/lry/.cache/modelscope/hub/models/qwen/Qwen2___5-VL-3B-Instruct",
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"model_revision": null,
|
||||||
|
"task_type": "causal_lm",
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"attn_impl": null,
|
||||||
|
"new_special_tokens": [],
|
||||||
|
"num_labels": null,
|
||||||
|
"problem_type": null,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"device_map": null,
|
||||||
|
"max_memory": {},
|
||||||
|
"max_model_len": null,
|
||||||
|
"local_repo_path": null,
|
||||||
|
"init_strategy": null,
|
||||||
|
"template": "qwen2_5_vl",
|
||||||
|
"system": null,
|
||||||
|
"max_length": 4096,
|
||||||
|
"truncation_strategy": "delete",
|
||||||
|
"max_pixels": null,
|
||||||
|
"agent_template": null,
|
||||||
|
"norm_bbox": null,
|
||||||
|
"use_chat_template": true,
|
||||||
|
"padding_free": false,
|
||||||
|
"padding_side": "right",
|
||||||
|
"loss_scale": "default",
|
||||||
|
"sequence_parallel_size": 1,
|
||||||
|
"response_prefix": null,
|
||||||
|
"template_backend": "swift",
|
||||||
|
"dataset": [
|
||||||
|
"/home/lry/Qwen/output_data/swift_train_data.jsonl"
|
||||||
|
],
|
||||||
|
"val_dataset": [],
|
||||||
|
"cached_dataset": [],
|
||||||
|
"cached_val_dataset": [],
|
||||||
|
"split_dataset_ratio": 0.0,
|
||||||
|
"dataset_num_proc": 1,
|
||||||
|
"load_from_cache_file": false,
|
||||||
|
"dataset_shuffle": true,
|
||||||
|
"val_dataset_shuffle": false,
|
||||||
|
"streaming": false,
|
||||||
|
"interleave_prob": null,
|
||||||
|
"stopping_strategy": "first_exhausted",
|
||||||
|
"shuffle_buffer_size": 1000,
|
||||||
|
"download_mode": "reuse_dataset_if_exists",
|
||||||
|
"columns": {},
|
||||||
|
"strict": false,
|
||||||
|
"model_name": null,
|
||||||
|
"model_author": null,
|
||||||
|
"custom_dataset_info": [],
|
||||||
|
"quant_method": null,
|
||||||
|
"quant_bits": null,
|
||||||
|
"hqq_axis": null,
|
||||||
|
"bnb_4bit_compute_dtype": "bfloat16",
|
||||||
|
"bnb_4bit_quant_type": "nf4",
|
||||||
|
"bnb_4bit_use_double_quant": true,
|
||||||
|
"bnb_4bit_quant_storage": null,
|
||||||
|
"max_new_tokens": 64,
|
||||||
|
"temperature": 0.0,
|
||||||
|
"top_k": null,
|
||||||
|
"top_p": null,
|
||||||
|
"repetition_penalty": null,
|
||||||
|
"num_beams": 1,
|
||||||
|
"stream": false,
|
||||||
|
"stop_words": [],
|
||||||
|
"logprobs": false,
|
||||||
|
"top_logprobs": null,
|
||||||
|
"ckpt_dir": null,
|
||||||
|
"lora_modules": [],
|
||||||
|
"train_type": "lora",
|
||||||
|
"adapters": [],
|
||||||
|
"external_plugins": [],
|
||||||
|
"model_kwargs": {},
|
||||||
|
"load_args": false,
|
||||||
|
"load_data_args": false,
|
||||||
|
"packing": false,
|
||||||
|
"packing_length": null,
|
||||||
|
"packing_num_proc": 1,
|
||||||
|
"lazy_tokenize": true,
|
||||||
|
"custom_register_path": [],
|
||||||
|
"use_hf": false,
|
||||||
|
"ignore_args_error": false,
|
||||||
|
"use_swift_lora": false,
|
||||||
|
"freeze_parameters": [],
|
||||||
|
"freeze_parameters_regex": null,
|
||||||
|
"freeze_parameters_ratio": 0.0,
|
||||||
|
"trainable_parameters": [],
|
||||||
|
"trainable_parameters_regex": null,
|
||||||
|
"freeze_llm": false,
|
||||||
|
"freeze_vit": true,
|
||||||
|
"freeze_aligner": true,
|
||||||
|
"target_modules": [
|
||||||
|
"all-linear"
|
||||||
|
],
|
||||||
|
"target_regex": null,
|
||||||
|
"target_parameters": null,
|
||||||
|
"modules_to_save": [],
|
||||||
|
"lora_rank": 8,
|
||||||
|
"lora_alpha": 32,
|
||||||
|
"lora_dropout": 0.05,
|
||||||
|
"lora_bias": "none",
|
||||||
|
"lora_dtype": null,
|
||||||
|
"lorap_lr_ratio": null,
|
||||||
|
"use_rslora": false,
|
||||||
|
"use_dora": false,
|
||||||
|
"lora_ga_batch_size": 2,
|
||||||
|
"lora_ga_iters": 2,
|
||||||
|
"lora_ga_max_length": 1024,
|
||||||
|
"lora_ga_direction": "ArB2r",
|
||||||
|
"lora_ga_scale": "stable",
|
||||||
|
"lora_ga_stable_gamma": 16,
|
||||||
|
"init_weights": true,
|
||||||
|
"fourier_n_frequency": 2000,
|
||||||
|
"fourier_scaling": 300.0,
|
||||||
|
"boft_block_size": 4,
|
||||||
|
"boft_block_num": 0,
|
||||||
|
"boft_n_butterfly_factor": 1,
|
||||||
|
"boft_dropout": 0.0,
|
||||||
|
"vera_rank": 256,
|
||||||
|
"vera_projection_prng_key": 0,
|
||||||
|
"vera_dropout": 0.0,
|
||||||
|
"vera_d_initial": 0.1,
|
||||||
|
"adapter_act": "gelu",
|
||||||
|
"adapter_length": 128,
|
||||||
|
"use_galore": false,
|
||||||
|
"galore_target_modules": null,
|
||||||
|
"galore_rank": 128,
|
||||||
|
"galore_update_proj_gap": 50,
|
||||||
|
"galore_scale": 1.0,
|
||||||
|
"galore_proj_type": "std",
|
||||||
|
"galore_optim_per_parameter": false,
|
||||||
|
"galore_with_embedding": false,
|
||||||
|
"galore_quantization": false,
|
||||||
|
"galore_proj_quant": false,
|
||||||
|
"galore_proj_bits": 4,
|
||||||
|
"galore_proj_group_size": 256,
|
||||||
|
"galore_cos_threshold": 0.4,
|
||||||
|
"galore_gamma_proj": 2,
|
||||||
|
"galore_queue_size": 5,
|
||||||
|
"adalora_target_r": 8,
|
||||||
|
"adalora_init_r": 12,
|
||||||
|
"adalora_tinit": 0,
|
||||||
|
"adalora_tfinal": 0,
|
||||||
|
"adalora_deltaT": 1,
|
||||||
|
"adalora_beta1": 0.85,
|
||||||
|
"adalora_beta2": 0.85,
|
||||||
|
"adalora_orth_reg_weight": 0.5,
|
||||||
|
"llamapro_num_new_blocks": 4,
|
||||||
|
"llamapro_num_groups": null,
|
||||||
|
"lisa_activated_layers": 0,
|
||||||
|
"lisa_step_interval": 20,
|
||||||
|
"reft_layer_key": null,
|
||||||
|
"reft_layers": null,
|
||||||
|
"reft_rank": 4,
|
||||||
|
"reft_intervention_type": "LoreftIntervention",
|
||||||
|
"reft_args": null,
|
||||||
|
"swanlab_token": null,
|
||||||
|
"swanlab_project": null,
|
||||||
|
"swanlab_workspace": null,
|
||||||
|
"swanlab_exp_name": null,
|
||||||
|
"swanlab_lark_webhook_url": null,
|
||||||
|
"swanlab_lark_secret": null,
|
||||||
|
"swanlab_mode": "cloud",
|
||||||
|
"add_version": true,
|
||||||
|
"create_checkpoint_symlink": false,
|
||||||
|
"zero_hpz_partition_size": null,
|
||||||
|
"deepspeed_autotp_size": null,
|
||||||
|
"early_stop_interval": null,
|
||||||
|
"rank": -1,
|
||||||
|
"global_world_size": 1,
|
||||||
|
"local_world_size": 1,
|
||||||
|
"model_suffix": "Qwen2.5-VL-3B-Instruct",
|
||||||
|
"model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/home/lry/.cache/modelscope/hub/models/qwen/Qwen2___5-VL-3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
||||||
|
"model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x74e0b768ee80>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
|
||||||
|
"model_dir": "/home/lry/.cache/modelscope/hub/models/qwen/Qwen2___5-VL-3B-Instruct",
|
||||||
|
"_val_dataset_exists": [],
|
||||||
|
"hub": "<class 'swift.hub.hub.MSHub'>",
|
||||||
|
"evaluation_strategy": "steps",
|
||||||
|
"training_args": "Seq2SeqTrainingArguments(output_dir='/home/lry/Qwen/output_3b_sft/v6-20251228-235811', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=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/lry/Qwen/output_3b_sft/v6-20251228-235811/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, 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=50.0, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/lry/Qwen/output_3b_sft/v6-20251228-235811', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm', problem_type=None)"
|
||||||
|
}
|
||||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{% 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
|
||||||
|
You are a helpful assistant.<|im_end|>
|
||||||
|
{% endif %}<|im_start|>{{ message['role'] }}
|
||||||
|
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
||||||
|
{% 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|>
|
||||||
|
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
||||||
|
{% endif %}
|
||||||
142
config.json
Normal file
142
config.json
Normal file
@@ -0,0 +1,142 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"max_position_embeddings": 128000,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"text_config": {
|
||||||
|
"_name_or_path": "/home/lry/.cache/modelscope/hub/models/qwen/Qwen2___5-VL-3B-Instruct",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 128000,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2_5_vl_text",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
},
|
||||||
|
"transformers_version": "4.57.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"depth": 32,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"fullatt_block_indexes": [
|
||||||
|
7,
|
||||||
|
15,
|
||||||
|
23,
|
||||||
|
31
|
||||||
|
],
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1280,
|
||||||
|
"in_channels": 3,
|
||||||
|
"in_chans": 3,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3420,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"num_heads": 16,
|
||||||
|
"out_hidden_size": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"patch_size": 14,
|
||||||
|
"spatial_merge_size": 2,
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"tokens_per_second": 2,
|
||||||
|
"window_size": 112
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "other"}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"repetition_penalty": 1.05,
|
||||||
|
"temperature": 1e-06,
|
||||||
|
"transformers_version": "4.57.3"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6ec370937ea730391d55035b64e735b9b4d13dd5c0582581041b17e967e337f4
|
||||||
|
size 4997750760
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:66a865524343ceb9ca93483e6e10c84530ed462d095017e19288d3decc03f45f
|
||||||
|
size 2511587184
|
||||||
832
model.safetensors.index.json
Normal file
832
model.safetensors.index.json
Normal file
@@ -0,0 +1,832 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 3754622976,
|
||||||
|
"total_size": 7509245952
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
19
preprocessor_config.json
Normal file
19
preprocessor_config.json
Normal file
@@ -0,0 +1,19 @@
|
|||||||
|
{
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"patch_size": 14,
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"merge_size": 2,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2VLImageProcessor",
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor"
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
757444
tokenizer.json
Normal file
757444
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
43
video_preprocessor_config.json
Normal file
43
video_preprocessor_config.json
Normal file
@@ -0,0 +1,43 @@
|
|||||||
|
{
|
||||||
|
"crop_size": null,
|
||||||
|
"data_format": "channels_first",
|
||||||
|
"default_to_square": true,
|
||||||
|
"device": null,
|
||||||
|
"do_center_crop": null,
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"do_sample_frames": false,
|
||||||
|
"fps": null,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"input_data_format": null,
|
||||||
|
"max_frames": 768,
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_frames": 4,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"num_frames": null,
|
||||||
|
"pad_size": null,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"return_metadata": false,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"video_metadata": null,
|
||||||
|
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user