Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/args.json +376 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/chat_template.jinja +7 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/config.json +106 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/generation_config.json +12 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/latest +1 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/model-00001-of-00004.safetensors +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/model-00002-of-00004.safetensors +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/model-00003-of-00004.safetensors +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/model-00004-of-00004.safetensors +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/model.safetensors.index.json +737 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/preprocessor_config.json +19 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/processor_config.json +63 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_0.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_1.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_2.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_3.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_4.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_5.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_6.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_7.pth +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/scheduler.pt +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/tokenizer.json +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/tokenizer_config.json +30 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/trainer_state.json +114 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/training_args.bin +3 -0
- output_dir_no123/v3-20260407-222221/checkpoint-48/zero_to_fp32.py +674 -0
.gitattributes
CHANGED
|
@@ -54,3 +54,4 @@ output_dir/v2-20260406-012551/checkpoint-48/tokenizer.json filter=lfs diff=lfs m
|
|
| 54 |
output_dir_blackimage/v2-20260404-031052/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
output_dir_no23_1round/v3-20260402-144535/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
output_dir_no2/v6-20260324-144529/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 54 |
output_dir_blackimage/v2-20260404-031052/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
output_dir_no23_1round/v3-20260402-144535/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
output_dir_no2/v6-20260324-144529/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
output_dir_no123/v3-20260407-222221/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
output_dir_no123/v3-20260407-222221/checkpoint-48/args.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/raid/icy/Thyme/output_dir_no123/v3-20260407-222221",
|
| 3 |
+
"per_device_train_batch_size": 1,
|
| 4 |
+
"num_train_epochs": 3.0,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 7 |
+
"lr_scheduler_type": "cosine",
|
| 8 |
+
"lr_scheduler_kwargs": null,
|
| 9 |
+
"warmup_steps": 0,
|
| 10 |
+
"optim": "adamw_torch",
|
| 11 |
+
"optim_args": null,
|
| 12 |
+
"weight_decay": 0.1,
|
| 13 |
+
"adam_beta1": 0.9,
|
| 14 |
+
"adam_beta2": 0.95,
|
| 15 |
+
"adam_epsilon": 1e-08,
|
| 16 |
+
"optim_target_modules": null,
|
| 17 |
+
"gradient_accumulation_steps": 16,
|
| 18 |
+
"average_tokens_across_devices": true,
|
| 19 |
+
"max_grad_norm": 1.0,
|
| 20 |
+
"label_smoothing_factor": 0.0,
|
| 21 |
+
"bf16": true,
|
| 22 |
+
"fp16": false,
|
| 23 |
+
"bf16_full_eval": false,
|
| 24 |
+
"fp16_full_eval": false,
|
| 25 |
+
"tf32": null,
|
| 26 |
+
"gradient_checkpointing": true,
|
| 27 |
+
"gradient_checkpointing_kwargs": null,
|
| 28 |
+
"torch_compile": false,
|
| 29 |
+
"torch_compile_backend": null,
|
| 30 |
+
"torch_compile_mode": null,
|
| 31 |
+
"use_liger_kernel": false,
|
| 32 |
+
"liger_kernel_config": null,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"neftune_noise_alpha": null,
|
| 35 |
+
"torch_empty_cache_steps": null,
|
| 36 |
+
"auto_find_batch_size": false,
|
| 37 |
+
"logging_strategy": "steps",
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"logging_first_step": true,
|
| 40 |
+
"log_on_each_node": true,
|
| 41 |
+
"logging_nan_inf_filter": true,
|
| 42 |
+
"include_num_input_tokens_seen": false,
|
| 43 |
+
"log_level": "passive",
|
| 44 |
+
"log_level_replica": "warning",
|
| 45 |
+
"disable_tqdm": null,
|
| 46 |
+
"report_to": [
|
| 47 |
+
"wandb"
|
| 48 |
+
],
|
| 49 |
+
"run_name": "/raid/icy/Thyme/output_dir_no123/v3-20260407-222221",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": "trackio",
|
| 52 |
+
"eval_strategy": "no",
|
| 53 |
+
"eval_steps": null,
|
| 54 |
+
"eval_delay": 0,
|
| 55 |
+
"per_device_eval_batch_size": 1,
|
| 56 |
+
"prediction_loss_only": false,
|
| 57 |
+
"eval_on_start": false,
|
| 58 |
+
"eval_do_concat_batches": true,
|
| 59 |
+
"eval_use_gather_object": false,
|
| 60 |
+
"eval_accumulation_steps": null,
|
| 61 |
+
"include_for_metrics": [],
|
| 62 |
+
"batch_eval_metrics": false,
|
| 63 |
+
"save_only_model": false,
|
| 64 |
+
"save_strategy": "epoch",
|
| 65 |
+
"save_steps": 500,
|
| 66 |
+
"save_on_each_node": false,
|
| 67 |
+
"save_total_limit": 1,
|
| 68 |
+
"enable_jit_checkpoint": false,
|
| 69 |
+
"push_to_hub": false,
|
| 70 |
+
"hub_token": null,
|
| 71 |
+
"hub_private_repo": null,
|
| 72 |
+
"hub_model_id": null,
|
| 73 |
+
"hub_strategy": "every_save",
|
| 74 |
+
"hub_always_push": false,
|
| 75 |
+
"hub_revision": null,
|
| 76 |
+
"load_best_model_at_end": false,
|
| 77 |
+
"metric_for_best_model": "loss",
|
| 78 |
+
"greater_is_better": false,
|
| 79 |
+
"ignore_data_skip": false,
|
| 80 |
+
"restore_callback_states_from_checkpoint": false,
|
| 81 |
+
"full_determinism": false,
|
| 82 |
+
"seed": 42,
|
| 83 |
+
"data_seed": 42,
|
| 84 |
+
"use_cpu": false,
|
| 85 |
+
"accelerator_config": {
|
| 86 |
+
"dispatch_batches": false
|
| 87 |
+
},
|
| 88 |
+
"parallelism_config": null,
|
| 89 |
+
"dataloader_drop_last": false,
|
| 90 |
+
"dataloader_num_workers": 4,
|
| 91 |
+
"dataloader_pin_memory": true,
|
| 92 |
+
"dataloader_persistent_workers": false,
|
| 93 |
+
"dataloader_prefetch_factor": null,
|
| 94 |
+
"remove_unused_columns": true,
|
| 95 |
+
"label_names": null,
|
| 96 |
+
"train_sampling_strategy": "random",
|
| 97 |
+
"length_column_name": "length",
|
| 98 |
+
"ddp_find_unused_parameters": null,
|
| 99 |
+
"ddp_bucket_cap_mb": null,
|
| 100 |
+
"ddp_broadcast_buffers": null,
|
| 101 |
+
"ddp_backend": null,
|
| 102 |
+
"ddp_timeout": 18000000,
|
| 103 |
+
"fsdp": [],
|
| 104 |
+
"fsdp_config": null,
|
| 105 |
+
"deepspeed": {
|
| 106 |
+
"fp16": {
|
| 107 |
+
"enabled": "auto",
|
| 108 |
+
"loss_scale": 0,
|
| 109 |
+
"loss_scale_window": 1000,
|
| 110 |
+
"initial_scale_power": 16,
|
| 111 |
+
"hysteresis": 2,
|
| 112 |
+
"min_loss_scale": 1
|
| 113 |
+
},
|
| 114 |
+
"bf16": {
|
| 115 |
+
"enabled": "auto"
|
| 116 |
+
},
|
| 117 |
+
"zero_optimization": {
|
| 118 |
+
"stage": 1,
|
| 119 |
+
"offload_optimizer": {
|
| 120 |
+
"device": "none",
|
| 121 |
+
"pin_memory": true
|
| 122 |
+
},
|
| 123 |
+
"allgather_partitions": true,
|
| 124 |
+
"allgather_bucket_size": 200000000.0,
|
| 125 |
+
"overlap_comm": false,
|
| 126 |
+
"reduce_scatter": true,
|
| 127 |
+
"reduce_bucket_size": 200000000.0,
|
| 128 |
+
"contiguous_gradients": true
|
| 129 |
+
},
|
| 130 |
+
"gradient_accumulation_steps": "auto",
|
| 131 |
+
"gradient_clipping": "auto",
|
| 132 |
+
"steps_per_print": 2000,
|
| 133 |
+
"train_batch_size": "auto",
|
| 134 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 135 |
+
"wall_clock_breakdown": false
|
| 136 |
+
},
|
| 137 |
+
"debug": null,
|
| 138 |
+
"skip_memory_metrics": true,
|
| 139 |
+
"do_train": false,
|
| 140 |
+
"do_eval": false,
|
| 141 |
+
"do_predict": false,
|
| 142 |
+
"resume_from_checkpoint": null,
|
| 143 |
+
"warmup_ratio": 0.05,
|
| 144 |
+
"logging_dir": "/raid/icy/Thyme/output_dir_no123/v3-20260407-222221/runs",
|
| 145 |
+
"local_rank": 0,
|
| 146 |
+
"sortish_sampler": false,
|
| 147 |
+
"predict_with_generate": false,
|
| 148 |
+
"generation_max_length": null,
|
| 149 |
+
"generation_num_beams": null,
|
| 150 |
+
"generation_config": null,
|
| 151 |
+
"tuner_backend": "peft",
|
| 152 |
+
"vit_gradient_checkpointing": null,
|
| 153 |
+
"router_aux_loss_coef": 0.0,
|
| 154 |
+
"enable_dft_loss": false,
|
| 155 |
+
"enable_channel_loss": false,
|
| 156 |
+
"safe_serialization": true,
|
| 157 |
+
"max_shard_size": "5GB",
|
| 158 |
+
"check_model": true,
|
| 159 |
+
"acc_strategy": "token",
|
| 160 |
+
"train_dataloader_shuffle": true,
|
| 161 |
+
"group_by_length": false,
|
| 162 |
+
"max_epochs": null,
|
| 163 |
+
"aligner_lr": null,
|
| 164 |
+
"vit_lr": null,
|
| 165 |
+
"use_logits_to_keep": null,
|
| 166 |
+
"ds3_gather_for_generation": true,
|
| 167 |
+
"resume_only_model": false,
|
| 168 |
+
"optimizer": null,
|
| 169 |
+
"loss_type": null,
|
| 170 |
+
"eval_metric": null,
|
| 171 |
+
"callbacks": [],
|
| 172 |
+
"early_stop_interval": null,
|
| 173 |
+
"eval_use_evalscope": false,
|
| 174 |
+
"eval_dataset": [],
|
| 175 |
+
"eval_dataset_args": null,
|
| 176 |
+
"eval_limit": null,
|
| 177 |
+
"eval_generation_config": null,
|
| 178 |
+
"extra_eval_args": null,
|
| 179 |
+
"tuner_type": "full",
|
| 180 |
+
"use_galore": false,
|
| 181 |
+
"galore_target_modules": null,
|
| 182 |
+
"galore_rank": 128,
|
| 183 |
+
"galore_update_proj_gap": 50,
|
| 184 |
+
"galore_scale": 1.0,
|
| 185 |
+
"galore_proj_type": "std",
|
| 186 |
+
"galore_optim_per_parameter": false,
|
| 187 |
+
"galore_with_embedding": false,
|
| 188 |
+
"galore_quantization": false,
|
| 189 |
+
"galore_proj_quant": false,
|
| 190 |
+
"galore_proj_bits": 4,
|
| 191 |
+
"galore_proj_group_size": 256,
|
| 192 |
+
"galore_cos_threshold": 0.4,
|
| 193 |
+
"galore_gamma_proj": 2,
|
| 194 |
+
"galore_queue_size": 5,
|
| 195 |
+
"lisa_activated_layers": 0,
|
| 196 |
+
"lisa_step_interval": 20,
|
| 197 |
+
"use_flash_ckpt": false,
|
| 198 |
+
"use_ray": false,
|
| 199 |
+
"ray_exp_name": null,
|
| 200 |
+
"device_groups": null,
|
| 201 |
+
"model": "/raid/icy/Thyme/output_dir_no123/v2-20260407-212707/checkpoint-243",
|
| 202 |
+
"model_type": "qwen2_5_vl",
|
| 203 |
+
"model_revision": null,
|
| 204 |
+
"task_type": "causal_lm",
|
| 205 |
+
"torch_dtype": "bfloat16",
|
| 206 |
+
"attn_impl": "flash_attn",
|
| 207 |
+
"experts_impl": null,
|
| 208 |
+
"new_special_tokens": [],
|
| 209 |
+
"num_labels": null,
|
| 210 |
+
"problem_type": null,
|
| 211 |
+
"rope_scaling": null,
|
| 212 |
+
"device_map": null,
|
| 213 |
+
"max_memory": {},
|
| 214 |
+
"max_model_len": null,
|
| 215 |
+
"local_repo_path": null,
|
| 216 |
+
"init_strategy": null,
|
| 217 |
+
"template": "qwen2_5_vl",
|
| 218 |
+
"system": null,
|
| 219 |
+
"max_length": 10240,
|
| 220 |
+
"truncation_strategy": "delete",
|
| 221 |
+
"max_pixels": null,
|
| 222 |
+
"agent_template": null,
|
| 223 |
+
"norm_bbox": null,
|
| 224 |
+
"use_chat_template": true,
|
| 225 |
+
"padding_side": "right",
|
| 226 |
+
"padding_free": false,
|
| 227 |
+
"loss_scale": "default",
|
| 228 |
+
"sequence_parallel_size": 1,
|
| 229 |
+
"template_backend": "swift",
|
| 230 |
+
"response_prefix": null,
|
| 231 |
+
"enable_thinking": null,
|
| 232 |
+
"add_non_thinking_prefix": true,
|
| 233 |
+
"dataset": [
|
| 234 |
+
"/raid/icy/data/Thyme_sft_data/jsonl/computation_without_image_no123.jsonl"
|
| 235 |
+
],
|
| 236 |
+
"val_dataset": [],
|
| 237 |
+
"cached_dataset": [],
|
| 238 |
+
"cached_val_dataset": [],
|
| 239 |
+
"split_dataset_ratio": 0.0,
|
| 240 |
+
"dataset_num_proc": 1,
|
| 241 |
+
"load_from_cache_file": false,
|
| 242 |
+
"dataset_shuffle": true,
|
| 243 |
+
"val_dataset_shuffle": false,
|
| 244 |
+
"streaming": false,
|
| 245 |
+
"interleave_prob": null,
|
| 246 |
+
"stopping_strategy": "first_exhausted",
|
| 247 |
+
"shuffle_buffer_size": 1000,
|
| 248 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 249 |
+
"columns": {},
|
| 250 |
+
"strict": false,
|
| 251 |
+
"model_name": null,
|
| 252 |
+
"model_author": null,
|
| 253 |
+
"custom_dataset_info": [],
|
| 254 |
+
"quant_method": null,
|
| 255 |
+
"quant_bits": null,
|
| 256 |
+
"hqq_axis": null,
|
| 257 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 258 |
+
"bnb_4bit_quant_type": "nf4",
|
| 259 |
+
"bnb_4bit_use_double_quant": true,
|
| 260 |
+
"bnb_4bit_quant_storage": null,
|
| 261 |
+
"max_new_tokens": 64,
|
| 262 |
+
"temperature": 0.0,
|
| 263 |
+
"top_k": null,
|
| 264 |
+
"top_p": null,
|
| 265 |
+
"repetition_penalty": null,
|
| 266 |
+
"num_beams": 1,
|
| 267 |
+
"stream": false,
|
| 268 |
+
"stop_words": [],
|
| 269 |
+
"logprobs": false,
|
| 270 |
+
"top_logprobs": null,
|
| 271 |
+
"structured_outputs_regex": null,
|
| 272 |
+
"train_type": "full",
|
| 273 |
+
"adapters": [],
|
| 274 |
+
"external_plugins": [],
|
| 275 |
+
"custom_register_path": [],
|
| 276 |
+
"model_kwargs": {},
|
| 277 |
+
"load_args": false,
|
| 278 |
+
"load_data_args": false,
|
| 279 |
+
"packing": false,
|
| 280 |
+
"packing_length": null,
|
| 281 |
+
"packing_num_proc": 1,
|
| 282 |
+
"lazy_tokenize": true,
|
| 283 |
+
"use_hf": false,
|
| 284 |
+
"ignore_args_error": false,
|
| 285 |
+
"use_swift_lora": false,
|
| 286 |
+
"freeze_parameters": [
|
| 287 |
+
"model.visual",
|
| 288 |
+
"model.visual.merger"
|
| 289 |
+
],
|
| 290 |
+
"freeze_parameters_regex": null,
|
| 291 |
+
"freeze_parameters_ratio": 0.0,
|
| 292 |
+
"trainable_parameters": [],
|
| 293 |
+
"trainable_parameters_regex": null,
|
| 294 |
+
"freeze_llm": false,
|
| 295 |
+
"freeze_vit": true,
|
| 296 |
+
"freeze_aligner": true,
|
| 297 |
+
"target_modules": [
|
| 298 |
+
"all-linear"
|
| 299 |
+
],
|
| 300 |
+
"target_regex": null,
|
| 301 |
+
"target_parameters": null,
|
| 302 |
+
"modules_to_save": [],
|
| 303 |
+
"lora_rank": 8,
|
| 304 |
+
"lora_alpha": 32,
|
| 305 |
+
"lora_dropout": 0.05,
|
| 306 |
+
"lora_bias": "none",
|
| 307 |
+
"lora_dtype": null,
|
| 308 |
+
"lorap_lr_ratio": null,
|
| 309 |
+
"use_rslora": false,
|
| 310 |
+
"use_dora": false,
|
| 311 |
+
"lora_ga_batch_size": 2,
|
| 312 |
+
"lora_ga_iters": 2,
|
| 313 |
+
"lora_ga_max_length": 1024,
|
| 314 |
+
"lora_ga_direction": "ArB2r",
|
| 315 |
+
"lora_ga_scale": "stable",
|
| 316 |
+
"lora_ga_stable_gamma": 16,
|
| 317 |
+
"init_weights": true,
|
| 318 |
+
"fourier_n_frequency": 2000,
|
| 319 |
+
"fourier_scaling": 300.0,
|
| 320 |
+
"boft_block_size": 4,
|
| 321 |
+
"boft_block_num": 0,
|
| 322 |
+
"boft_n_butterfly_factor": 1,
|
| 323 |
+
"boft_dropout": 0.0,
|
| 324 |
+
"vera_rank": 256,
|
| 325 |
+
"vera_projection_prng_key": 0,
|
| 326 |
+
"vera_dropout": 0.0,
|
| 327 |
+
"vera_d_initial": 0.1,
|
| 328 |
+
"adapter_act": "gelu",
|
| 329 |
+
"adapter_length": 128,
|
| 330 |
+
"adalora_target_r": 8,
|
| 331 |
+
"adalora_init_r": 12,
|
| 332 |
+
"adalora_tinit": 0,
|
| 333 |
+
"adalora_tfinal": 0,
|
| 334 |
+
"adalora_deltaT": 1,
|
| 335 |
+
"adalora_beta1": 0.85,
|
| 336 |
+
"adalora_beta2": 0.85,
|
| 337 |
+
"adalora_orth_reg_weight": 0.5,
|
| 338 |
+
"llamapro_num_new_blocks": 4,
|
| 339 |
+
"llamapro_num_groups": null,
|
| 340 |
+
"reft_layer_key": null,
|
| 341 |
+
"reft_layers": null,
|
| 342 |
+
"reft_rank": 4,
|
| 343 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 344 |
+
"reft_args": null,
|
| 345 |
+
"swanlab_token": null,
|
| 346 |
+
"swanlab_project": "ms-swift",
|
| 347 |
+
"swanlab_workspace": null,
|
| 348 |
+
"swanlab_exp_name": null,
|
| 349 |
+
"swanlab_notification_method": null,
|
| 350 |
+
"swanlab_webhook_url": null,
|
| 351 |
+
"swanlab_secret": null,
|
| 352 |
+
"swanlab_sender_email": null,
|
| 353 |
+
"swanlab_receiver_email": null,
|
| 354 |
+
"swanlab_smtp_server": null,
|
| 355 |
+
"swanlab_smtp_port": null,
|
| 356 |
+
"swanlab_email_language": "zh",
|
| 357 |
+
"swanlab_mode": "cloud",
|
| 358 |
+
"add_version": true,
|
| 359 |
+
"create_checkpoint_symlink": false,
|
| 360 |
+
"zero_hpz_partition_size": null,
|
| 361 |
+
"deepspeed_autotp_size": null,
|
| 362 |
+
"swift_version": "4.1.0.dev0",
|
| 363 |
+
"ckpt_dir": "/raid/icy/Thyme/output_dir_no123/v2-20260407-212707/checkpoint-243",
|
| 364 |
+
"rank": 0,
|
| 365 |
+
"global_world_size": 8,
|
| 366 |
+
"local_world_size": 8,
|
| 367 |
+
"model_suffix": "checkpoint-243",
|
| 368 |
+
"model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/raid/icy/Thyme/output_dir_no123/v2-20260407-212707/checkpoint-243', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 369 |
+
"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)], template='qwen2_5_vl', 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)], template='qwen2_5_vl', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', hf_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-RL', hf_model_id='XiaomiMiMo/MiMo-VL-7B-RL', model_path=None, ms_revision=None, hf_revision=None)], template='mimo_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen2_5VLLoader'>, template=None, 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, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
|
| 370 |
+
"model_dir": "/raid/icy/Thyme/output_dir_no123/v2-20260407-212707/checkpoint-243",
|
| 371 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen2_5_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen2_5VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system='You are a helpful assistant.', auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
|
| 372 |
+
"_val_dataset_exists": false,
|
| 373 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 374 |
+
"evaluation_strategy": "epoch",
|
| 375 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/raid/icy/Thyme/output_dir_no123/v3-20260407-222221', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=-1, learning_rate=1e-06, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.05, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=16, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='/raid/icy/Thyme/output_dir_no123/v3-20260407-222221', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=None, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.05, logging_dir='/raid/icy/Thyme/output_dir_no123/v3-20260407-222221/runs', local_rank=0, 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, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, 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, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, 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, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
|
| 376 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% 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
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% 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|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/config.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_size": 3584,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"model_type": "qwen2_5_vl",
|
| 11 |
+
"pad_token_id": 151643,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bos_token_id": 151643,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 3584,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 18944,
|
| 21 |
+
"layer_types": [
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 128000,
|
| 52 |
+
"max_window_layers": 28,
|
| 53 |
+
"model_type": "qwen2_5_vl_text",
|
| 54 |
+
"num_attention_heads": 28,
|
| 55 |
+
"num_hidden_layers": 28,
|
| 56 |
+
"num_key_value_heads": 4,
|
| 57 |
+
"pad_token_id": 151643,
|
| 58 |
+
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_parameters": {
|
| 60 |
+
"mrope_section": [
|
| 61 |
+
16,
|
| 62 |
+
24,
|
| 63 |
+
24
|
| 64 |
+
],
|
| 65 |
+
"rope_theta": 1000000.0,
|
| 66 |
+
"rope_type": "default",
|
| 67 |
+
"type": "mrope"
|
| 68 |
+
},
|
| 69 |
+
"sliding_window": null,
|
| 70 |
+
"use_cache": false,
|
| 71 |
+
"use_sliding_window": false,
|
| 72 |
+
"vocab_size": 152064
|
| 73 |
+
},
|
| 74 |
+
"tie_word_embeddings": false,
|
| 75 |
+
"transformers_version": "5.3.0",
|
| 76 |
+
"use_cache": false,
|
| 77 |
+
"video_token_id": 151656,
|
| 78 |
+
"vision_config": {
|
| 79 |
+
"depth": 32,
|
| 80 |
+
"dtype": "bfloat16",
|
| 81 |
+
"fullatt_block_indexes": [
|
| 82 |
+
7,
|
| 83 |
+
15,
|
| 84 |
+
23,
|
| 85 |
+
31
|
| 86 |
+
],
|
| 87 |
+
"hidden_act": "silu",
|
| 88 |
+
"hidden_size": 1280,
|
| 89 |
+
"in_channels": 3,
|
| 90 |
+
"in_chans": 3,
|
| 91 |
+
"initializer_range": 0.02,
|
| 92 |
+
"intermediate_size": 3420,
|
| 93 |
+
"model_type": "qwen2_5_vl",
|
| 94 |
+
"num_heads": 16,
|
| 95 |
+
"out_hidden_size": 3584,
|
| 96 |
+
"patch_size": 14,
|
| 97 |
+
"spatial_merge_size": 2,
|
| 98 |
+
"spatial_patch_size": 14,
|
| 99 |
+
"temporal_patch_size": 2,
|
| 100 |
+
"tokens_per_second": 2,
|
| 101 |
+
"window_size": 112
|
| 102 |
+
},
|
| 103 |
+
"vision_end_token_id": 151653,
|
| 104 |
+
"vision_start_token_id": 151652,
|
| 105 |
+
"vision_token_id": 151654
|
| 106 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "5.3.0"
|
| 12 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step48
|
output_dir_no123/v3-20260407-222221/checkpoint-48/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cbe44e4baeb5515540d6eb3f615a23bdae5b2a16dd6d34a9135adddab0a05e3
|
| 3 |
+
size 4976698728
|
output_dir_no123/v3-20260407-222221/checkpoint-48/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a0cc9ceb94201c26e0b6172d39bb959ff25cb3a60c95cc376c20981d28675c3
|
| 3 |
+
size 4932750984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e8fc45d24eba0a138c156dfae6544575d37f27bbb9d753ce4a0093444be737
|
| 3 |
+
size 4991495880
|
output_dir_no123/v3-20260407-222221/checkpoint-48/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e22f272f4f4ca7ad4d9d63cc5c137948917eb7af7f798e762572f5aa0f70adf9
|
| 3 |
+
size 1683468520
|
output_dir_no123/v3-20260407-222221/checkpoint-48/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8292166656,
|
| 4 |
+
"total_size": 16584333312
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 347 |
+
"visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 348 |
+
"visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 349 |
+
"visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 350 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 351 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 352 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 353 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 354 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 355 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 356 |
+
"visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 357 |
+
"visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 358 |
+
"visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 359 |
+
"visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 360 |
+
"visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 361 |
+
"visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 362 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 363 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 364 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 365 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 366 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 367 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 368 |
+
"visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 369 |
+
"visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 370 |
+
"visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 371 |
+
"visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 372 |
+
"visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 373 |
+
"visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 374 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 375 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 376 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 377 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 378 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 379 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 380 |
+
"visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 381 |
+
"visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 382 |
+
"visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 383 |
+
"visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 384 |
+
"visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 385 |
+
"visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 386 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 387 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 388 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 389 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 390 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 391 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 392 |
+
"visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 393 |
+
"visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 394 |
+
"visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 395 |
+
"visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 396 |
+
"visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 397 |
+
"visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 398 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 399 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 400 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 401 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 402 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 403 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 404 |
+
"visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 407 |
+
"visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 408 |
+
"visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 409 |
+
"visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 410 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 411 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 412 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 413 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 414 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 415 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 416 |
+
"visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 417 |
+
"visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 418 |
+
"visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 419 |
+
"visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 420 |
+
"visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 421 |
+
"visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 422 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 423 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 424 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 425 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 426 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 427 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 428 |
+
"visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 429 |
+
"visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 430 |
+
"visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 431 |
+
"visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 432 |
+
"visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 433 |
+
"visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 434 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 435 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 436 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 437 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 438 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 439 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 441 |
+
"visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
+
"visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 443 |
+
"visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 444 |
+
"visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 445 |
+
"visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 446 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 447 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 448 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 449 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 450 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 451 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 452 |
+
"visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
+
"visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 455 |
+
"visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 456 |
+
"visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 460 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 461 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 463 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 464 |
+
"visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 466 |
+
"visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 467 |
+
"visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 469 |
+
"visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 471 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 472 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 473 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 474 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 475 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 476 |
+
"visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
+
"visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 479 |
+
"visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 480 |
+
"visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 481 |
+
"visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 483 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 484 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 485 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 486 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 492 |
+
"visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 493 |
+
"visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 495 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 496 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 497 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 499 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 500 |
+
"visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 503 |
+
"visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 504 |
+
"visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 505 |
+
"visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 511 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 514 |
+
"visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 516 |
+
"visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 517 |
+
"visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 519 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 521 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 522 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 523 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 524 |
+
"visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 526 |
+
"visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 527 |
+
"visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 528 |
+
"visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 529 |
+
"visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 532 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 533 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 534 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 535 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 536 |
+
"visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 538 |
+
"visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 539 |
+
"visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 540 |
+
"visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 541 |
+
"visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 543 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 544 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 545 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 547 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 548 |
+
"visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 550 |
+
"visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 551 |
+
"visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 552 |
+
"visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 553 |
+
"visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 555 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 556 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 557 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 565 |
+
"visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 567 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 569 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 570 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 571 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 574 |
+
"visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 575 |
+
"visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 576 |
+
"visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 579 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 580 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 581 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 582 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 583 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 584 |
+
"visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 586 |
+
"visual.blocks.27.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 587 |
+
"visual.blocks.27.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 588 |
+
"visual.blocks.27.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 589 |
+
"visual.blocks.27.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 592 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 593 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 594 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 595 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 596 |
+
"visual.blocks.27.norm1.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"visual.blocks.27.norm2.weight": "model-00004-of-00004.safetensors",
|
| 598 |
+
"visual.blocks.28.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 599 |
+
"visual.blocks.28.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 600 |
+
"visual.blocks.28.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"visual.blocks.28.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 603 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 605 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 607 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 608 |
+
"visual.blocks.28.norm1.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"visual.blocks.28.norm2.weight": "model-00004-of-00004.safetensors",
|
| 610 |
+
"visual.blocks.29.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 611 |
+
"visual.blocks.29.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 612 |
+
"visual.blocks.29.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 613 |
+
"visual.blocks.29.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 615 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 616 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 617 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 618 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 619 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 620 |
+
"visual.blocks.29.norm1.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"visual.blocks.29.norm2.weight": "model-00004-of-00004.safetensors",
|
| 622 |
+
"visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 623 |
+
"visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 624 |
+
"visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 625 |
+
"visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 628 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 629 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 630 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 631 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 632 |
+
"visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 634 |
+
"visual.blocks.30.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 635 |
+
"visual.blocks.30.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"visual.blocks.30.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 637 |
+
"visual.blocks.30.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 639 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 642 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 643 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 644 |
+
"visual.blocks.30.norm1.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"visual.blocks.30.norm2.weight": "model-00004-of-00004.safetensors",
|
| 646 |
+
"visual.blocks.31.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 647 |
+
"visual.blocks.31.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 648 |
+
"visual.blocks.31.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 649 |
+
"visual.blocks.31.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 651 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 653 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 656 |
+
"visual.blocks.31.norm1.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"visual.blocks.31.norm2.weight": "model-00004-of-00004.safetensors",
|
| 658 |
+
"visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 661 |
+
"visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 663 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 664 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 665 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 666 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 667 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 668 |
+
"visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 669 |
+
"visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
+
"visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 671 |
+
"visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 673 |
+
"visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 675 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 676 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 677 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 681 |
+
"visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 682 |
+
"visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 683 |
+
"visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 684 |
+
"visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 685 |
+
"visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 686 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 687 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 688 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 689 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 690 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 691 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 692 |
+
"visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 693 |
+
"visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 694 |
+
"visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 695 |
+
"visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 696 |
+
"visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 697 |
+
"visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 699 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 700 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 701 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 702 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 705 |
+
"visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 707 |
+
"visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 708 |
+
"visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 709 |
+
"visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 710 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 711 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 712 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 713 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 714 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 716 |
+
"visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 717 |
+
"visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
+
"visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 729 |
+
"visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"visual.merger.ln_q.weight": "model-00004-of-00004.safetensors",
|
| 731 |
+
"visual.merger.mlp.0.bias": "model-00004-of-00004.safetensors",
|
| 732 |
+
"visual.merger.mlp.0.weight": "model-00004-of-00004.safetensors",
|
| 733 |
+
"visual.merger.mlp.2.bias": "model-00004-of-00004.safetensors",
|
| 734 |
+
"visual.merger.mlp.2.weight": "model-00004-of-00004.safetensors",
|
| 735 |
+
"visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors"
|
| 736 |
+
}
|
| 737 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.48145466,
|
| 10 |
+
0.4578275,
|
| 11 |
+
0.40821073
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.26862954,
|
| 16 |
+
0.26130258,
|
| 17 |
+
0.27577711
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 12845056,
|
| 25 |
+
"shortest_edge": 3136
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": false,
|
| 38 |
+
"image_mean": [
|
| 39 |
+
0.48145466,
|
| 40 |
+
0.4578275,
|
| 41 |
+
0.40821073
|
| 42 |
+
],
|
| 43 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.26862954,
|
| 46 |
+
0.26130258,
|
| 47 |
+
0.27577711
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 14,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 12845056,
|
| 58 |
+
"shortest_edge": 3136
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74386f26f36ed67f56395205881e5db2d0c28ffcbeed50dd95b28771d2dac588
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c88f9de084200454883a13c3717941ea3fd433e2f8735507fc30611f9c5501
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965b00d4cb4710ebab57c8787b9925bb3f77b8eeba94a186ec4bc1c2f326ef3f
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5dc374b8b9a4c45c950f9d136feab85a767081fa59f0c7d68ed3a62060c4949
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7c212fb779217f1edac0baf44f67b608eefc1e0e4e3f5a9dd7eb557032c1bc
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86e1effd626ce1e95dd68a0c8089fe19218f2b24dfe9e45ed2cab1c0ebc10ba1
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:799cc83f60dfc1c4243cfd6403592112414a2eec494e6832f10221c96ff62c20
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:586777c398770c3255d3a1f48c7fef44ea9d89117c627c9ea490e16bfd9a49ba
|
| 3 |
+
size 15984
|
output_dir_no123/v3-20260407-222221/checkpoint-48/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39788f5c12e60a3abb9757db4a3ac31b72797ca865bcb95bcdb8880929fce9a4
|
| 3 |
+
size 1064
|
output_dir_no123/v3-20260407-222221/checkpoint-48/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
output_dir_no123/v3-20260407-222221/checkpoint-48/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/trainer_state.json
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 48,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06477732793522267,
|
| 14 |
+
"grad_norm": 31.791717529296875,
|
| 15 |
+
"learning_rate": 3.333333333333333e-07,
|
| 16 |
+
"loss": 1.1534664630889893,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.7118055555555556
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.32388663967611336,
|
| 22 |
+
"grad_norm": 32.343624114990234,
|
| 23 |
+
"learning_rate": 9.95134034370785e-07,
|
| 24 |
+
"loss": 1.1402716636657715,
|
| 25 |
+
"step": 5,
|
| 26 |
+
"token_acc": 0.7121011615938833
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.6477732793522267,
|
| 30 |
+
"grad_norm": 29.438018798828125,
|
| 31 |
+
"learning_rate": 9.414737964294634e-07,
|
| 32 |
+
"loss": 0.9581957817077636,
|
| 33 |
+
"step": 10,
|
| 34 |
+
"token_acc": 0.7187350263536176
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.97165991902834,
|
| 38 |
+
"grad_norm": 10.981688499450684,
|
| 39 |
+
"learning_rate": 8.34565303179429e-07,
|
| 40 |
+
"loss": 0.5733880996704102,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"token_acc": 0.801109537299339
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.2591093117408907,
|
| 46 |
+
"grad_norm": 4.334969520568848,
|
| 47 |
+
"learning_rate": 6.87303296707956e-07,
|
| 48 |
+
"loss": 0.5193193912506103,
|
| 49 |
+
"step": 20,
|
| 50 |
+
"token_acc": 0.8446018172100481
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.582995951417004,
|
| 54 |
+
"grad_norm": 4.081247806549072,
|
| 55 |
+
"learning_rate": 5.174497483512505e-07,
|
| 56 |
+
"loss": 0.4201364517211914,
|
| 57 |
+
"step": 25,
|
| 58 |
+
"token_acc": 0.8691533451746596
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.9068825910931175,
|
| 62 |
+
"grad_norm": 3.199093818664551,
|
| 63 |
+
"learning_rate": 3.454915028125263e-07,
|
| 64 |
+
"loss": 0.4021294116973877,
|
| 65 |
+
"step": 30,
|
| 66 |
+
"token_acc": 0.8769431588940311
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.194331983805668,
|
| 70 |
+
"grad_norm": 4.008501052856445,
|
| 71 |
+
"learning_rate": 1.9216926233717084e-07,
|
| 72 |
+
"loss": 0.4186545372009277,
|
| 73 |
+
"step": 35,
|
| 74 |
+
"token_acc": 0.866737176097303
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.5182186234817814,
|
| 78 |
+
"grad_norm": 3.1948792934417725,
|
| 79 |
+
"learning_rate": 7.597595192178702e-08,
|
| 80 |
+
"loss": 0.38708205223083497,
|
| 81 |
+
"step": 40,
|
| 82 |
+
"token_acc": 0.8758045292014303
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.8421052631578947,
|
| 86 |
+
"grad_norm": 2.8163161277770996,
|
| 87 |
+
"learning_rate": 1.0926199633097154e-08,
|
| 88 |
+
"loss": 0.37027928829193113,
|
| 89 |
+
"step": 45,
|
| 90 |
+
"token_acc": 0.8794045819281312
|
| 91 |
+
}
|
| 92 |
+
],
|
| 93 |
+
"logging_steps": 5,
|
| 94 |
+
"max_steps": 48,
|
| 95 |
+
"num_input_tokens_seen": 0,
|
| 96 |
+
"num_train_epochs": 3,
|
| 97 |
+
"save_steps": 500,
|
| 98 |
+
"stateful_callbacks": {
|
| 99 |
+
"TrainerControl": {
|
| 100 |
+
"args": {
|
| 101 |
+
"should_epoch_stop": false,
|
| 102 |
+
"should_evaluate": false,
|
| 103 |
+
"should_log": false,
|
| 104 |
+
"should_save": true,
|
| 105 |
+
"should_training_stop": true
|
| 106 |
+
},
|
| 107 |
+
"attributes": {}
|
| 108 |
+
}
|
| 109 |
+
},
|
| 110 |
+
"total_flos": 2.982229387824333e+16,
|
| 111 |
+
"train_batch_size": 1,
|
| 112 |
+
"trial_name": null,
|
| 113 |
+
"trial_params": null
|
| 114 |
+
}
|
output_dir_no123/v3-20260407-222221/checkpoint-48/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2938849dec2df3bb07eb6b672951301e87981c8fc860654d86862315df21911
|
| 3 |
+
size 8312
|
output_dir_no123/v3-20260407-222221/checkpoint-48/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import json
|
| 25 |
+
from tqdm import tqdm
|
| 26 |
+
from collections import OrderedDict
|
| 27 |
+
from dataclasses import dataclass
|
| 28 |
+
|
| 29 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 30 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 31 |
+
from deepspeed.utils import logger
|
| 32 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 33 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 34 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
@dataclass
|
| 38 |
+
class zero_model_state:
|
| 39 |
+
buffers: dict()
|
| 40 |
+
param_shapes: dict()
|
| 41 |
+
shared_params: list
|
| 42 |
+
ds_version: int
|
| 43 |
+
frozen_param_shapes: dict()
|
| 44 |
+
frozen_param_fragments: dict()
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
debug = 0
|
| 48 |
+
|
| 49 |
+
# load to cpu
|
| 50 |
+
device = torch.device('cpu')
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def atoi(text):
|
| 54 |
+
return int(text) if text.isdigit() else text
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
def natural_keys(text):
|
| 58 |
+
'''
|
| 59 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 60 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 61 |
+
(See Toothy's implementation in the comments)
|
| 62 |
+
'''
|
| 63 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 67 |
+
if not os.path.isdir(checkpoint_dir):
|
| 68 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 69 |
+
|
| 70 |
+
# there should be only one file
|
| 71 |
+
if zero_stage <= 2:
|
| 72 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 73 |
+
elif zero_stage == 3:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 75 |
+
|
| 76 |
+
if not os.path.exists(file):
|
| 77 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 78 |
+
|
| 79 |
+
return file
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 83 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 84 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 85 |
+
|
| 86 |
+
if len(ckpt_files) == 0:
|
| 87 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 88 |
+
|
| 89 |
+
return ckpt_files
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
def get_optim_files(checkpoint_dir):
|
| 93 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
def get_model_state_files(checkpoint_dir):
|
| 97 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
def parse_model_states(files):
|
| 101 |
+
zero_model_states = []
|
| 102 |
+
for file in files:
|
| 103 |
+
state_dict = torch.load(file, map_location=device)
|
| 104 |
+
|
| 105 |
+
if BUFFER_NAMES not in state_dict:
|
| 106 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 107 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 108 |
+
if debug:
|
| 109 |
+
print("Found buffers:", buffer_names)
|
| 110 |
+
|
| 111 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 112 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 113 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 114 |
+
|
| 115 |
+
# collect parameters that are included in param_shapes
|
| 116 |
+
param_names = []
|
| 117 |
+
for s in param_shapes:
|
| 118 |
+
for name in s.keys():
|
| 119 |
+
param_names.append(name)
|
| 120 |
+
|
| 121 |
+
# update with frozen parameters
|
| 122 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 123 |
+
if frozen_param_shapes is not None:
|
| 124 |
+
if debug:
|
| 125 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 126 |
+
param_names += list(frozen_param_shapes.keys())
|
| 127 |
+
|
| 128 |
+
# handle shared params
|
| 129 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 130 |
+
|
| 131 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 132 |
+
|
| 133 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 134 |
+
|
| 135 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 136 |
+
param_shapes=param_shapes,
|
| 137 |
+
shared_params=shared_params,
|
| 138 |
+
ds_version=ds_version,
|
| 139 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 140 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 141 |
+
zero_model_states.append(z_model_state)
|
| 142 |
+
|
| 143 |
+
return zero_model_states
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 147 |
+
total_files = len(files)
|
| 148 |
+
state_dicts = []
|
| 149 |
+
for f in files:
|
| 150 |
+
state_dict = torch.load(f, map_location=device)
|
| 151 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 152 |
+
# and also handle the case where it was already removed by another helper script
|
| 153 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 154 |
+
state_dicts.append(state_dict)
|
| 155 |
+
|
| 156 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 157 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 158 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 159 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 160 |
+
|
| 161 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 162 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 163 |
+
# use the max of the partition_count to get the dp world_size.
|
| 164 |
+
|
| 165 |
+
if type(world_size) is list:
|
| 166 |
+
world_size = max(world_size)
|
| 167 |
+
|
| 168 |
+
if world_size != total_files:
|
| 169 |
+
raise ValueError(
|
| 170 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 171 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 172 |
+
)
|
| 173 |
+
|
| 174 |
+
# the groups are named differently in each stage
|
| 175 |
+
if zero_stage <= 2:
|
| 176 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 177 |
+
elif zero_stage == 3:
|
| 178 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 179 |
+
else:
|
| 180 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 181 |
+
|
| 182 |
+
if zero_stage <= 2:
|
| 183 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 184 |
+
elif zero_stage == 3:
|
| 185 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 186 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 187 |
+
#
|
| 188 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 189 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 190 |
+
|
| 191 |
+
fp32_flat_groups = [
|
| 192 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 193 |
+
]
|
| 194 |
+
|
| 195 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 199 |
+
"""
|
| 200 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 201 |
+
|
| 202 |
+
Args:
|
| 203 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 204 |
+
|
| 205 |
+
"""
|
| 206 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 207 |
+
|
| 208 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 209 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 210 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 211 |
+
|
| 212 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 213 |
+
|
| 214 |
+
zero_model_states = parse_model_states(model_files)
|
| 215 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 216 |
+
|
| 217 |
+
if zero_stage <= 2:
|
| 218 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 219 |
+
exclude_frozen_parameters)
|
| 220 |
+
elif zero_stage == 3:
|
| 221 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 222 |
+
exclude_frozen_parameters)
|
| 223 |
+
|
| 224 |
+
|
| 225 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 226 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 227 |
+
return
|
| 228 |
+
|
| 229 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 230 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 231 |
+
|
| 232 |
+
if debug:
|
| 233 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 235 |
+
|
| 236 |
+
wanted_params = len(frozen_param_shapes)
|
| 237 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 238 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 239 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 240 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 241 |
+
|
| 242 |
+
total_params = 0
|
| 243 |
+
total_numel = 0
|
| 244 |
+
for name, shape in frozen_param_shapes.items():
|
| 245 |
+
total_params += 1
|
| 246 |
+
unpartitioned_numel = shape.numel()
|
| 247 |
+
total_numel += unpartitioned_numel
|
| 248 |
+
|
| 249 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 250 |
+
|
| 251 |
+
if debug:
|
| 252 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 253 |
+
|
| 254 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
def _has_callable(obj, fn):
|
| 258 |
+
attr = getattr(obj, fn, None)
|
| 259 |
+
return callable(attr)
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 263 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 264 |
+
|
| 265 |
+
# Reconstruction protocol:
|
| 266 |
+
#
|
| 267 |
+
# XXX: document this
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
for i in range(world_size):
|
| 271 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 272 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 273 |
+
|
| 274 |
+
# XXX: memory usage doubles here (zero2)
|
| 275 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 276 |
+
merged_single_partition_of_fp32_groups = []
|
| 277 |
+
for i in range(num_param_groups):
|
| 278 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 279 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 280 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 281 |
+
avail_numel = sum(
|
| 282 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 283 |
+
|
| 284 |
+
if debug:
|
| 285 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 286 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 287 |
+
# not asserting if there is a mismatch due to possible padding
|
| 288 |
+
print(f"Have {avail_numel} numels to process.")
|
| 289 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 290 |
+
|
| 291 |
+
# params
|
| 292 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 293 |
+
# out-of-core computing solution
|
| 294 |
+
total_numel = 0
|
| 295 |
+
total_params = 0
|
| 296 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 297 |
+
offset = 0
|
| 298 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 299 |
+
for name, shape in shapes.items():
|
| 300 |
+
|
| 301 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 302 |
+
total_numel += unpartitioned_numel
|
| 303 |
+
total_params += 1
|
| 304 |
+
|
| 305 |
+
if debug:
|
| 306 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 307 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 308 |
+
offset += unpartitioned_numel
|
| 309 |
+
|
| 310 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 311 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 312 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 313 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 314 |
+
align_to = 2 * world_size
|
| 315 |
+
|
| 316 |
+
def zero2_align(x):
|
| 317 |
+
return align_to * math.ceil(x / align_to)
|
| 318 |
+
|
| 319 |
+
if debug:
|
| 320 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 321 |
+
|
| 322 |
+
offset = zero2_align(offset)
|
| 323 |
+
avail_numel = zero2_align(avail_numel)
|
| 324 |
+
|
| 325 |
+
if debug:
|
| 326 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 327 |
+
|
| 328 |
+
# Sanity check
|
| 329 |
+
if offset != avail_numel:
|
| 330 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 331 |
+
|
| 332 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 333 |
+
|
| 334 |
+
|
| 335 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 336 |
+
exclude_frozen_parameters):
|
| 337 |
+
state_dict = OrderedDict()
|
| 338 |
+
|
| 339 |
+
# buffers
|
| 340 |
+
buffers = zero_model_states[0].buffers
|
| 341 |
+
state_dict.update(buffers)
|
| 342 |
+
if debug:
|
| 343 |
+
print(f"added {len(buffers)} buffers")
|
| 344 |
+
|
| 345 |
+
if not exclude_frozen_parameters:
|
| 346 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 347 |
+
|
| 348 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 349 |
+
|
| 350 |
+
# recover shared parameters
|
| 351 |
+
for pair in zero_model_states[0].shared_params:
|
| 352 |
+
if pair[1] in state_dict:
|
| 353 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 354 |
+
|
| 355 |
+
return state_dict
|
| 356 |
+
|
| 357 |
+
|
| 358 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 359 |
+
remainder = unpartitioned_numel % world_size
|
| 360 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 361 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 362 |
+
return partitioned_numel, padding_numel
|
| 363 |
+
|
| 364 |
+
|
| 365 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 366 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 367 |
+
return
|
| 368 |
+
|
| 369 |
+
if debug:
|
| 370 |
+
for i in range(world_size):
|
| 371 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 372 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 373 |
+
|
| 374 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 375 |
+
wanted_params = len(frozen_param_shapes)
|
| 376 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 377 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 378 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 379 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 380 |
+
|
| 381 |
+
total_params = 0
|
| 382 |
+
total_numel = 0
|
| 383 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 384 |
+
total_params += 1
|
| 385 |
+
unpartitioned_numel = shape.numel()
|
| 386 |
+
total_numel += unpartitioned_numel
|
| 387 |
+
|
| 388 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 389 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 390 |
+
|
| 391 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
print(
|
| 395 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 396 |
+
)
|
| 397 |
+
|
| 398 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 399 |
+
|
| 400 |
+
|
| 401 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 402 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 403 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 404 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 405 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 406 |
+
|
| 407 |
+
# merge list of dicts, preserving order
|
| 408 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 409 |
+
|
| 410 |
+
if debug:
|
| 411 |
+
for i in range(world_size):
|
| 412 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 413 |
+
|
| 414 |
+
wanted_params = len(param_shapes)
|
| 415 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 416 |
+
# not asserting if there is a mismatch due to possible padding
|
| 417 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 418 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 419 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 420 |
+
|
| 421 |
+
# params
|
| 422 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 423 |
+
# out-of-core computing solution
|
| 424 |
+
offset = 0
|
| 425 |
+
total_numel = 0
|
| 426 |
+
total_params = 0
|
| 427 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
|
| 428 |
+
unpartitioned_numel = shape.numel()
|
| 429 |
+
total_numel += unpartitioned_numel
|
| 430 |
+
total_params += 1
|
| 431 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 432 |
+
|
| 433 |
+
if debug:
|
| 434 |
+
print(
|
| 435 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
# XXX: memory usage doubles here
|
| 439 |
+
state_dict[name] = torch.cat(
|
| 440 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 441 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 442 |
+
offset += partitioned_numel
|
| 443 |
+
|
| 444 |
+
offset *= world_size
|
| 445 |
+
|
| 446 |
+
# Sanity check
|
| 447 |
+
if offset != avail_numel:
|
| 448 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 449 |
+
|
| 450 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 454 |
+
exclude_frozen_parameters):
|
| 455 |
+
state_dict = OrderedDict()
|
| 456 |
+
|
| 457 |
+
# buffers
|
| 458 |
+
buffers = zero_model_states[0].buffers
|
| 459 |
+
state_dict.update(buffers)
|
| 460 |
+
if debug:
|
| 461 |
+
print(f"added {len(buffers)} buffers")
|
| 462 |
+
|
| 463 |
+
if not exclude_frozen_parameters:
|
| 464 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 465 |
+
|
| 466 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 467 |
+
|
| 468 |
+
# recover shared parameters
|
| 469 |
+
for pair in zero_model_states[0].shared_params:
|
| 470 |
+
if pair[1] in state_dict:
|
| 471 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 472 |
+
|
| 473 |
+
return state_dict
|
| 474 |
+
|
| 475 |
+
|
| 476 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 477 |
+
"""
|
| 478 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 479 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 480 |
+
via a model hub.
|
| 481 |
+
|
| 482 |
+
Args:
|
| 483 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 484 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 485 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 486 |
+
|
| 487 |
+
Returns:
|
| 488 |
+
- pytorch ``state_dict``
|
| 489 |
+
|
| 490 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 491 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 492 |
+
the checkpoint.
|
| 493 |
+
|
| 494 |
+
A typical usage might be ::
|
| 495 |
+
|
| 496 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 497 |
+
# do the training and checkpoint saving
|
| 498 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 499 |
+
model = model.cpu() # move to cpu
|
| 500 |
+
model.load_state_dict(state_dict)
|
| 501 |
+
# submit to model hub or save the model to share with others
|
| 502 |
+
|
| 503 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 504 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 505 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 506 |
+
|
| 507 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 508 |
+
|
| 509 |
+
"""
|
| 510 |
+
if tag is None:
|
| 511 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 512 |
+
if os.path.isfile(latest_path):
|
| 513 |
+
with open(latest_path, 'r') as fd:
|
| 514 |
+
tag = fd.read().strip()
|
| 515 |
+
else:
|
| 516 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 517 |
+
|
| 518 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 519 |
+
|
| 520 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 521 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 522 |
+
|
| 523 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 524 |
+
|
| 525 |
+
|
| 526 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 527 |
+
output_dir,
|
| 528 |
+
max_shard_size="5GB",
|
| 529 |
+
safe_serialization=False,
|
| 530 |
+
tag=None,
|
| 531 |
+
exclude_frozen_parameters=False):
|
| 532 |
+
"""
|
| 533 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 534 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 535 |
+
|
| 536 |
+
Args:
|
| 537 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 538 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 539 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 540 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 541 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 542 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 543 |
+
"""
|
| 544 |
+
# Dependency pre-check
|
| 545 |
+
if safe_serialization:
|
| 546 |
+
try:
|
| 547 |
+
from safetensors.torch import save_file
|
| 548 |
+
except ImportError:
|
| 549 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 550 |
+
raise
|
| 551 |
+
if max_shard_size is not None:
|
| 552 |
+
try:
|
| 553 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 554 |
+
except ImportError:
|
| 555 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 556 |
+
raise
|
| 557 |
+
|
| 558 |
+
# Convert zero checkpoint to state_dict
|
| 559 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 560 |
+
|
| 561 |
+
# Shard the model if it is too big.
|
| 562 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 563 |
+
if max_shard_size is not None:
|
| 564 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 565 |
+
state_dict_split = split_torch_state_dict_into_shards(state_dict,
|
| 566 |
+
filename_pattern=filename_pattern,
|
| 567 |
+
max_shard_size=max_shard_size)
|
| 568 |
+
else:
|
| 569 |
+
from collections import namedtuple
|
| 570 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 571 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 572 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 573 |
+
|
| 574 |
+
# Save the model
|
| 575 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 576 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 577 |
+
shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
|
| 578 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 579 |
+
if safe_serialization:
|
| 580 |
+
save_file(shard, output_path, metadata={"format": "pt"})
|
| 581 |
+
else:
|
| 582 |
+
torch.save(shard, output_path)
|
| 583 |
+
|
| 584 |
+
# Save index if sharded
|
| 585 |
+
if state_dict_split.is_sharded:
|
| 586 |
+
index = {
|
| 587 |
+
"metadata": state_dict_split.metadata,
|
| 588 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 589 |
+
}
|
| 590 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 591 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 592 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 593 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 594 |
+
f.write(content)
|
| 595 |
+
|
| 596 |
+
|
| 597 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 598 |
+
"""
|
| 599 |
+
1. Put the provided model to cpu
|
| 600 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 601 |
+
3. Load it into the provided model
|
| 602 |
+
|
| 603 |
+
Args:
|
| 604 |
+
- ``model``: the model object to update
|
| 605 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 606 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 607 |
+
|
| 608 |
+
Returns:
|
| 609 |
+
- ``model`: modified model
|
| 610 |
+
|
| 611 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 612 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 613 |
+
conveniently placed for you in the checkpoint folder.
|
| 614 |
+
|
| 615 |
+
A typical usage might be ::
|
| 616 |
+
|
| 617 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 618 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 619 |
+
# submit to model hub or save the model to share with others
|
| 620 |
+
|
| 621 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 622 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 623 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 624 |
+
|
| 625 |
+
"""
|
| 626 |
+
logger.info(f"Extracting fp32 weights")
|
| 627 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 628 |
+
|
| 629 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 630 |
+
model = model.cpu()
|
| 631 |
+
model.load_state_dict(state_dict, strict=False)
|
| 632 |
+
|
| 633 |
+
return model
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
if __name__ == "__main__":
|
| 637 |
+
parser = argparse.ArgumentParser()
|
| 638 |
+
parser.add_argument("checkpoint_dir",
|
| 639 |
+
type=str,
|
| 640 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 641 |
+
parser.add_argument("output_dir",
|
| 642 |
+
type=str,
|
| 643 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 644 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 645 |
+
parser.add_argument(
|
| 646 |
+
"--max_shard_size",
|
| 647 |
+
type=str,
|
| 648 |
+
default="5GB",
|
| 649 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 650 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 651 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 652 |
+
"without CPU OOM issues.")
|
| 653 |
+
parser.add_argument(
|
| 654 |
+
"--safe_serialization",
|
| 655 |
+
default=False,
|
| 656 |
+
action='store_true',
|
| 657 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 658 |
+
parser.add_argument("-t",
|
| 659 |
+
"--tag",
|
| 660 |
+
type=str,
|
| 661 |
+
default=None,
|
| 662 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 663 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 664 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 665 |
+
args = parser.parse_args()
|
| 666 |
+
|
| 667 |
+
debug = args.debug
|
| 668 |
+
|
| 669 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 670 |
+
args.output_dir,
|
| 671 |
+
max_shard_size=args.max_shard_size,
|
| 672 |
+
safe_serialization=args.safe_serialization,
|
| 673 |
+
tag=args.tag,
|
| 674 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|